Real-time dissemination of emergency warning messages in 5G enabled selfish vehicular social networks
- Ullah, Noor, Kong, Xiangjie, Lin, Limei, Alrashoud, Mubarak, Tolba, Amr, Xia, Feng
- Authors: Ullah, Noor , Kong, Xiangjie , Lin, Limei , Alrashoud, Mubarak , Tolba, Amr , Xia, Feng
- Date: 2020
- Type: Text , Journal article
- Relation: Computer Networks Vol. 182, no. (2020), p.
- Full Text:
- Reviewed:
- Description: This paper addresses the issues of selfishness, limited network resources, and their adverse effects on real-time dissemination of Emergency Warning Messages (EWMs) in modern Autonomous Moving Platforms (AMPs) such as Vehicular Social Networks (VSNs). For this purpose, we propose a social intelligence based identification mechanism to differentiate between a selfish and a cooperative node in the network. Therefore, we devise a crowdsensing based mechanism to calculate a tie-strength value based on several social metrics. Moreover, we design a recursive evolutionary algorithm for each node's reputation calculation and update. Given that, then we estimate each node's state-transition probability to select a super-spreader for rapid dissemination. In order to ensure a seamless and reliable dissemination process, we incorporate 5G network structure instead of conventional short range communication which is used in most vehicular networks at present. Finally, we design a real-time dissemination algorithm for EWMs and evaluate its performance in terms of network parameters such as delivery-ratio, delay, hop-count, and message-overhead for varying values of vehicular density, speed, and selfish nodes’ density based on realistic vehicular mobility traces. In addition, we present a comparative analysis of the performance of the proposed scheme with state-of-the-art dissemination schemes in VSNs. © 2020 Elsevier B.V.
- Authors: Ullah, Noor , Kong, Xiangjie , Lin, Limei , Alrashoud, Mubarak , Tolba, Amr , Xia, Feng
- Date: 2020
- Type: Text , Journal article
- Relation: Computer Networks Vol. 182, no. (2020), p.
- Full Text:
- Reviewed:
- Description: This paper addresses the issues of selfishness, limited network resources, and their adverse effects on real-time dissemination of Emergency Warning Messages (EWMs) in modern Autonomous Moving Platforms (AMPs) such as Vehicular Social Networks (VSNs). For this purpose, we propose a social intelligence based identification mechanism to differentiate between a selfish and a cooperative node in the network. Therefore, we devise a crowdsensing based mechanism to calculate a tie-strength value based on several social metrics. Moreover, we design a recursive evolutionary algorithm for each node's reputation calculation and update. Given that, then we estimate each node's state-transition probability to select a super-spreader for rapid dissemination. In order to ensure a seamless and reliable dissemination process, we incorporate 5G network structure instead of conventional short range communication which is used in most vehicular networks at present. Finally, we design a real-time dissemination algorithm for EWMs and evaluate its performance in terms of network parameters such as delivery-ratio, delay, hop-count, and message-overhead for varying values of vehicular density, speed, and selfish nodes’ density based on realistic vehicular mobility traces. In addition, we present a comparative analysis of the performance of the proposed scheme with state-of-the-art dissemination schemes in VSNs. © 2020 Elsevier B.V.
Heterogeneous graph learning for explainable recommendation over academic networks
- Chen, Xiangtai, Tang, Tao, Ren, Jing, Lee, Ivan, Chen, Honglong, Xia, Feng
- Authors: Chen, Xiangtai , Tang, Tao , Ren, Jing , Lee, Ivan , Chen, Honglong , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2021, Virtual, Online, 14-17 December 2021, ACM International Conference Proceeding Series p. 29-36
- Full Text:
- Reviewed:
- Description: With the explosive growth of new graduates with research degrees every year, unprecedented challenges arise for early-career researchers to find a job at a suitable institution. This study aims to understand the behavior of academic job transition and hence recommend suitable institutions for PhD graduates. Specifically, we design a deep learning model to predict the career move of early-career researchers and provide suggestions. The design is built on top of scholarly/academic networks, which contains abundant information about scientific collaboration among scholars and institutions. We construct a heterogeneous scholarly network to facilitate the exploring of the behavior of career moves and the recommendation of institutions for scholars. We devise an unsupervised learning model called HAI (Heterogeneous graph Attention InfoMax) which aggregates attention mechanism and mutual information for institution recommendation. Moreover, we propose scholar attention and meta-path attention to discover the hidden relationships between several meta-paths. With these mechanisms, HAI provides ordered recommendations with explainability. We evaluate HAI upon a real-world dataset against baseline methods. Experimental results verify the effectiveness and efficiency of our approach. © 2021 ACM.
- Authors: Chen, Xiangtai , Tang, Tao , Ren, Jing , Lee, Ivan , Chen, Honglong , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2021, Virtual, Online, 14-17 December 2021, ACM International Conference Proceeding Series p. 29-36
- Full Text:
- Reviewed:
- Description: With the explosive growth of new graduates with research degrees every year, unprecedented challenges arise for early-career researchers to find a job at a suitable institution. This study aims to understand the behavior of academic job transition and hence recommend suitable institutions for PhD graduates. Specifically, we design a deep learning model to predict the career move of early-career researchers and provide suggestions. The design is built on top of scholarly/academic networks, which contains abundant information about scientific collaboration among scholars and institutions. We construct a heterogeneous scholarly network to facilitate the exploring of the behavior of career moves and the recommendation of institutions for scholars. We devise an unsupervised learning model called HAI (Heterogeneous graph Attention InfoMax) which aggregates attention mechanism and mutual information for institution recommendation. Moreover, we propose scholar attention and meta-path attention to discover the hidden relationships between several meta-paths. With these mechanisms, HAI provides ordered recommendations with explainability. We evaluate HAI upon a real-world dataset against baseline methods. Experimental results verify the effectiveness and efficiency of our approach. © 2021 ACM.
Lost at starting line : predicting maladaptation of university freshmen based on educational big data
- Guo, Teng, Bai, Xiaomei, Zhen, Shihao, Abid, Shagufta, Xia, Feng
- Authors: Guo, Teng , Bai, Xiaomei , Zhen, Shihao , Abid, Shagufta , Xia, Feng
- Date: 2023
- Type: Text , Journal article
- Relation: Journal of the Association for Information Science and Technology Vol. 74, no. 1 (2023), p. 17-32
- Full Text:
- Reviewed:
- Description: The transition from secondary education to higher education could be challenging for most freshmen. For students who fail to adjust to university life smoothly, their status may worsen if the university cannot offer timely and proper guidance. Helping students adapt to university life is a long-term goal for any academic institution. Therefore, understanding the nature of the maladaptation phenomenon and the early prediction of “at-risk” students are crucial tasks that urgently need to be tackled effectively. This article aims to analyze the relevant factors that affect the maladaptation phenomenon and predict this phenomenon in advance. We develop a prediction framework (MAladaptive STudEnt pRediction, MASTER) for the early prediction of students with maladaptation. First, our framework uses the SMOTE (Synthetic Minority Oversampling Technique) algorithm to solve the data label imbalance issue. Moreover, a novel ensemble algorithm, priority forest, is proposed for outputting ranks instead of binary results, which enables us to perform proactive interventions in a prioritized manner where limited education resources are available. Experimental results on real-world education datasets demonstrate that the MASTER framework outperforms other state-of-art methods. © 2022 The Authors. Journal of the Association for Information Science and Technology published by Wiley Periodicals LLC on behalf of Association for Information Science and Technology.
- Authors: Guo, Teng , Bai, Xiaomei , Zhen, Shihao , Abid, Shagufta , Xia, Feng
- Date: 2023
- Type: Text , Journal article
- Relation: Journal of the Association for Information Science and Technology Vol. 74, no. 1 (2023), p. 17-32
- Full Text:
- Reviewed:
- Description: The transition from secondary education to higher education could be challenging for most freshmen. For students who fail to adjust to university life smoothly, their status may worsen if the university cannot offer timely and proper guidance. Helping students adapt to university life is a long-term goal for any academic institution. Therefore, understanding the nature of the maladaptation phenomenon and the early prediction of “at-risk” students are crucial tasks that urgently need to be tackled effectively. This article aims to analyze the relevant factors that affect the maladaptation phenomenon and predict this phenomenon in advance. We develop a prediction framework (MAladaptive STudEnt pRediction, MASTER) for the early prediction of students with maladaptation. First, our framework uses the SMOTE (Synthetic Minority Oversampling Technique) algorithm to solve the data label imbalance issue. Moreover, a novel ensemble algorithm, priority forest, is proposed for outputting ranks instead of binary results, which enables us to perform proactive interventions in a prioritized manner where limited education resources are available. Experimental results on real-world education datasets demonstrate that the MASTER framework outperforms other state-of-art methods. © 2022 The Authors. Journal of the Association for Information Science and Technology published by Wiley Periodicals LLC on behalf of Association for Information Science and Technology.
RMGen : a tri-layer vehicular trajectory data generation model exploring urban region division and mobility pattern
- Kong, Xiangjie, Chen, Qiao, Hou, Mingliang, Rahim, Azizur, Ma, Kai, Xia, Feng
- Authors: Kong, Xiangjie , Chen, Qiao , Hou, Mingliang , Rahim, Azizur , Ma, Kai , Xia, Feng
- Date: 2022
- Type: Text , Journal article
- Relation: IEEE Transactions on Vehicular Technology Vol. 71, no. 9 (2022), p. 9225-9238
- Full Text:
- Reviewed:
- Description: As an important branch of the Internet of Things (IoT), the Internet of Vehicles (IoV) has attracted extensive attention in the research field. To deeply study the IoV and build a vehicle spatiotemporal interaction network, it is necessary to use the trajectory data of private cars. However, due to privacy and security protection policies and other reasons, the data set of private cars cannot be obtained, which hinders the research on the social attributes of vehicles in the IoV. Most of the previous work generated the same type of data, and how to generate private car data sets from various existing data sets is a huge challenge. In this paper, we propose a tri-layer framework to solve this problem. First, we propose a novel region division scheme that considers detailed inter-region relations connected by traffic flux. Second, a new spatial-temporal interaction model is developed to estimate the traffic flow between two regions. Third, we devise an evaluation pipeline to validate generation results from microscopic and macroscopic perspectives. Qualitative and quantitative results demonstrate that the data generated in heavy density scenarios can provide strong data support for downstream IoV and mobility research tasks. © 1967-2012 IEEE.
- Authors: Kong, Xiangjie , Chen, Qiao , Hou, Mingliang , Rahim, Azizur , Ma, Kai , Xia, Feng
- Date: 2022
- Type: Text , Journal article
- Relation: IEEE Transactions on Vehicular Technology Vol. 71, no. 9 (2022), p. 9225-9238
- Full Text:
- Reviewed:
- Description: As an important branch of the Internet of Things (IoT), the Internet of Vehicles (IoV) has attracted extensive attention in the research field. To deeply study the IoV and build a vehicle spatiotemporal interaction network, it is necessary to use the trajectory data of private cars. However, due to privacy and security protection policies and other reasons, the data set of private cars cannot be obtained, which hinders the research on the social attributes of vehicles in the IoV. Most of the previous work generated the same type of data, and how to generate private car data sets from various existing data sets is a huge challenge. In this paper, we propose a tri-layer framework to solve this problem. First, we propose a novel region division scheme that considers detailed inter-region relations connected by traffic flux. Second, a new spatial-temporal interaction model is developed to estimate the traffic flow between two regions. Third, we devise an evaluation pipeline to validate generation results from microscopic and macroscopic perspectives. Qualitative and quantitative results demonstrate that the data generated in heavy density scenarios can provide strong data support for downstream IoV and mobility research tasks. © 1967-2012 IEEE.
Predicting mental health problems with personality, behavior, and social networks
- Zhang, Dongyu, Guo, Teng, Han, Shiyu, Vahabli, Sadaf, Naseriparsa, Mehdi, Xia, Feng
- Authors: Zhang, Dongyu , Guo, Teng , Han, Shiyu , Vahabli, Sadaf , Naseriparsa, Mehdi , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 IEEE International Conference on Big Data, Big Data 2021, virtual online, 15-18 December 2021, Proceedings - 2021 IEEE International Conference on Big Data, Big Data 2021 p. 4537-4546
- Full Text:
- Reviewed:
- Description: Mental health is an integral part of human health and well-being. Unhealthy mentality leads to serious consequences such as self-mutilation and suicide, especially for college students. While the literature focused on analysing the relationship between mental health and a single factor such as personality or behavior, accurate prediction is yet to be achieved due to the lack of cross-dimensional analysis and multi-dimensional joint prediction. To this end, this work proposes leveraging multiple factors from three crucial dimensions of mental health: behaviors, personality, and social networks. We recruited 490 college students, and collected their behavioral records from smart cards. In addition, we extracted their psychological traits from questionnaires, and social networks by conducting the survey on the nominating community members. We created a neural network-based model to integrate behavioral, psychological, and social network factors to predict mental health problems. The experimental results verify the efficacy of the proposed model, and demonstrate that the classification model of various factors effectively predicts the students' mental issues. © 2021 IEEE.
- Authors: Zhang, Dongyu , Guo, Teng , Han, Shiyu , Vahabli, Sadaf , Naseriparsa, Mehdi , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 IEEE International Conference on Big Data, Big Data 2021, virtual online, 15-18 December 2021, Proceedings - 2021 IEEE International Conference on Big Data, Big Data 2021 p. 4537-4546
- Full Text:
- Reviewed:
- Description: Mental health is an integral part of human health and well-being. Unhealthy mentality leads to serious consequences such as self-mutilation and suicide, especially for college students. While the literature focused on analysing the relationship between mental health and a single factor such as personality or behavior, accurate prediction is yet to be achieved due to the lack of cross-dimensional analysis and multi-dimensional joint prediction. To this end, this work proposes leveraging multiple factors from three crucial dimensions of mental health: behaviors, personality, and social networks. We recruited 490 college students, and collected their behavioral records from smart cards. In addition, we extracted their psychological traits from questionnaires, and social networks by conducting the survey on the nominating community members. We created a neural network-based model to integrate behavioral, psychological, and social network factors to predict mental health problems. The experimental results verify the efficacy of the proposed model, and demonstrate that the classification model of various factors effectively predicts the students' mental issues. © 2021 IEEE.
CHIEF : clustering With higher-order motifs in big networks
- Xia, Feng, Yu, Shuo, Liu, Chengfei, Li, Jianxin, Lee, Ivan
- Authors: Xia, Feng , Yu, Shuo , Liu, Chengfei , Li, Jianxin , Lee, Ivan
- Date: 2022
- Type: Text , Journal article
- Relation: IEEE Transactions on Network Science and Engineering Vol. 9, no. 3 (2022), p. 990-1005
- Full Text:
- Reviewed:
- Description: Clustering network vertices is an enabler of various applications such as social computing and Internet of Things. However, challenges arise for clustering when networks increase in scale. This paper proposes CHIEF (Clustering with HIgher-ordEr motiFs), a solution which consists of two motif clustering techniques: standard acceleration CHIEF-ST and approximate acceleration CHIEF-AP. Both algorithms firstly find the maximal $k$-edge-connected subgraphs within the target networks to lower the network scale by optimizing the network structure with maximal $k$-edge-connected subgraphs, and then use heterogeneous four-node motifs clustering in higher-order dense networks. For CHIEF-ST, we illustrate that all target motifs will be kept after this procedure when the minimum node degree of the target motif is equal or greater than $k$. For CHIEF-AP, we prove that the eigenvalues of the adjacency matrix and the Laplacian matrix are relatively stable after this step. CHIEF offers an improved efficiency of motif clustering for big networks, and it verifies higher-order motif significance. Experiments on real and synthetic networks demonstrate that the proposed solutions outperform baseline approaches in large network analysis, and higher-order motifs outperform traditional triangle motifs in clustering. © 2022 IEEE Computer Society. All rights reserved.
- Authors: Xia, Feng , Yu, Shuo , Liu, Chengfei , Li, Jianxin , Lee, Ivan
- Date: 2022
- Type: Text , Journal article
- Relation: IEEE Transactions on Network Science and Engineering Vol. 9, no. 3 (2022), p. 990-1005
- Full Text:
- Reviewed:
- Description: Clustering network vertices is an enabler of various applications such as social computing and Internet of Things. However, challenges arise for clustering when networks increase in scale. This paper proposes CHIEF (Clustering with HIgher-ordEr motiFs), a solution which consists of two motif clustering techniques: standard acceleration CHIEF-ST and approximate acceleration CHIEF-AP. Both algorithms firstly find the maximal $k$-edge-connected subgraphs within the target networks to lower the network scale by optimizing the network structure with maximal $k$-edge-connected subgraphs, and then use heterogeneous four-node motifs clustering in higher-order dense networks. For CHIEF-ST, we illustrate that all target motifs will be kept after this procedure when the minimum node degree of the target motif is equal or greater than $k$. For CHIEF-AP, we prove that the eigenvalues of the adjacency matrix and the Laplacian matrix are relatively stable after this step. CHIEF offers an improved efficiency of motif clustering for big networks, and it verifies higher-order motif significance. Experiments on real and synthetic networks demonstrate that the proposed solutions outperform baseline approaches in large network analysis, and higher-order motifs outperform traditional triangle motifs in clustering. © 2022 IEEE Computer Society. All rights reserved.
Cross network representation matching with outliers
- Hou, Mingliang, Ren, Jing, Febrinanto, Febrinanto, Shehzad, Ahsan, Xia, Feng
- Authors: Hou, Mingliang , Ren, Jing , Febrinanto, Febrinanto , Shehzad, Ahsan , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 21st IEEE International Conference on Data Mining Workshops, ICDMW 2021, Virtual, online, 7-10 December 2021, IEEE International Conference on Data Mining Workshops, ICDMW Vol. 2021-December, p. 951-958
- Full Text:
- Reviewed:
- Description: Research has revealed the effectiveness of network representation techniques in handling diverse downstream machine learning tasks upon graph structured data. However, most network representation methods only seek to learn information in a single network, which fails to learn knowledge across different networks. Moreover, outliers in real-world networks pose great challenges to match distribution shift of learned embeddings. In this paper, we propose a novel joint learning framework, called CrossOSR, to learn network-invariant embeddings across different networks in the presence of outliers in the source network. To learn outlier-aware representations, a modified graph convolutional network (GCN) layer is designed to indicate the potential outliers. To learn more fine-grained information between different domains, a subdomain matching is adopted to align the shift distribution of learned vectors. To learn robust network representations, the learned indicator is utilized to smooth the noise effect from source domain to target domain. Extensive experimental results on three real-world datasets in the node classification task show that the proposed framework yields state-of-the-art cross network representation matching performance with outliers in the source network. © 2021 IEEE.
- Authors: Hou, Mingliang , Ren, Jing , Febrinanto, Febrinanto , Shehzad, Ahsan , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 21st IEEE International Conference on Data Mining Workshops, ICDMW 2021, Virtual, online, 7-10 December 2021, IEEE International Conference on Data Mining Workshops, ICDMW Vol. 2021-December, p. 951-958
- Full Text:
- Reviewed:
- Description: Research has revealed the effectiveness of network representation techniques in handling diverse downstream machine learning tasks upon graph structured data. However, most network representation methods only seek to learn information in a single network, which fails to learn knowledge across different networks. Moreover, outliers in real-world networks pose great challenges to match distribution shift of learned embeddings. In this paper, we propose a novel joint learning framework, called CrossOSR, to learn network-invariant embeddings across different networks in the presence of outliers in the source network. To learn outlier-aware representations, a modified graph convolutional network (GCN) layer is designed to indicate the potential outliers. To learn more fine-grained information between different domains, a subdomain matching is adopted to align the shift distribution of learned vectors. To learn robust network representations, the learned indicator is utilized to smooth the noise effect from source domain to target domain. Extensive experimental results on three real-world datasets in the node classification task show that the proposed framework yields state-of-the-art cross network representation matching performance with outliers in the source network. © 2021 IEEE.
Higher-order structure based anomaly detection on attributed networks
- Yuan, Xu, Zhou, Na, Yu, Shuo, Huang, Huafei, Chen, Zhikui, Xia, Feng
- Authors: Yuan, Xu , Zhou, Na , Yu, Shuo , Huang, Huafei , Chen, Zhikui , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 IEEE International Conference on Big Data, Big Data 2021, virtual online, 15-18 December 2021, Proceedings - 2021 IEEE International Conference on Big Data, Big Data 2021 p. 2691-2700
- Full Text:
- Reviewed:
- Description: Anomaly detection (such as telecom fraud detection and medical image detection) has attracted the increasing attention of people. The complex interaction between multiple entities widely exists in the network, which can reflect specific human behavior patterns. Such patterns can be modeled by higher-order network structures, thus benefiting anomaly detection on attributed networks. However, due to the lack of an effective mechanism in most existing graph learning methods, these complex interaction patterns fail to be applied in detecting anomalies, hindering the progress of anomaly detection to some extent. In order to address the aforementioned issue, we present a higher-order structure based anomaly detection (GUIDE) method. We exploit attribute autoencoder and structure autoencoder to reconstruct node attributes and higher-order structures, respectively. Moreover, we design a graph attention layer to evaluate the significance of neighbors to nodes through their higher-order structure differences. Finally, we leverage node attribute and higher-order structure reconstruction errors to find anomalies. Extensive experiments on five real-world datasets (i.e., ACM, Citation, Cora, DBLP, and Pubmed) are implemented to verify the effectiveness of GUIDE. Experimental results in terms of ROC-AUC, PR-AUC, and Recall@K show that GUIDE significantly outperforms the state-of-art methods. © 2021 IEEE.
- Authors: Yuan, Xu , Zhou, Na , Yu, Shuo , Huang, Huafei , Chen, Zhikui , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 IEEE International Conference on Big Data, Big Data 2021, virtual online, 15-18 December 2021, Proceedings - 2021 IEEE International Conference on Big Data, Big Data 2021 p. 2691-2700
- Full Text:
- Reviewed:
- Description: Anomaly detection (such as telecom fraud detection and medical image detection) has attracted the increasing attention of people. The complex interaction between multiple entities widely exists in the network, which can reflect specific human behavior patterns. Such patterns can be modeled by higher-order network structures, thus benefiting anomaly detection on attributed networks. However, due to the lack of an effective mechanism in most existing graph learning methods, these complex interaction patterns fail to be applied in detecting anomalies, hindering the progress of anomaly detection to some extent. In order to address the aforementioned issue, we present a higher-order structure based anomaly detection (GUIDE) method. We exploit attribute autoencoder and structure autoencoder to reconstruct node attributes and higher-order structures, respectively. Moreover, we design a graph attention layer to evaluate the significance of neighbors to nodes through their higher-order structure differences. Finally, we leverage node attribute and higher-order structure reconstruction errors to find anomalies. Extensive experiments on five real-world datasets (i.e., ACM, Citation, Cora, DBLP, and Pubmed) are implemented to verify the effectiveness of GUIDE. Experimental results in terms of ROC-AUC, PR-AUC, and Recall@K show that GUIDE significantly outperforms the state-of-art methods. © 2021 IEEE.
Edge computing for Internet of Everything : a survey
- Kong, Xiangjie, Wu, Yuhan, Wang, Hui, Xia, Feng
- Authors: Kong, Xiangjie , Wu, Yuhan , Wang, Hui , Xia, Feng
- Date: 2022
- Type: Text , Journal article
- Relation: IEEE Internet of Things Journal Vol. 9, no. 23 (2022), p. 23472-23485
- Full Text:
- Reviewed:
- Description: In this era of the Internet of Everything (IoE), edge computing has emerged as the critical enabling technology to solve a series of issues caused by an increasing amount of interconnected devices and large-scale data transmission. However, the deficiencies of edge computing paradigm are gradually being magnified in the context of IoE, especially in terms of service migration, security and privacy preservation, and deployment issues of edge node. These issues can not be well addressed by conventional approaches. Thanks to the rapid development of upcoming technologies, such as artificial intelligence (AI), blockchain, and microservices, novel and more effective solutions have emerged and been applied to solve existing challenges. In addition, edge computing can be deeply integrated with technologies in other domains (e.g., AI, blockchain, 6G, and digital twin) through interdisciplinary intersection and practice, releasing the potential for mutual benefit. These promising integrations need to be further explored and researched. In addition, edge computing provides strong support in applications scenarios, such as remote working, new physical retail industries, and digital advertising, which has greatly changed the way we live, work, and study. In this article, we present an up-to-date survey of the edge computing research. In addition to introducing the definition, model, and characteristics of edge computing, we discuss a set of key issues in edge computing and novel solutions supported by emerging technologies in IoE era. Furthermore, we explore the potential and promising trends from the perspective of technology integration. Finally, new application scenarios and the final form of edge computing are discussed. © 2014 IEEE.
- Authors: Kong, Xiangjie , Wu, Yuhan , Wang, Hui , Xia, Feng
- Date: 2022
- Type: Text , Journal article
- Relation: IEEE Internet of Things Journal Vol. 9, no. 23 (2022), p. 23472-23485
- Full Text:
- Reviewed:
- Description: In this era of the Internet of Everything (IoE), edge computing has emerged as the critical enabling technology to solve a series of issues caused by an increasing amount of interconnected devices and large-scale data transmission. However, the deficiencies of edge computing paradigm are gradually being magnified in the context of IoE, especially in terms of service migration, security and privacy preservation, and deployment issues of edge node. These issues can not be well addressed by conventional approaches. Thanks to the rapid development of upcoming technologies, such as artificial intelligence (AI), blockchain, and microservices, novel and more effective solutions have emerged and been applied to solve existing challenges. In addition, edge computing can be deeply integrated with technologies in other domains (e.g., AI, blockchain, 6G, and digital twin) through interdisciplinary intersection and practice, releasing the potential for mutual benefit. These promising integrations need to be further explored and researched. In addition, edge computing provides strong support in applications scenarios, such as remote working, new physical retail industries, and digital advertising, which has greatly changed the way we live, work, and study. In this article, we present an up-to-date survey of the edge computing research. In addition to introducing the definition, model, and characteristics of edge computing, we discuss a set of key issues in edge computing and novel solutions supported by emerging technologies in IoE era. Furthermore, we explore the potential and promising trends from the perspective of technology integration. Finally, new application scenarios and the final form of edge computing are discussed. © 2014 IEEE.
Efficient anomaly recognition using surveillance videos
- Saleem, Gulshan, Bajwa, Usama, Raza, Rana, Alqahtani, Fayez, Tolba, Amr, Xia, Feng
- Authors: Saleem, Gulshan , Bajwa, Usama , Raza, Rana , Alqahtani, Fayez , Tolba, Amr , Xia, Feng
- Date: 2022
- Type: Text , Journal article
- Relation: PeerJ Computer Science Vol. 8, no. (2022), p.
- Full Text:
- Reviewed:
- Description: Smart surveillance is a difficult task that is gaining popularity due to its direct link to human safety. Today, many indoor and outdoor surveillance systems are in use at public places and smart cities. Because these systems are expensive to deploy, these are out of reach for the vast majority of the public and private sectors. Due to the lack of a precise definition of an anomaly, automated surveillance is a challenging task, especially when large amounts of data, such as 24/7 CCTV footage, must be processed. When implementing such systems in real-time environments, the high computational resource requirements for automated surveillance becomes a major bottleneck. Another challenge is to recognize anomalies accurately as achieving high accuracy while reducing computational cost is more challenging. To address these challenge, this research is based on the developing a system that is both efficient and cost effective. Although 3D convolutional neural networks have proven to be accurate, they are prohibitively expensive for practical use, particularly in real-time surveillance. In this article, we present two contributions: a resource-efficient framework for anomaly recognition problems and two-class and multi-class anomaly recognition on spatially augmented surveillance videos. This research aims to address the problem of computation overhead while maintaining recognition accuracy. The proposed Temporal based Anomaly Recognizer (TAR) framework combines a partial shift strategy with a 2D convolutional architecture-based model, namely MobileNetV2. Extensive experiments were carried out to evaluate the model's performance on the UCF Crime dataset, with MobileNetV2 as the baseline architecture; it achieved an accuracy of 88% which is 2.47% increased performance than available state-of-the-art. The proposed framework achieves 52.7% accuracy for multiclass anomaly recognition on the UCF Crime2Local dataset. The proposed model has been tested in real-time camera stream settings and can handle six streams simultaneously without the need for additional resources. © Copyright 2022 Saleem et al.
- Authors: Saleem, Gulshan , Bajwa, Usama , Raza, Rana , Alqahtani, Fayez , Tolba, Amr , Xia, Feng
- Date: 2022
- Type: Text , Journal article
- Relation: PeerJ Computer Science Vol. 8, no. (2022), p.
- Full Text:
- Reviewed:
- Description: Smart surveillance is a difficult task that is gaining popularity due to its direct link to human safety. Today, many indoor and outdoor surveillance systems are in use at public places and smart cities. Because these systems are expensive to deploy, these are out of reach for the vast majority of the public and private sectors. Due to the lack of a precise definition of an anomaly, automated surveillance is a challenging task, especially when large amounts of data, such as 24/7 CCTV footage, must be processed. When implementing such systems in real-time environments, the high computational resource requirements for automated surveillance becomes a major bottleneck. Another challenge is to recognize anomalies accurately as achieving high accuracy while reducing computational cost is more challenging. To address these challenge, this research is based on the developing a system that is both efficient and cost effective. Although 3D convolutional neural networks have proven to be accurate, they are prohibitively expensive for practical use, particularly in real-time surveillance. In this article, we present two contributions: a resource-efficient framework for anomaly recognition problems and two-class and multi-class anomaly recognition on spatially augmented surveillance videos. This research aims to address the problem of computation overhead while maintaining recognition accuracy. The proposed Temporal based Anomaly Recognizer (TAR) framework combines a partial shift strategy with a 2D convolutional architecture-based model, namely MobileNetV2. Extensive experiments were carried out to evaluate the model's performance on the UCF Crime dataset, with MobileNetV2 as the baseline architecture; it achieved an accuracy of 88% which is 2.47% increased performance than available state-of-the-art. The proposed framework achieves 52.7% accuracy for multiclass anomaly recognition on the UCF Crime2Local dataset. The proposed model has been tested in real-time camera stream settings and can handle six streams simultaneously without the need for additional resources. © Copyright 2022 Saleem et al.
GraphLearning’22: 1st International Workshop on Graph Learning
- Xia, Feng, Lambiotte, Renaud, Aggarwal, Charu
- Authors: Xia, Feng , Lambiotte, Renaud , Aggarwal, Charu
- Date: 2022
- Type: Text , Conference proceedings
- Relation: WWW '22: Companion Proceedings of the Web Conference 2022, Virtual Event, Lyon France April 25 - 29, 2022 p. 1004-1005
- Full Text:
- Reviewed:
- Description: The First Workshop on Graph Learning aims to bring together researchers and practitioners from academia and industry to discuss recent advances and core challenges of graph learning. This workshop will be established as a platform for multiple disciplines such as computer science, applied mathematics, physics, social sciences, data science, complex networks, and systems engineering. Core challenges in regard to theory, methodology, and applications of graph learning will be the main center of discussions at the workshop.
- Authors: Xia, Feng , Lambiotte, Renaud , Aggarwal, Charu
- Date: 2022
- Type: Text , Conference proceedings
- Relation: WWW '22: Companion Proceedings of the Web Conference 2022, Virtual Event, Lyon France April 25 - 29, 2022 p. 1004-1005
- Full Text:
- Reviewed:
- Description: The First Workshop on Graph Learning aims to bring together researchers and practitioners from academia and industry to discuss recent advances and core challenges of graph learning. This workshop will be established as a platform for multiple disciplines such as computer science, applied mathematics, physics, social sciences, data science, complex networks, and systems engineering. Core challenges in regard to theory, methodology, and applications of graph learning will be the main center of discussions at the workshop.
Exploring human mobility for multi-pattern passenger prediction : a graph learning framework
- Kong, Xiangjiea, Wang, Kailai, Hou, Mingliang, Xia, Feng, Karmakar, Gour, Li, Jianxin
- Authors: Kong, Xiangjiea , Wang, Kailai , Hou, Mingliang , Xia, Feng , Karmakar, Gour , Li, Jianxin
- Date: 2022
- Type: Text , Journal article
- Relation: IEEE Transactions on Intelligent Transportation Systems Vol. 23, no. 9 (2022), p. 16148-16160
- Full Text:
- Reviewed:
- Description: Traffic flow prediction is an integral part of an intelligent transportation system and thus fundamental for various traffic-related applications. Buses are an indispensable way of moving for urban residents with fixed routes and schedules, which leads to latent travel regularity. However, human mobility patterns, specifically the complex relationships between bus passengers, are deeply hidden in this fixed mobility mode. Although many models exist to predict traffic flow, human mobility patterns have not been well explored in this regard. To address this research gap and learn human mobility knowledge from this fixed travel behaviors, we propose a multi-pattern passenger flow prediction framework, MPGCN, based on Graph Convolutional Network (GCN). Firstly, we construct a novel sharing-stop network to model relationships between passengers based on bus record data. Then, we employ GCN to extract features from the graph by learning useful topology information and introduce a deep clustering method to recognize mobility patterns hidden in bus passengers. Furthermore, to fully utilize spatio-temporal information, we propose GCN2Flow to predict passenger flow based on various mobility patterns. To the best of our knowledge, this paper is the first work to adopt a multi-pattern approach to predict the bus passenger flow by taking advantage of graph learning. We design a case study for optimizing routes. Extensive experiments upon a real-world bus dataset demonstrate that MPGCN has potential efficacy in passenger flow prediction and route optimization. © 2000-2011 IEEE.
- Authors: Kong, Xiangjiea , Wang, Kailai , Hou, Mingliang , Xia, Feng , Karmakar, Gour , Li, Jianxin
- Date: 2022
- Type: Text , Journal article
- Relation: IEEE Transactions on Intelligent Transportation Systems Vol. 23, no. 9 (2022), p. 16148-16160
- Full Text:
- Reviewed:
- Description: Traffic flow prediction is an integral part of an intelligent transportation system and thus fundamental for various traffic-related applications. Buses are an indispensable way of moving for urban residents with fixed routes and schedules, which leads to latent travel regularity. However, human mobility patterns, specifically the complex relationships between bus passengers, are deeply hidden in this fixed mobility mode. Although many models exist to predict traffic flow, human mobility patterns have not been well explored in this regard. To address this research gap and learn human mobility knowledge from this fixed travel behaviors, we propose a multi-pattern passenger flow prediction framework, MPGCN, based on Graph Convolutional Network (GCN). Firstly, we construct a novel sharing-stop network to model relationships between passengers based on bus record data. Then, we employ GCN to extract features from the graph by learning useful topology information and introduce a deep clustering method to recognize mobility patterns hidden in bus passengers. Furthermore, to fully utilize spatio-temporal information, we propose GCN2Flow to predict passenger flow based on various mobility patterns. To the best of our knowledge, this paper is the first work to adopt a multi-pattern approach to predict the bus passenger flow by taking advantage of graph learning. We design a case study for optimizing routes. Extensive experiments upon a real-world bus dataset demonstrate that MPGCN has potential efficacy in passenger flow prediction and route optimization. © 2000-2011 IEEE.
Familiarity-based collaborative team recognition in academic social networks
- Yu, Shuo, Xia, Feng, Zhang, Chen, Wei, Haoran, Keogh, Kathleen, Chen, Honglong
- Authors: Yu, Shuo , Xia, Feng , Zhang, Chen , Wei, Haoran , Keogh, Kathleen , Chen, Honglong
- Date: 2022
- Type: Text , Journal article
- Relation: IEEE Transactions on Computational Social Systems Vol. 9, no. 5 (2022), p. 1432-1445
- Full Text:
- Reviewed:
- Description: Collaborative teamwork is key to major scientific discoveries. However, the prevalence of collaboration among researchers makes team recognition increasingly challenging. Previous studies have demonstrated that people are more likely to collaborate with individuals they are familiar with. In this work, we employ the definition of familiarity and then propose faMiliarity-based cOllaborative Team recOgnition (MOTO) algorithm to recognize collaborative teams. MOTO calculates the shortest distance matrix within the global collaboration network and the local density of each node. Central team members are initially recognized based on local density. Then, MOTO recognizes the remaining team members by using the familiarity metric and shortest distance matrix. Extensive experiments have been conducted upon a large-scale dataset. The experimental results show that compared with baseline methods, MOTO can recognize the largest number of teams. The teams recognized by the MOTO possess more cohesive team structures and lower team communication costs compared with other methods. MOTO utilizes familiarity in team recognition to identify cohesive academic teams. The recognized teams are in line with real-world collaborative teamwork patterns. Based on team recognition using MOTO, the research team structure and performance are further analyzed for given time periods. The number of teams that consist of members from different institutions increases gradually. Such teams are found to perform better in comparison with those whose members are from the same institution. © 2014 IEEE.
- Authors: Yu, Shuo , Xia, Feng , Zhang, Chen , Wei, Haoran , Keogh, Kathleen , Chen, Honglong
- Date: 2022
- Type: Text , Journal article
- Relation: IEEE Transactions on Computational Social Systems Vol. 9, no. 5 (2022), p. 1432-1445
- Full Text:
- Reviewed:
- Description: Collaborative teamwork is key to major scientific discoveries. However, the prevalence of collaboration among researchers makes team recognition increasingly challenging. Previous studies have demonstrated that people are more likely to collaborate with individuals they are familiar with. In this work, we employ the definition of familiarity and then propose faMiliarity-based cOllaborative Team recOgnition (MOTO) algorithm to recognize collaborative teams. MOTO calculates the shortest distance matrix within the global collaboration network and the local density of each node. Central team members are initially recognized based on local density. Then, MOTO recognizes the remaining team members by using the familiarity metric and shortest distance matrix. Extensive experiments have been conducted upon a large-scale dataset. The experimental results show that compared with baseline methods, MOTO can recognize the largest number of teams. The teams recognized by the MOTO possess more cohesive team structures and lower team communication costs compared with other methods. MOTO utilizes familiarity in team recognition to identify cohesive academic teams. The recognized teams are in line with real-world collaborative teamwork patterns. Based on team recognition using MOTO, the research team structure and performance are further analyzed for given time periods. The number of teams that consist of members from different institutions increases gradually. Such teams are found to perform better in comparison with those whose members are from the same institution. © 2014 IEEE.
Graph learning : a survey
- Xia, Feng, Sun, Ke, Yu, Shuo, Aziz, Abdul, Wan, Liangtian, Pan, Shirui, Liu, Huan
- Authors: Xia, Feng , Sun, Ke , Yu, Shuo , Aziz, Abdul , Wan, Liangtian , Pan, Shirui , Liu, Huan
- Date: 2021
- Type: Text , Journal article , Review
- Relation: IEEE Transactions on Artificial Intelligence Vol. 2, no. 2 (2021), p. 109-127
- Full Text:
- Reviewed:
- Description: Graphs are widely used as a popular representation of the network structure of connected data. Graph data can be found in a broad spectrum of application domains such as social systems, ecosystems, biological networks, knowledge graphs, and information systems. With the continuous penetration of artificial intelligence technologies, graph learning (i.e., machine learning on graphs) is gaining attention from both researchers and practitioners. Graph learning proves effective for many tasks, such as classification, link prediction, and matching. Generally, graph learning methods extract relevant features of graphs by taking advantage of machine learning algorithms. In this survey, we present a comprehensive overview on the state-of-the-art of graph learning. Special attention is paid to four categories of existing graph learning methods, including graph signal processing, matrix factorization, random walk, and deep learning. Major models and algorithms under these categories are reviewed, respectively. We examine graph learning applications in areas such as text, images, science, knowledge graphs, and combinatorial optimization. In addition, we discuss several promising research directions in this field. Impact Statement—Real-world intelligent systems generally rely on machine learning algorithms handling data of various types. Despite their ubiquity, graph data have imposed unprecedented challenges to machine learning due to their inherent complexity. Unlike text, audio and images, graph data are embedded in an irregular domain, making some essential operations of existing machine learning algorithms inapplicable. Many graph learning models and algorithms have been developed to tackle these challenges. This article presents a systematic review of the state-of-the-art graph learning approaches as well as their potential applications. The article serves multiple purposes. First, it acts as a quick reference to graph learning for researchers and practitioners in different areas such as social computing, information retrieval, computer vision, bioinformatics, economics, and e-commence. Second, it presents insights into open areas of research in the field. Third, it aims to stimulate new research ideas and more interests in graph learning. © IEEE Transactions on Artificial Intelligence 2020.
- Authors: Xia, Feng , Sun, Ke , Yu, Shuo , Aziz, Abdul , Wan, Liangtian , Pan, Shirui , Liu, Huan
- Date: 2021
- Type: Text , Journal article , Review
- Relation: IEEE Transactions on Artificial Intelligence Vol. 2, no. 2 (2021), p. 109-127
- Full Text:
- Reviewed:
- Description: Graphs are widely used as a popular representation of the network structure of connected data. Graph data can be found in a broad spectrum of application domains such as social systems, ecosystems, biological networks, knowledge graphs, and information systems. With the continuous penetration of artificial intelligence technologies, graph learning (i.e., machine learning on graphs) is gaining attention from both researchers and practitioners. Graph learning proves effective for many tasks, such as classification, link prediction, and matching. Generally, graph learning methods extract relevant features of graphs by taking advantage of machine learning algorithms. In this survey, we present a comprehensive overview on the state-of-the-art of graph learning. Special attention is paid to four categories of existing graph learning methods, including graph signal processing, matrix factorization, random walk, and deep learning. Major models and algorithms under these categories are reviewed, respectively. We examine graph learning applications in areas such as text, images, science, knowledge graphs, and combinatorial optimization. In addition, we discuss several promising research directions in this field. Impact Statement—Real-world intelligent systems generally rely on machine learning algorithms handling data of various types. Despite their ubiquity, graph data have imposed unprecedented challenges to machine learning due to their inherent complexity. Unlike text, audio and images, graph data are embedded in an irregular domain, making some essential operations of existing machine learning algorithms inapplicable. Many graph learning models and algorithms have been developed to tackle these challenges. This article presents a systematic review of the state-of-the-art graph learning approaches as well as their potential applications. The article serves multiple purposes. First, it acts as a quick reference to graph learning for researchers and practitioners in different areas such as social computing, information retrieval, computer vision, bioinformatics, economics, and e-commence. Second, it presents insights into open areas of research in the field. Third, it aims to stimulate new research ideas and more interests in graph learning. © IEEE Transactions on Artificial Intelligence 2020.
Edge data based trailer inception probabilistic matrix factorization for context-aware movie recommendation
- Chen, Honglong, Li, Zhe, Wang, Zhu, Ni, Zhichen, Li, Junjian, Xu, Ge, Aziz, Abdul, Xia, Feng
- Authors: Chen, Honglong , Li, Zhe , Wang, Zhu , Ni, Zhichen , Li, Junjian , Xu, Ge , Aziz, Abdul , Xia, Feng
- Date: 2022
- Type: Text , Journal article
- Relation: World Wide Web Vol. 25, no. 5 (2022), p. 1863-1882
- Full Text:
- Reviewed:
- Description: The rapid growth of edge data generated by mobile devices and applications deployed at the edge of the network has exacerbated the problem of information overload. As an effective way to alleviate information overload, recommender system can improve the quality of various services by adding application data generated by users on edge devices, such as visual and textual information, on the basis of sparse rating data. The visual information in the movie trailer is a significant part of the movie recommender system. However, due to the complexity of visual information extraction, data sparsity cannot be remarkably alleviated by merely using the rough visual features to improve the rating prediction accuracy. Fortunately, the convolutional neural network can be used to extract the visual features precisely. Therefore, the end-to-end neural image caption (NIC) model can be utilized to obtain the textual information describing the visual features of movie trailers. This paper proposes a trailer inception probabilistic matrix factorization model called Ti-PMF, which combines NIC, recurrent convolutional neural network, and probabilistic matrix factorization models as the rating prediction model. We implement the proposed Ti-PMF model with extensive experiments on three real-world datasets to validate its effectiveness. The experimental results illustrate that the proposed Ti-PMF outperforms the existing ones. © 2021, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.
- Authors: Chen, Honglong , Li, Zhe , Wang, Zhu , Ni, Zhichen , Li, Junjian , Xu, Ge , Aziz, Abdul , Xia, Feng
- Date: 2022
- Type: Text , Journal article
- Relation: World Wide Web Vol. 25, no. 5 (2022), p. 1863-1882
- Full Text:
- Reviewed:
- Description: The rapid growth of edge data generated by mobile devices and applications deployed at the edge of the network has exacerbated the problem of information overload. As an effective way to alleviate information overload, recommender system can improve the quality of various services by adding application data generated by users on edge devices, such as visual and textual information, on the basis of sparse rating data. The visual information in the movie trailer is a significant part of the movie recommender system. However, due to the complexity of visual information extraction, data sparsity cannot be remarkably alleviated by merely using the rough visual features to improve the rating prediction accuracy. Fortunately, the convolutional neural network can be used to extract the visual features precisely. Therefore, the end-to-end neural image caption (NIC) model can be utilized to obtain the textual information describing the visual features of movie trailers. This paper proposes a trailer inception probabilistic matrix factorization model called Ti-PMF, which combines NIC, recurrent convolutional neural network, and probabilistic matrix factorization models as the rating prediction model. We implement the proposed Ti-PMF model with extensive experiments on three real-world datasets to validate its effectiveness. The experimental results illustrate that the proposed Ti-PMF outperforms the existing ones. © 2021, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.
Graph self-supervised learning : a survey
- Liu, Yixin, Jin, Ming, Pan, Shirui, Zhou, Chuan, Zheng, Yu, Xia, Feng, Yu, Philip
- Authors: Liu, Yixin , Jin, Ming , Pan, Shirui , Zhou, Chuan , Zheng, Yu , Xia, Feng , Yu, Philip
- Date: 2022
- Type: Text , Journal article
- Relation: IEEE Transactions on Knowledge and Data Engineering Vol. 35, no. 6 (2022), p. 5879-5900
- Full Text:
- Reviewed:
- Description: Deep learning on graphs has attracted significant interests recently. However, most of the works have focused on (semi-) supervised learning, resulting in shortcomings including heavy label reliance, poor generalization, and weak robustness. To address these issues, self-supervised learning (SSL), which extracts informative knowledge through well-designed pretext tasks without relying on manual labels, has become a promising and trending learning paradigm for graph data. Different from SSL on other domains like computer vision and natural language processing, SSL on graphs has an exclusive background, design ideas, and taxonomies. Under the umbrella of graph self-supervised learning, we present a timely and comprehensive review of the existing approaches which employ SSL techniques for graph data. We construct a unified framework that mathematically formalizes the paradigm of graph SSL. According to the objectives of pretext tasks, we divide these approaches into four categories: generation-based, auxiliary property-based, contrast-based, and hybrid approaches. We further describe the applications of graph SSL across various research fields and summarize the commonly used datasets, evaluation benchmark, performance comparison and open-source codes of graph SSL. Finally, we discuss the remaining challenges and potential future directions in this research field. IEEE
- Authors: Liu, Yixin , Jin, Ming , Pan, Shirui , Zhou, Chuan , Zheng, Yu , Xia, Feng , Yu, Philip
- Date: 2022
- Type: Text , Journal article
- Relation: IEEE Transactions on Knowledge and Data Engineering Vol. 35, no. 6 (2022), p. 5879-5900
- Full Text:
- Reviewed:
- Description: Deep learning on graphs has attracted significant interests recently. However, most of the works have focused on (semi-) supervised learning, resulting in shortcomings including heavy label reliance, poor generalization, and weak robustness. To address these issues, self-supervised learning (SSL), which extracts informative knowledge through well-designed pretext tasks without relying on manual labels, has become a promising and trending learning paradigm for graph data. Different from SSL on other domains like computer vision and natural language processing, SSL on graphs has an exclusive background, design ideas, and taxonomies. Under the umbrella of graph self-supervised learning, we present a timely and comprehensive review of the existing approaches which employ SSL techniques for graph data. We construct a unified framework that mathematically formalizes the paradigm of graph SSL. According to the objectives of pretext tasks, we divide these approaches into four categories: generation-based, auxiliary property-based, contrast-based, and hybrid approaches. We further describe the applications of graph SSL across various research fields and summarize the commonly used datasets, evaluation benchmark, performance comparison and open-source codes of graph SSL. Finally, we discuss the remaining challenges and potential future directions in this research field. IEEE
Subgraph adaptive structure-aware graph contrastive learning
- Chen, Zhikui, Peng, Yin, Yu, Shuo, Cao, Chen, Xia, Feng
- Authors: Chen, Zhikui , Peng, Yin , Yu, Shuo , Cao, Chen , Xia, Feng
- Date: 2022
- Type: Text , Journal article
- Relation: Mathematics (Basel) Vol. 10, no. 17 (2022), p. 3047
- Full Text:
- Reviewed:
- Description: Graph contrastive learning (GCL) has been subject to more attention and been widely applied to numerous graph learning tasks such as node classification and link prediction. Although it has achieved great success and even performed better than supervised methods in some tasks, most of them depend on node-level comparison, while ignoring the rich semantic information contained in graph topology, especially for social networks. However, a higher-level comparison requires subgraph construction and encoding, which remain unsolved. To address this problem, we propose a subgraph adaptive structure-aware graph contrastive learning method (PASCAL) in this work, which is a subgraph-level GCL method. In PASCAL, we construct subgraphs by merging all motifs that contain the target node. Then we encode them on the basis of motif number distribution to capture the rich information hidden in subgraphs. By incorporating motif information, PASCAL can capture richer semantic information hidden in local structures compared with other GCL methods. Extensive experiments on six benchmark datasets show that PASCAL outperforms state-of-art graph contrastive learning and supervised methods in most cases.
- Authors: Chen, Zhikui , Peng, Yin , Yu, Shuo , Cao, Chen , Xia, Feng
- Date: 2022
- Type: Text , Journal article
- Relation: Mathematics (Basel) Vol. 10, no. 17 (2022), p. 3047
- Full Text:
- Reviewed:
- Description: Graph contrastive learning (GCL) has been subject to more attention and been widely applied to numerous graph learning tasks such as node classification and link prediction. Although it has achieved great success and even performed better than supervised methods in some tasks, most of them depend on node-level comparison, while ignoring the rich semantic information contained in graph topology, especially for social networks. However, a higher-level comparison requires subgraph construction and encoding, which remain unsolved. To address this problem, we propose a subgraph adaptive structure-aware graph contrastive learning method (PASCAL) in this work, which is a subgraph-level GCL method. In PASCAL, we construct subgraphs by merging all motifs that contain the target node. Then we encode them on the basis of motif number distribution to capture the rich information hidden in subgraphs. By incorporating motif information, PASCAL can capture richer semantic information hidden in local structures compared with other GCL methods. Extensive experiments on six benchmark datasets show that PASCAL outperforms state-of-art graph contrastive learning and supervised methods in most cases.
CenGCN : centralized convolutional networks with vertex imbalance for scale-free graphs
- Xia, Feng, Wang, Lei, Tang, Tao, Chen, Xin, Kong, Xiangjie, Oatley, Giles, King, Irwin
- Authors: Xia, Feng , Wang, Lei , Tang, Tao , Chen, Xin , Kong, Xiangjie , Oatley, Giles , King, Irwin
- Date: 2023
- Type: Text , Journal article
- Relation: IEEE Transactions on Knowledge and Data Engineering Vol. 35, no. 5 (2023), p. 4555-4569
- Full Text:
- Reviewed:
- Description: Graph Convolutional Networks (GCNs) have achieved impressive performance in a wide variety of areas, attracting considerable attention. The core step of GCNs is the information-passing framework that considers all information from neighbors to the central vertex to be equally important. Such equal importance, however, is inadequate for scale-free networks, where hub vertices propagate more dominant information due to vertex imbalance. In this paper, we propose a novel centrality-based framework named CenGCN to address the inequality of information. This framework first quantifies the similarity between hub vertices and their neighbors by label propagation with hub vertices. Based on this similarity and centrality indices, the framework transforms the graph by increasing or decreasing the weights of edges connecting hub vertices and adding self-connections to vertices. In each non-output layer of the GCN, this framework uses a hub attention mechanism to assign new weights to connected non-hub vertices based on their common information with hub vertices. We present two variants CenGCN_D and CenGCN_E, based on degree centrality and eigenvector centrality, respectively. We also conduct comprehensive experiments, including vertex classification, link prediction, vertex clustering, and network visualization. The results demonstrate that the two variants significantly outperform state-of-the-art baselines. © 1989-2012 IEEE.
- Authors: Xia, Feng , Wang, Lei , Tang, Tao , Chen, Xin , Kong, Xiangjie , Oatley, Giles , King, Irwin
- Date: 2023
- Type: Text , Journal article
- Relation: IEEE Transactions on Knowledge and Data Engineering Vol. 35, no. 5 (2023), p. 4555-4569
- Full Text:
- Reviewed:
- Description: Graph Convolutional Networks (GCNs) have achieved impressive performance in a wide variety of areas, attracting considerable attention. The core step of GCNs is the information-passing framework that considers all information from neighbors to the central vertex to be equally important. Such equal importance, however, is inadequate for scale-free networks, where hub vertices propagate more dominant information due to vertex imbalance. In this paper, we propose a novel centrality-based framework named CenGCN to address the inequality of information. This framework first quantifies the similarity between hub vertices and their neighbors by label propagation with hub vertices. Based on this similarity and centrality indices, the framework transforms the graph by increasing or decreasing the weights of edges connecting hub vertices and adding self-connections to vertices. In each non-output layer of the GCN, this framework uses a hub attention mechanism to assign new weights to connected non-hub vertices based on their common information with hub vertices. We present two variants CenGCN_D and CenGCN_E, based on degree centrality and eigenvector centrality, respectively. We also conduct comprehensive experiments, including vertex classification, link prediction, vertex clustering, and network visualization. The results demonstrate that the two variants significantly outperform state-of-the-art baselines. © 1989-2012 IEEE.
Relational structure-aware knowledge graph representation in complex space
- Sun, Ke, Yu, Shuo, Peng, Ciyuan, Wang, Yueru, Alfarraj, Osama, Tolba, Amr, Xia, Feng
- Authors: Sun, Ke , Yu, Shuo , Peng, Ciyuan , Wang, Yueru , Alfarraj, Osama , Tolba, Amr , Xia, Feng
- Date: 2022
- Type: Text , Journal article
- Relation: Mathematics Vol. 10, no. 11 (2022), p.
- Full Text:
- Reviewed:
- Description: Relations in knowledge graphs have rich relational structures and various binary relational patterns. Various relation modelling strategies are proposed for embedding knowledge graphs, but they fail to fully capture both features of relations, rich relational structures and various binary relational patterns. To address the problem of insufficient embedding due to the complexity of the relations, we propose a novel knowledge graph representation model in complex space, namely MARS, to exploit complex relations to embed knowledge graphs. MARS takes the mechanisms of complex numbers and message-passing and then embeds triplets into relation-specific complex hyperplanes. Thus, MARS can well preserve various relation patterns, as well as structural information in knowledge graphs. In addition, we find that the scores generated from the score function approximate a Gaussian distribution. The scores in the tail cannot effectively represent triplets. To address this particular issue and improve the precision of embeddings, we use the standard deviation to limit the dispersion of the score distribution, resulting in more accurate embeddings of triplets. Comprehensive experiments on multiple benchmarks demonstrate that our model significantly outperforms existing state-of-the-art models for link prediction and triple classification. © 2022 by the authors. Licensee MDPI, Basel, Switzerland.
- Authors: Sun, Ke , Yu, Shuo , Peng, Ciyuan , Wang, Yueru , Alfarraj, Osama , Tolba, Amr , Xia, Feng
- Date: 2022
- Type: Text , Journal article
- Relation: Mathematics Vol. 10, no. 11 (2022), p.
- Full Text:
- Reviewed:
- Description: Relations in knowledge graphs have rich relational structures and various binary relational patterns. Various relation modelling strategies are proposed for embedding knowledge graphs, but they fail to fully capture both features of relations, rich relational structures and various binary relational patterns. To address the problem of insufficient embedding due to the complexity of the relations, we propose a novel knowledge graph representation model in complex space, namely MARS, to exploit complex relations to embed knowledge graphs. MARS takes the mechanisms of complex numbers and message-passing and then embeds triplets into relation-specific complex hyperplanes. Thus, MARS can well preserve various relation patterns, as well as structural information in knowledge graphs. In addition, we find that the scores generated from the score function approximate a Gaussian distribution. The scores in the tail cannot effectively represent triplets. To address this particular issue and improve the precision of embeddings, we use the standard deviation to limit the dispersion of the score distribution, resulting in more accurate embeddings of triplets. Comprehensive experiments on multiple benchmarks demonstrate that our model significantly outperforms existing state-of-the-art models for link prediction and triple classification. © 2022 by the authors. Licensee MDPI, Basel, Switzerland.
Graph augmentation learning
- Yu, Shuo, Huang, Huafei, Dao, Minh, Xia, Feng
- Authors: Yu, Shuo , Huang, Huafei , Dao, Minh , Xia, Feng
- Date: 2022
- Type: Text , Conference paper
- Relation: 31st ACM Web Conference, WWW 2022, Virtual, online, 25 April 2022, WWW 2022 - Companion Proceedings of the Web Conference 2022 p. 1063-1072
- Full Text:
- Reviewed:
- Description: Graph Augmentation Learning (GAL) provides outstanding solutions for graph learning in handling incomplete data, noise data, etc. Numerous GAL methods have been proposed for graph-based applications such as social network analysis and traffic flow forecasting. However, the underlying reasons for the effectiveness of these GAL methods are still unclear. As a consequence, how to choose optimal graph augmentation strategy for a certain application scenario is still in black box. There is a lack of systematic, comprehensive, and experimentally validated guideline of GAL for scholars. Therefore, in this survey, we in-depth review GAL techniques from macro (graph), meso (subgraph), and micro (node/edge) levels. We further detailedly illustrate how GAL enhance the data quality and the model performance. The aggregation mechanism of augmentation strategies and graph learning models are also discussed by different application scenarios, i.e., data-specific, model-specific, and hybrid scenarios. To better show the outperformance of GAL, we experimentally validate the effectiveness and adaptability of different GAL strategies in different downstream tasks. Finally, we share our insights on several open issues of GAL, including heterogeneity, spatio-temporal dynamics, scalability, and generalization. © 2022 ACM.
- Authors: Yu, Shuo , Huang, Huafei , Dao, Minh , Xia, Feng
- Date: 2022
- Type: Text , Conference paper
- Relation: 31st ACM Web Conference, WWW 2022, Virtual, online, 25 April 2022, WWW 2022 - Companion Proceedings of the Web Conference 2022 p. 1063-1072
- Full Text:
- Reviewed:
- Description: Graph Augmentation Learning (GAL) provides outstanding solutions for graph learning in handling incomplete data, noise data, etc. Numerous GAL methods have been proposed for graph-based applications such as social network analysis and traffic flow forecasting. However, the underlying reasons for the effectiveness of these GAL methods are still unclear. As a consequence, how to choose optimal graph augmentation strategy for a certain application scenario is still in black box. There is a lack of systematic, comprehensive, and experimentally validated guideline of GAL for scholars. Therefore, in this survey, we in-depth review GAL techniques from macro (graph), meso (subgraph), and micro (node/edge) levels. We further detailedly illustrate how GAL enhance the data quality and the model performance. The aggregation mechanism of augmentation strategies and graph learning models are also discussed by different application scenarios, i.e., data-specific, model-specific, and hybrid scenarios. To better show the outperformance of GAL, we experimentally validate the effectiveness and adaptability of different GAL strategies in different downstream tasks. Finally, we share our insights on several open issues of GAL, including heterogeneity, spatio-temporal dynamics, scalability, and generalization. © 2022 ACM.