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.
The significance and impact of winning an academic award : a study of early career academics
- Ren, Jing, Shi, Yajie, Shatte, Adrian, Kong, Xiangjie, Xia, Feng
- Authors: Ren, Jing , Shi, Yajie , Shatte, Adrian , Kong, Xiangjie , Xia, Feng
- Date: 2022
- Type: Text , Conference paper
- Relation: 22nd ACM/IEEE Joint Conference on Digital Libraries, JCDL 2022, Virtual, online, 20-24 June 2022, Proceedings of the ACM/IEEE Joint Conference on Digital Libraries
- Full Text: false
- Reviewed:
- Description: Academic award plays an important role in an academic's careerparticularly for early career academics. Previous studies have primarilyfocused on the impact of awards conferred to academics whoe made outstanding contributions to a specific research field, such as the Nobel Prize. In contrast, this paper aims to investigatethe effect of awards conferred to academics at an earlier careerstage, who have the potential to make a great impact in the future. We devise a metric named Award Change Factor (ACF), to evaluatethe change of a recipient's academic behavior after winningan academic award. Next, we propose a model to compare awardrecipients with academics who have similar performance beforewinning an academic award. In summary, we analyze the impact ofan award on the recipients' academic impact and their teams fromdifferent perspectives. Experimental results show that most recipientsdo have improvements in both productivity and citations afterwinning an academic award, while there is no significant impacton publication quality. In addition, receipt of an academic awardnot only expands recipients' collaboration network, but also has apositive effect on their team size. © 2022 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.
Urban region profiling with spatio-temporal graph neural networks
- Hou, Mingliang, Xia, Feng, Gao, Haoran, Chen, Xin, Chen, Honglong
- Authors: Hou, Mingliang , Xia, Feng , Gao, Haoran , Chen, Xin , Chen, Honglong
- Date: 2022
- Type: Text , Journal article
- Relation: IEEE Transactions on Computational Social Systems Vol. 9, no. 6 (2022), p. 1736-1747
- Full Text: false
- Reviewed:
- Description: Region profiles are summaries of characteristics of urban regions. Region profiling is a process to discover the correlations between urban regions. The learned urban profiles can be used to represent and identify regions in supporting downstream tasks, e.g., region traffic status estimation. While some efforts have been made to model urban regions, representation learning with awareness of graph-structured data can improve the existing methods. To do this, we first construct an attribute spatio-temporal graph, in which a node represents a region, an edge represents mobility across regions, and a node attribute represents a region's point of interest (PoI) distribution. The problem of region profiling is reformulated as a representation learning problem based on attribute spatio-temporal graphs. To solve this problem, we developed URGENT, a spatio-temporal graph learning framework. URGENT is made up of two modules. The graph convolutional neural network is used in the first module to learn spatial dependencies. The second module is an encoding-decoding temporal learning structure with self-attention mechanism. Furthermore, we use the learned representations of regions to estimate region traffic status. Experimental results demonstrate that URGENT outperforms major baselines in estimation accuracy under various settings and produces more meaningful results. © 2014 IEEE.
VRConvMF : visual recurrent convolutional matrix factorization for movie ecommendation
- Wang, Zhu, Chen, Honglong, Li, Zhe, Lin, Kai, Jiang, Nan, Xia, Feng
- Authors: Wang, Zhu , Chen, Honglong , Li, Zhe , Lin, Kai , Jiang, Nan , Xia, Feng
- Date: 2022
- Type: Text , Journal article
- Relation: IEEE Transactions on Emerging Topics in Computational Intelligence Vol. 6, no. 3 (2022), p. 519-529
- Full Text:
- Reviewed:
- Description: Sparsity of user-to-item rating data becomes one of challenging issues in the recommender systems, which severely deteriorates the recommendation performance. Fortunately, context-aware recommender systems can alleviate the sparsity problem by making use of some auxiliary information, such as the information of both the users and items. In particular, the visual information of items, such as the movie poster, can be considered as the supplement for item description documents, which helps to obtain more item features. In this paper, we focus on movie recommender system and propose a probabilistic matrix factorization based recommendation scheme called visual recurrent convolutional matrix factorization (VRConvMF), which utilizes the textual and multi-level visual features extracted from the descriptive texts and posters respectively. We implement the proposed VRConvMF and conduct extensive experiments on three commonly used real world datasets to validate its effectiveness. The experimental results illustrate that the proposed VRConvMF outperforms the existing schemes. © 2017 IEEE.
- Authors: Wang, Zhu , Chen, Honglong , Li, Zhe , Lin, Kai , Jiang, Nan , Xia, Feng
- Date: 2022
- Type: Text , Journal article
- Relation: IEEE Transactions on Emerging Topics in Computational Intelligence Vol. 6, no. 3 (2022), p. 519-529
- Full Text:
- Reviewed:
- Description: Sparsity of user-to-item rating data becomes one of challenging issues in the recommender systems, which severely deteriorates the recommendation performance. Fortunately, context-aware recommender systems can alleviate the sparsity problem by making use of some auxiliary information, such as the information of both the users and items. In particular, the visual information of items, such as the movie poster, can be considered as the supplement for item description documents, which helps to obtain more item features. In this paper, we focus on movie recommender system and propose a probabilistic matrix factorization based recommendation scheme called visual recurrent convolutional matrix factorization (VRConvMF), which utilizes the textual and multi-level visual features extracted from the descriptive texts and posters respectively. We implement the proposed VRConvMF and conduct extensive experiments on three commonly used real world datasets to validate its effectiveness. The experimental results illustrate that the proposed VRConvMF outperforms the existing schemes. © 2017 IEEE.
A federated learning-based license plate recognition scheme for 5G-enabled Internet of vehicles
- Kong, Xiangjie, Wang, Kailai, Hou, Mingliang, Hao, Xinyu, Shen, Guojiang, Chen, Xin, Xia, Feng
- Authors: Kong, Xiangjie , Wang, Kailai , Hou, Mingliang , Hao, Xinyu , Shen, Guojiang , Chen, Xin , Xia, Feng
- Date: 2021
- Type: Text , Journal article
- Relation: IEEE Transactions on Industrial Informatics Vol. 17, no. 12 (Dec 2021), p. 8523-8530
- Full Text:
- Reviewed:
- Description: License plate is an essential characteristic to identify vehicles for the traffic management, and thus, license plate recognition is important for Internet of Vehicles. Since 5G has been widely covered, mobile devices are utilized to assist the traffic management, which is a significant part of Industry 4.0. However, there have always been privacy risks due to centralized training of models. Also, the trained model cannot be directly deployed on the mobile device due to its large number of parameters. In this article, we propose a federated learning-based license plate recognition framework (FedLPR) to solve these problems. We design detection and recognition model to apply in the mobile device. In terms of user privacy, data in individuals is harnessed on their mobile devices instead of the server to train models based on federated learning. Extensive experiments demonstrate that FedLPR has high accuracy and acceptable communication cost while preserving user privacy.
- Authors: Kong, Xiangjie , Wang, Kailai , Hou, Mingliang , Hao, Xinyu , Shen, Guojiang , Chen, Xin , Xia, Feng
- Date: 2021
- Type: Text , Journal article
- Relation: IEEE Transactions on Industrial Informatics Vol. 17, no. 12 (Dec 2021), p. 8523-8530
- Full Text:
- Reviewed:
- Description: License plate is an essential characteristic to identify vehicles for the traffic management, and thus, license plate recognition is important for Internet of Vehicles. Since 5G has been widely covered, mobile devices are utilized to assist the traffic management, which is a significant part of Industry 4.0. However, there have always been privacy risks due to centralized training of models. Also, the trained model cannot be directly deployed on the mobile device due to its large number of parameters. In this article, we propose a federated learning-based license plate recognition framework (FedLPR) to solve these problems. We design detection and recognition model to apply in the mobile device. In terms of user privacy, data in individuals is harnessed on their mobile devices instead of the server to train models based on federated learning. Extensive experiments demonstrate that FedLPR has high accuracy and acceptable communication cost while preserving user privacy.
A3Graph : adversarial attributed autoencoder for graph representation learning
- Hou, Mingliang, Wang, Lei, Liu, Jiaying, Kong, Xiangjie, Xia, Feng
- Authors: Hou, Mingliang , Wang, Lei , Liu, Jiaying , Kong, Xiangjie , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 36th Annual ACM Symposium on Applied Computing, SAC 2021 p. 1697-1704
- Full Text:
- Reviewed:
- Description: Recent years have witnessed a proliferation of graph representation techniques in social network analysis. Graph representation aims to map nodes in the graph into low-dimensional vector space while preserving as much information as possible. However, most existing methods ignore the robustness of learned latent vectors, which leads to inferior representation results due to sparse and noisy data in graphs. In this paper, we propose a novel framework, named A3Graph, which aims to improve the robustness and stability of graph representations. Specifically, we first construct an aggregation matrix by the combining positive point-wise mutual information matrix with the attribute matrix. Then, we enforce the autoencoder to reconstruct the aggregation matrix instead of the input attribute matrix. The enhancement autoencoder can incorporate structural and attributed information in a joint learning way to improve the noise-resilient during the learning process. Furthermore, an adversarial learning component is leveraged in our framework to impose a prior distribution on learned representations has been demonstrated as an effective mechanism in improving the robustness and stability in representation learning. Experimental studies on real-world datasets have demonstrated the effectiveness of the proposed A3Graph. © 2021 ACM.
- Authors: Hou, Mingliang , Wang, Lei , Liu, Jiaying , Kong, Xiangjie , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 36th Annual ACM Symposium on Applied Computing, SAC 2021 p. 1697-1704
- Full Text:
- Reviewed:
- Description: Recent years have witnessed a proliferation of graph representation techniques in social network analysis. Graph representation aims to map nodes in the graph into low-dimensional vector space while preserving as much information as possible. However, most existing methods ignore the robustness of learned latent vectors, which leads to inferior representation results due to sparse and noisy data in graphs. In this paper, we propose a novel framework, named A3Graph, which aims to improve the robustness and stability of graph representations. Specifically, we first construct an aggregation matrix by the combining positive point-wise mutual information matrix with the attribute matrix. Then, we enforce the autoencoder to reconstruct the aggregation matrix instead of the input attribute matrix. The enhancement autoencoder can incorporate structural and attributed information in a joint learning way to improve the noise-resilient during the learning process. Furthermore, an adversarial learning component is leveraged in our framework to impose a prior distribution on learned representations has been demonstrated as an effective mechanism in improving the robustness and stability in representation learning. Experimental studies on real-world datasets have demonstrated the effectiveness of the proposed A3Graph. © 2021 ACM.
ANSWER : generating information dissemination network on campus
- Qing, Qing, Guo, Teng, Zhang, Dongyu, Xia, Feng
- Authors: Qing, Qing , Guo, Teng , Zhang, Dongyu , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 32nd Australasian Database Conference, ADC 2021 Vol. 12610 LNCS, p. 74-86
- Full Text:
- Reviewed:
- Description: Information dissemination matters, both on an individual and group level. For college students who are physically and mentally immature, they are more sensitive and susceptible to unnormal information like rumors. However, current researches focus on large-scale online message sharing networks like Facebook and Twitter, rather than profile the information dissemination on campus, which fail to provide any references for daily campus management. Against this background, we propose a framework to generate the information dissemination network on campus, named ANSWER (cAmpus iNformation diSsemination netWork gEneRation), based on multimodal data including behavior data, appearance data, and psychological data. The construction of the ANSWER is listed as four steps. First, we use a convolutional autoencoder to extract the students’ facial features. Second, we process the behavior data to construct a friendship network. Third, heterogeneous information is embedded in the low-dimensional vector space by using network representation learning to obtain embedding vectors. Fourth, we use the deep learning model to predict. The experiment results show that ANSWER outperforms other methods in multiple feature fusion and prediction of information dissemination relationship performance. © 2021, Springer Nature Switzerland AG.
- Authors: Qing, Qing , Guo, Teng , Zhang, Dongyu , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 32nd Australasian Database Conference, ADC 2021 Vol. 12610 LNCS, p. 74-86
- Full Text:
- Reviewed:
- Description: Information dissemination matters, both on an individual and group level. For college students who are physically and mentally immature, they are more sensitive and susceptible to unnormal information like rumors. However, current researches focus on large-scale online message sharing networks like Facebook and Twitter, rather than profile the information dissemination on campus, which fail to provide any references for daily campus management. Against this background, we propose a framework to generate the information dissemination network on campus, named ANSWER (cAmpus iNformation diSsemination netWork gEneRation), based on multimodal data including behavior data, appearance data, and psychological data. The construction of the ANSWER is listed as four steps. First, we use a convolutional autoencoder to extract the students’ facial features. Second, we process the behavior data to construct a friendship network. Third, heterogeneous information is embedded in the low-dimensional vector space by using network representation learning to obtain embedding vectors. Fourth, we use the deep learning model to predict. The experiment results show that ANSWER outperforms other methods in multiple feature fusion and prediction of information dissemination relationship performance. © 2021, Springer Nature Switzerland AG.
Attributed collaboration network embedding for academic relationship mining
- Wang, Wei, Liu, Jiaying, Tang, Tao, Tuarob, Suppawong, Xia, Feng, Gong, Zhiguo, King, Irwin
- Authors: Wang, Wei , Liu, Jiaying , Tang, Tao , Tuarob, Suppawong , Xia, Feng , Gong, Zhiguo , King, Irwin
- Date: 2021
- Type: Text , Journal article
- Relation: ACM Transactions on the Web Vol. 15, no. 1 (2021), p.
- Full Text:
- Reviewed:
- Description: Finding both efficient and effective quantitative representations for scholars in scientific digital libraries has been a focal point of research. The unprecedented amounts of scholarly datasets, combined with contemporary machine learning and big data techniques, have enabled intelligent and automatic profiling of scholars from this vast and ever-increasing pool of scholarly data. Meanwhile, recent advance in network embedding techniques enables us to mitigate the challenges of large scale and sparsity of academic collaboration networks. In real-world academic social networks, scholars are accompanied with various attributes or features, such as co-authorship and publication records, which result in attributed collaboration networks. It has been observed that both network topology and scholar attributes are important in academic relationship mining. However, previous studies mainly focus on network topology, whereas scholar attributes are overlooked. Moreover, the influence of different scholar attributes are unclear. To bridge this gap, in this work, we present a novel framework of Attributed Collaboration Network Embedding (ACNE) for academic relationship mining. ACNE extracts four types of scholar attributes based on the proposed scholar profiling model, including demographics, research, influence, and sociability. ACNE can learn a low-dimensional representation of scholars considering both scholar attributes and network topology simultaneously. We demonstrate the effectiveness and potentials of ACNE in academic relationship mining by performing collaborator recommendation on two real-world datasets and the contribution and importance of each scholar attribute on scientific collaborator recommendation is investigated. Our work may shed light on academic relationship mining by taking advantage of attributed collaboration network embedding. © 2020 ACM.
- Authors: Wang, Wei , Liu, Jiaying , Tang, Tao , Tuarob, Suppawong , Xia, Feng , Gong, Zhiguo , King, Irwin
- Date: 2021
- Type: Text , Journal article
- Relation: ACM Transactions on the Web Vol. 15, no. 1 (2021), p.
- Full Text:
- Reviewed:
- Description: Finding both efficient and effective quantitative representations for scholars in scientific digital libraries has been a focal point of research. The unprecedented amounts of scholarly datasets, combined with contemporary machine learning and big data techniques, have enabled intelligent and automatic profiling of scholars from this vast and ever-increasing pool of scholarly data. Meanwhile, recent advance in network embedding techniques enables us to mitigate the challenges of large scale and sparsity of academic collaboration networks. In real-world academic social networks, scholars are accompanied with various attributes or features, such as co-authorship and publication records, which result in attributed collaboration networks. It has been observed that both network topology and scholar attributes are important in academic relationship mining. However, previous studies mainly focus on network topology, whereas scholar attributes are overlooked. Moreover, the influence of different scholar attributes are unclear. To bridge this gap, in this work, we present a novel framework of Attributed Collaboration Network Embedding (ACNE) for academic relationship mining. ACNE extracts four types of scholar attributes based on the proposed scholar profiling model, including demographics, research, influence, and sociability. ACNE can learn a low-dimensional representation of scholars considering both scholar attributes and network topology simultaneously. We demonstrate the effectiveness and potentials of ACNE in academic relationship mining by performing collaborator recommendation on two real-world datasets and the contribution and importance of each scholar attribute on scientific collaborator recommendation is investigated. Our work may shed light on academic relationship mining by taking advantage of attributed collaboration network embedding. © 2020 ACM.
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.
Data-driven decision-making in COVID-19 response : a survey
- Yu, Shuo, Qing, Qing, Zhang, Chen, Shehzad, Ahsan, Oatley, Giles, Xia, Feng
- Authors: Yu, Shuo , Qing, Qing , Zhang, Chen , Shehzad, Ahsan , Oatley, Giles , Xia, Feng
- Date: 2021
- Type: Text , Journal article , Review
- Relation: IEEE Transactions on Computational Social Systems Vol. 8, no. 4 (2021), p. 989-1002
- Full Text:
- Reviewed:
- Description: COVID-19 has spread all over the world, having an enormous effect on our daily life and work. In response to the epidemic, a lot of important decisions need to be taken to save communities and economies worldwide. Data clearly play a vital role in effective decision-making. Data-driven decision-making uses data-related evidence and insights to guide the decision-making process and verify the plan of action before it is committed. To better handle the epidemic, governments and policy-making institutes have investigated abundant data originating from COVID-19. These data include those related to medicine, knowledge, media, and so on. Based on these data, many prevention and control policies are made. In this survey article, we summarize the progress of data-driven decision-making in the response to COVID-19, including COVID-19 prevention and control, psychological counseling, financial aid, work resumption, and school reopening. We also propose some current challenges and open issues in data-driven decision-making, including data collection and quality, complex data analysis, and fairness in decision-making. This survey article sheds light on current policy-making driven by data, which also provides a feasible direction for further scientific research. © 2014 IEEE.
- Authors: Yu, Shuo , Qing, Qing , Zhang, Chen , Shehzad, Ahsan , Oatley, Giles , Xia, Feng
- Date: 2021
- Type: Text , Journal article , Review
- Relation: IEEE Transactions on Computational Social Systems Vol. 8, no. 4 (2021), p. 989-1002
- Full Text:
- Reviewed:
- Description: COVID-19 has spread all over the world, having an enormous effect on our daily life and work. In response to the epidemic, a lot of important decisions need to be taken to save communities and economies worldwide. Data clearly play a vital role in effective decision-making. Data-driven decision-making uses data-related evidence and insights to guide the decision-making process and verify the plan of action before it is committed. To better handle the epidemic, governments and policy-making institutes have investigated abundant data originating from COVID-19. These data include those related to medicine, knowledge, media, and so on. Based on these data, many prevention and control policies are made. In this survey article, we summarize the progress of data-driven decision-making in the response to COVID-19, including COVID-19 prevention and control, psychological counseling, financial aid, work resumption, and school reopening. We also propose some current challenges and open issues in data-driven decision-making, including data collection and quality, complex data analysis, and fairness in decision-making. This survey article sheds light on current policy-making driven by data, which also provides a feasible direction for further scientific research. © 2014 IEEE.
Decision behavior based private vehicle trajectory generation towards smart cities
- Chen, Qiao, Ma, Kai, Hou, Mingliang, Kong, Xiangjie, Xia, Feng
- Authors: Chen, Qiao , Ma, Kai , Hou, Mingliang , Kong, Xiangjie , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 18th International Conference on Web Information Systems and Applications, WISA 2021 Vol. 12999 LNCS, p. 109-120
- Full Text:
- Reviewed:
- Description: In contrast with the condition that the trajectory dataset of floating cars (taxis) can be easily obtained from the Internet, it is hard to get the trajectory data of social vehicles (private vehicles) because of personal privacy and government policies. This paper absorbs the idea of game theory, considers the influence of individuals in the group, and proposes a decision behavior based dataset generation (DBDG) model of vehicles to predict future inter-regional traffic. In addition, we adopt simulation tools and generative adversarial networks to train the trajectory prediction model so that the private vehicle trajectory dataset conforming to social rules (e.g., collisionless) is generated. Finally, we construct from macroscopic and microscopic perspectives to verify dataset generation methods proposed in this paper. The results show that the generated data not only has high accuracy and is valuable but can provide strong data support for the Internet of Vehicles and transportation research work. © 2021, Springer Nature Switzerland AG.
- Authors: Chen, Qiao , Ma, Kai , Hou, Mingliang , Kong, Xiangjie , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 18th International Conference on Web Information Systems and Applications, WISA 2021 Vol. 12999 LNCS, p. 109-120
- Full Text:
- Reviewed:
- Description: In contrast with the condition that the trajectory dataset of floating cars (taxis) can be easily obtained from the Internet, it is hard to get the trajectory data of social vehicles (private vehicles) because of personal privacy and government policies. This paper absorbs the idea of game theory, considers the influence of individuals in the group, and proposes a decision behavior based dataset generation (DBDG) model of vehicles to predict future inter-regional traffic. In addition, we adopt simulation tools and generative adversarial networks to train the trajectory prediction model so that the private vehicle trajectory dataset conforming to social rules (e.g., collisionless) is generated. Finally, we construct from macroscopic and microscopic perspectives to verify dataset generation methods proposed in this paper. The results show that the generated data not only has high accuracy and is valuable but can provide strong data support for the Internet of Vehicles and transportation research work. © 2021, Springer Nature Switzerland AG.
Deep matrix factorization for trust-aware recommendation in social networks
- Wan, Liangtian, Xia, Feng, Kong, Xiangjie, Hsu, Ching-Hsien, Huang, Runhe, Ma, Jianhua
- Authors: Wan, Liangtian , Xia, Feng , Kong, Xiangjie , Hsu, Ching-Hsien , Huang, Runhe , Ma, Jianhua
- Date: 2021
- Type: Text , Journal article
- Relation: IEEE Transactions on Network Science and Engineering Vol. 8, no. 1 (2021), p. 511-528
- Full Text:
- Reviewed:
- Description: Recent years have witnessed remarkable information overload in online social networks, and social network based approaches for recommender systems have been widely studied. The trust information in social networks among users is an important factor for improving recommendation performance. Many successful recommendation tasks are treated as the matrix factorization problems. However, the prediction performance of matrix factorization based methods largely depends on the matrixes initialization of users and items. To address this challenge, we develop a novel trust-aware approach based on deep learning to alleviate the initialization dependence. First, we propose two deep matrix factorization (DMF) techniques, i.e., linear DMF and non-linear DMF to extract features from the user-item rating matrix for improving the initialization accuracy. The trust relationship is integrated into the DMF model according to the preference similarity and the derivations of users on items. Second, we exploit deep marginalized Denoising Autoencoder (Deep-MDAE) to extract the latent representation in the hidden layer from the trust relationship matrix to approximate the user factor matrix factorized from the user-item rating matrix. The community regularization is integrated in the joint optimization function to take neighbours' effects into consideration. The results of DMF are applied to initialize the updating variables of Deep-MDAE in order to further improve the recommendation performance. Finally, we validate that the proposed approach outperforms state-of-the-art baselines for recommendation, especially for the cold-start users. © 2013 IEEE.
- Authors: Wan, Liangtian , Xia, Feng , Kong, Xiangjie , Hsu, Ching-Hsien , Huang, Runhe , Ma, Jianhua
- Date: 2021
- Type: Text , Journal article
- Relation: IEEE Transactions on Network Science and Engineering Vol. 8, no. 1 (2021), p. 511-528
- Full Text:
- Reviewed:
- Description: Recent years have witnessed remarkable information overload in online social networks, and social network based approaches for recommender systems have been widely studied. The trust information in social networks among users is an important factor for improving recommendation performance. Many successful recommendation tasks are treated as the matrix factorization problems. However, the prediction performance of matrix factorization based methods largely depends on the matrixes initialization of users and items. To address this challenge, we develop a novel trust-aware approach based on deep learning to alleviate the initialization dependence. First, we propose two deep matrix factorization (DMF) techniques, i.e., linear DMF and non-linear DMF to extract features from the user-item rating matrix for improving the initialization accuracy. The trust relationship is integrated into the DMF model according to the preference similarity and the derivations of users on items. Second, we exploit deep marginalized Denoising Autoencoder (Deep-MDAE) to extract the latent representation in the hidden layer from the trust relationship matrix to approximate the user factor matrix factorized from the user-item rating matrix. The community regularization is integrated in the joint optimization function to take neighbours' effects into consideration. The results of DMF are applied to initialize the updating variables of Deep-MDAE in order to further improve the recommendation performance. Finally, we validate that the proposed approach outperforms state-of-the-art baselines for recommendation, especially for the cold-start users. © 2013 IEEE.
Deep video anomaly detection : opportunities and challenges
- Ren, Jing, Xia, Feng, Liu, Yemeng, Lee, Ivan
- Authors: Ren, Jing , Xia, Feng , Liu, Yemeng , Lee, Ivan
- 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. 959-966
- Full Text:
- Reviewed:
- Description: Anomaly detection is a popular and vital task in various research contexts, which has been studied for several decades. To ensure the safety of people's lives and assets, video surveillance has been widely deployed in various public spaces, such as crossroads, elevators, hospitals, banks, and even in private homes. Deep learning has shown its capacity in a number of domains, ranging from acoustics, images, to natural language processing. However, it is non-trivial to devise intelligent video anomaly detection systems cause anomalies significantly differ from each other in different application scenarios. There are numerous advantages if such intelligent systems could be realised in our daily lives, such as saving human resources in a large degree, reducing financial burden on the government, and identifying the anomalous behaviours timely and accurately. Recently, many studies on extending deep learning models for solving anomaly detection problems have emerged, resulting in beneficial advances in deep video anomaly detection techniques. In this paper, we present a comprehensive review of deep learning-based methods to detect the video anomalies from a new perspective. Specifically, we summarise the opportunities and challenges of deep learning models on video anomaly detection tasks, respectively. We put forth several potential future research directions of intelligent video anomaly detection system in various application domains. Moreover, we summarise the characteristics and technical problems in current deep learning methods for video anomaly detection. © 2021 IEEE.
- Authors: Ren, Jing , Xia, Feng , Liu, Yemeng , Lee, Ivan
- 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. 959-966
- Full Text:
- Reviewed:
- Description: Anomaly detection is a popular and vital task in various research contexts, which has been studied for several decades. To ensure the safety of people's lives and assets, video surveillance has been widely deployed in various public spaces, such as crossroads, elevators, hospitals, banks, and even in private homes. Deep learning has shown its capacity in a number of domains, ranging from acoustics, images, to natural language processing. However, it is non-trivial to devise intelligent video anomaly detection systems cause anomalies significantly differ from each other in different application scenarios. There are numerous advantages if such intelligent systems could be realised in our daily lives, such as saving human resources in a large degree, reducing financial burden on the government, and identifying the anomalous behaviours timely and accurately. Recently, many studies on extending deep learning models for solving anomaly detection problems have emerged, resulting in beneficial advances in deep video anomaly detection techniques. In this paper, we present a comprehensive review of deep learning-based methods to detect the video anomalies from a new perspective. Specifically, we summarise the opportunities and challenges of deep learning models on video anomaly detection tasks, respectively. We put forth several potential future research directions of intelligent video anomaly detection system in various application domains. Moreover, we summarise the characteristics and technical problems in current deep learning methods for video anomaly detection. © 2021 IEEE.
Detecting outlier patterns with query-based artificially generated searching conditions
- Yu, Shuo, Xia, Feng, Sun, Yuchen, Tang, Tao, Yan, Xiaoran, Lee, Ivan
- Authors: Yu, Shuo , Xia, Feng , Sun, Yuchen , Tang, Tao , Yan, Xiaoran , Lee, Ivan
- Date: 2021
- Type: Text , Journal article
- Relation: IEEE Transactions on Computational Social Systems Vol. 8, no. 1 (2021), p. 134-147
- Full Text:
- Reviewed:
- Description: In the age of social computing, finding interesting network patterns or motifs is significant and critical for various areas, such as decision intelligence, intrusion detection, medical diagnosis, social network analysis, fake news identification, and national security. However, subgraph matching remains a computationally challenging problem, let alone identifying special motifs among them. This is especially the case in large heterogeneous real-world networks. In this article, we propose an efficient solution for discovering and ranking human behavior patterns based on network motifs by exploring a user's query in an intelligent way. Our method takes advantage of the semantics provided by a user's query, which in turn provides the mathematical constraint that is crucial for faster detection. We propose an approach to generate query conditions based on the user's query. In particular, we use meta paths between the nodes to define target patterns as well as their similarities, leading to efficient motif discovery and ranking at the same time. The proposed method is examined in a real-world academic network using different similarity measures between the nodes. The experiment result demonstrates that our method can identify interesting motifs and is robust to the choice of similarity measures. © 2014 IEEE.
- Authors: Yu, Shuo , Xia, Feng , Sun, Yuchen , Tang, Tao , Yan, Xiaoran , Lee, Ivan
- Date: 2021
- Type: Text , Journal article
- Relation: IEEE Transactions on Computational Social Systems Vol. 8, no. 1 (2021), p. 134-147
- Full Text:
- Reviewed:
- Description: In the age of social computing, finding interesting network patterns or motifs is significant and critical for various areas, such as decision intelligence, intrusion detection, medical diagnosis, social network analysis, fake news identification, and national security. However, subgraph matching remains a computationally challenging problem, let alone identifying special motifs among them. This is especially the case in large heterogeneous real-world networks. In this article, we propose an efficient solution for discovering and ranking human behavior patterns based on network motifs by exploring a user's query in an intelligent way. Our method takes advantage of the semantics provided by a user's query, which in turn provides the mathematical constraint that is crucial for faster detection. We propose an approach to generate query conditions based on the user's query. In particular, we use meta paths between the nodes to define target patterns as well as their similarities, leading to efficient motif discovery and ranking at the same time. The proposed method is examined in a real-world academic network using different similarity measures between the nodes. The experiment result demonstrates that our method can identify interesting motifs and is robust to the choice of similarity measures. © 2014 IEEE.
Educational big data : predictions, applications and challenges
- Bai, Xiaomei, Zhang, Fuli, Li, Jinzhou, Guo, Teng, Xia, Feng
- Authors: Bai, Xiaomei , Zhang, Fuli , Li, Jinzhou , Guo, Teng , Xia, Feng
- Date: 2021
- Type: Text , Journal article , Review
- Relation: Big Data Research Vol. 26, no. (2021), p.
- Full Text:
- Reviewed:
- Description: Educational big data is becoming a strategic educational asset, exceptionally significant in advancing educational reform. The term educational big data stems from the rapidly growing educational data development, including students' inherent attributes, learning behavior, and psychological state. Educational big data has many applications that can be used for educational administration, teaching innovation, and research management. The representative examples of such applications are student academic performance prediction, employment recommendation, and financial support for low-income students. Different empirical studies have shown that it is possible to predict student performance in the courses during the next term. Predictive research for the higher education stage has become an attractive area of study since it allowed us to predict student behavior. In this survey, we will review predictive research, its applications, and its challenges. We first introduce the significance and background of educational big data. Second, we review the students' academic performance prediction research, such as factors influencing students' academic performance, predicting models, evaluating indices. Third, we introduce the applications of educational big data such as prediction, recommendation, and evaluation. Finally, we investigate challenging research issues in this area. This discussion aims to provide a comprehensive overview of educational big data. © 2021 Elsevier Inc. **Please note that there are multiple authors for this article therefore only the name of the first 5 including Federation University Australia affiliate “Feng Xia” is provided in this record**
- Authors: Bai, Xiaomei , Zhang, Fuli , Li, Jinzhou , Guo, Teng , Xia, Feng
- Date: 2021
- Type: Text , Journal article , Review
- Relation: Big Data Research Vol. 26, no. (2021), p.
- Full Text:
- Reviewed:
- Description: Educational big data is becoming a strategic educational asset, exceptionally significant in advancing educational reform. The term educational big data stems from the rapidly growing educational data development, including students' inherent attributes, learning behavior, and psychological state. Educational big data has many applications that can be used for educational administration, teaching innovation, and research management. The representative examples of such applications are student academic performance prediction, employment recommendation, and financial support for low-income students. Different empirical studies have shown that it is possible to predict student performance in the courses during the next term. Predictive research for the higher education stage has become an attractive area of study since it allowed us to predict student behavior. In this survey, we will review predictive research, its applications, and its challenges. We first introduce the significance and background of educational big data. Second, we review the students' academic performance prediction research, such as factors influencing students' academic performance, predicting models, evaluating indices. Third, we introduce the applications of educational big data such as prediction, recommendation, and evaluation. Finally, we investigate challenging research issues in this area. This discussion aims to provide a comprehensive overview of educational big data. © 2021 Elsevier Inc. **Please note that there are multiple authors for this article therefore only the name of the first 5 including Federation University Australia affiliate “Feng Xia” is provided in this record**
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.
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.
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.
How to optimize an academic team when the outlier member is leaving?
- Yu, Shuo, Liu, Jiaying, Wei, Haoran, Xia, Feng, Tong, Hanghang
- Authors: Yu, Shuo , Liu, Jiaying , Wei, Haoran , Xia, Feng , Tong, Hanghang
- Date: 2021
- Type: Text , Journal article
- Relation: IEEE Intelligent Systems Vol. 36, no. 3 (May-Jun 2021), p. 23-30
- Full Text:
- Reviewed:
- Description: An academic team is a highly cohesive collaboration group of scholars, which has been recognized as an effective way to improve scientific output in terms of both quality and quantity. However, the high staff turnover brings about a series of problems that may have negative influences on team performance. To address this challenge, we first detect the tendency of the member who may potentially leave. Here, the outlierness is defined with respect to familiarity, which is quantified by using collaboration intensity. It is assumed that if a team member has a higher familiarity with scholars outside the team, then this member might probably leave the team. To minimize the influence caused by the leaving of such an outlier member, we propose an optimization solution to find a proper candidate who can replace the outlier member. Based on random walk with graph kernel, our solution involves familiarity matching, skill matching, as well as structure matching. The proposed approach proves to be effective and outperforms existing methods when applied to computer science academic teams.
- Authors: Yu, Shuo , Liu, Jiaying , Wei, Haoran , Xia, Feng , Tong, Hanghang
- Date: 2021
- Type: Text , Journal article
- Relation: IEEE Intelligent Systems Vol. 36, no. 3 (May-Jun 2021), p. 23-30
- Full Text:
- Reviewed:
- Description: An academic team is a highly cohesive collaboration group of scholars, which has been recognized as an effective way to improve scientific output in terms of both quality and quantity. However, the high staff turnover brings about a series of problems that may have negative influences on team performance. To address this challenge, we first detect the tendency of the member who may potentially leave. Here, the outlierness is defined with respect to familiarity, which is quantified by using collaboration intensity. It is assumed that if a team member has a higher familiarity with scholars outside the team, then this member might probably leave the team. To minimize the influence caused by the leaving of such an outlier member, we propose an optimization solution to find a proper candidate who can replace the outlier member. Based on random walk with graph kernel, our solution involves familiarity matching, skill matching, as well as structure matching. The proposed approach proves to be effective and outperforms existing methods when applied to computer science academic teams.
In your face : sentiment analysis of metaphor with facial expressive features
- Zhang, Dongyu, Zhang, Minghao, Guo, Teng, Peng, Ciyuan, Saikrishna, Vidya, Xia, Feng
- Authors: Zhang, Dongyu , Zhang, Minghao , Guo, Teng , Peng, Ciyuan , Saikrishna, Vidya , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 International Joint Conference on Neural Networks, IJCNN 2021 Vol. 2021-July
- Full Text:
- Reviewed:
- Description: Metaphor plays an important role in human communication, which often conveys and evokes sentiments. Numerous approaches to sentiment analysis of metaphors have thus gained attention in natural language processing (NLP). The primary focus of these approaches is on linguistic features and text rather than other modal information and data. However, visual features such as facial expressions also play an important role in expressing sentiments. In this paper, we present a novel neural network approach to sentiment analysis of metaphorical expressions that combines both linguistic and visual features and refer to it as the multimodal model approach. For this, we create a Chinese dataset, containing textual data from metaphorical sentences along with visual data on synchronized facial images. The experimental results indicate that our multimodal model outperforms several other linguistic and visual models, and also outperforms the state-of-the-art methods. The contribution is realized in terms of novelty of the approach and creation of a new, sizeable, and scarce dataset with linguistic and synchronized facial expressive image data. The dataset is particularly useful in languages other than English and the approach addresses one of the most challenging NLP issue: sentiment analysis in metaphor. © 2021 IEEE.
- Authors: Zhang, Dongyu , Zhang, Minghao , Guo, Teng , Peng, Ciyuan , Saikrishna, Vidya , Xia, Feng
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 International Joint Conference on Neural Networks, IJCNN 2021 Vol. 2021-July
- Full Text:
- Reviewed:
- Description: Metaphor plays an important role in human communication, which often conveys and evokes sentiments. Numerous approaches to sentiment analysis of metaphors have thus gained attention in natural language processing (NLP). The primary focus of these approaches is on linguistic features and text rather than other modal information and data. However, visual features such as facial expressions also play an important role in expressing sentiments. In this paper, we present a novel neural network approach to sentiment analysis of metaphorical expressions that combines both linguistic and visual features and refer to it as the multimodal model approach. For this, we create a Chinese dataset, containing textual data from metaphorical sentences along with visual data on synchronized facial images. The experimental results indicate that our multimodal model outperforms several other linguistic and visual models, and also outperforms the state-of-the-art methods. The contribution is realized in terms of novelty of the approach and creation of a new, sizeable, and scarce dataset with linguistic and synchronized facial expressive image data. The dataset is particularly useful in languages other than English and the approach addresses one of the most challenging NLP issue: sentiment analysis in metaphor. © 2021 IEEE.