Abnormal entity-aware knowledge graph completion
- Sun, Ke, Yu, Shuo, Peng, Ciyuan, Li, Xiang, Naseriparsa, Mehdi, Xia, Feng
- Authors: Sun, Ke , Yu, Shuo , Peng, Ciyuan , Li, Xiang , Naseriparsa, Mehdi , Xia, Feng
- Date: 2022
- Type: Text , Conference paper
- Relation: 22nd IEEE International Conference on Data Mining Workshops, ICDMW 2022, Orlando USA, 28 November to 1 December 2022, Proceedings: 22nd IEEE International Conference on Data Mining Workshops Vol. 2022-November, p. 891-900
- Full Text: false
- Reviewed:
- Description: In real-world scenarios, knowledge graphs remain incomplete and contain abnormal information, such as redundan-cies, contradictions, inconsistencies, misspellings, and abnormal values. These shortcomings in the knowledge graphs potentially affect service quality in many applications. Although many approaches are proposed to perform knowledge graph completion, they are incapable of handling the abnormal information of knowledge graphs. Therefore, to address the abnormal information issue for the knowledge graph completion task, we design a novel knowledge graph completion framework called ABET, which specially focuses on abnormal entities. ABET consists of two components: a) abnormal entity prediction and b) knowledge graph completion. Firstly, the prediction component automati-cally predicts the abnormal entities in knowledge graphs. Then, the completion component effectively captures the heterogeneous structural information and the high-order features of neighbours based on different relations. Experiments demonstrate that ABET is an effective knowledge graph completion framework, which has made significant improvements over baselines. We further verify that ABET is robust for knowledge graph completion task with abnormal entities. © 2022 IEEE.
Attributed graph force learning
- Sun, Ke, Xia, Feng, Liu, Jiaying, Xu, Bo, Saikrishna, Vidya, Aggarwal, Charu
- Authors: Sun, Ke , Xia, Feng , Liu, Jiaying , Xu, Bo , Saikrishna, Vidya , Aggarwal, Charu
- Date: 2024
- Type: Text , Journal article
- Relation: IEEE Transactions on Neural Networks and Learning Systems Vol. 35, no. 4 (2024), p. 4502-4515
- Full Text: false
- Reviewed:
- Description: In numerous network analysis tasks, feature representation plays an imperative role. Due to the intrinsic nature of networks being discrete, enormous challenges are imposed on their effective usage. There has been a significant amount of attention on network feature learning in recent times that has the potential of mapping discrete features into a continuous feature space. The methods, however, lack preserving the structural information owing to the utilization of random negative sampling during the training phase. The ability to effectively join attribute information to embedding feature space is also compromised. To address the shortcomings identified, a novel attribute force-based graph (AGForce) learning model is proposed that keeps the structural information intact along with adaptively joining attribute information to the node's features. To demonstrate the effectiveness of the proposed framework, comprehensive experiments on benchmark datasets are performed. AGForce based on the spring-electrical model extends opportunities to simulate node interaction for graph learning. © 2012 IEEE.
COVID-19 datasets : a brief overview
- Sun, Ke, Li, Wuyang, Saikrishna, Vidya, Chadhar, Mehmood, Xia, Feng
- Authors: Sun, Ke , Li, Wuyang , Saikrishna, Vidya , Chadhar, Mehmood , Xia, Feng
- Date: 2022
- Type: Text , Journal article
- Relation: Computer Science and Information Systems Vol. 19, no. 3 (2022), p. 1115-1132
- Full Text:
- Reviewed:
- Description: The outbreak of the COVID-19 pandemic affects lives and social-economic development around the world. The affecting of the pandemic has motivated researchers from different domains to find effective solutions to diagnose, prevent, and estimate the pandemic and relieve its adverse effects. Numerous COVID-19 datasets are built from these studies and are available to the public. These datasets can be used for disease diagnosis and case prediction, speeding up solving problems caused by the pandemic. To meet the needs of researchers to understand various COVID-19 datasets, we examine and provide an overview of them. We organise the majority of these datasets into three categories based on the category of ap-plications, i.e., time-series, knowledge base, and media-based datasets. Organising COVID-19 datasets into appropriate categories can help researchers hold their focus on methodology rather than the datasets. In addition, applications and COVID-19 datasets suffer from a series of problems, such as privacy and quality. We discuss these issues as well as potentials of COVID-19 datasets. © 2022, ComSIS Consortium. All rights reserved.
- Authors: Sun, Ke , Li, Wuyang , Saikrishna, Vidya , Chadhar, Mehmood , Xia, Feng
- Date: 2022
- Type: Text , Journal article
- Relation: Computer Science and Information Systems Vol. 19, no. 3 (2022), p. 1115-1132
- Full Text:
- Reviewed:
- Description: The outbreak of the COVID-19 pandemic affects lives and social-economic development around the world. The affecting of the pandemic has motivated researchers from different domains to find effective solutions to diagnose, prevent, and estimate the pandemic and relieve its adverse effects. Numerous COVID-19 datasets are built from these studies and are available to the public. These datasets can be used for disease diagnosis and case prediction, speeding up solving problems caused by the pandemic. To meet the needs of researchers to understand various COVID-19 datasets, we examine and provide an overview of them. We organise the majority of these datasets into three categories based on the category of ap-plications, i.e., time-series, knowledge base, and media-based datasets. Organising COVID-19 datasets into appropriate categories can help researchers hold their focus on methodology rather than the datasets. In addition, applications and COVID-19 datasets suffer from a series of problems, such as privacy and quality. We discuss these issues as well as potentials of COVID-19 datasets. © 2022, ComSIS Consortium. All rights reserved.
From electroencephalogram data to brain networks : graph-learning-based brain disease diagnosis
- Sun, Ke, Peng, Ciyuan, Yu, Shuo, Han, Zhuoyang, Xia, Feng
- Authors: Sun, Ke , Peng, Ciyuan , Yu, Shuo , Han, Zhuoyang , Xia, Feng
- Date: 2024
- Type: Text , Journal article
- Relation: IEEE Intelligent Systems Vol. 39, no. 2 (2024), p. 21-29
- Full Text: false
- Reviewed:
- Description: Brain networks are built according to the structures or neural activities of different brain regions, which can be modeled as complex networks. Many studies exploit brains from the perspective of graph learning to diagnose the nerve diseases of brains. However, many of these algorithms are unable to automatically construct brain function topology based on electroencephalogram (EEG) and fail to capture the global features of multichannel EEG signals for whole-graph embedding. To address these challenging issues, we propose an attention-based whole-graph learning model for the diagnosis of brain diseases, namely, MAINS, which can adaptively construct brain functional topology from EEG signals and effectively embed multiple node features and the global structural features of brain networks into the whole-graph representations. We validated the model by conducting classification (diagnosis) experiments on real EEG datasets. Comprehensive experimental results demonstrate the superiority of the proposed approach over state-of-the-art methods. © 2001-2011 IEEE.
Graph Force Learning
- Sun, Ke, Liu, Jiaying, Yu, Shuo, Xu, Bo, Xia, Feng
- Authors: Sun, Ke , Liu, Jiaying , Yu, Shuo , Xu, Bo , Xia, Feng
- Date: 2020
- Type: Text , Conference paper
- Relation: 8th IEEE International Conference on Big Data, Big Data 2020 p. 2987-2994
- Full Text:
- Reviewed:
- Description: Features representation leverages the great power in network analysis tasks. However, most features are discrete which poses tremendous challenges to effective use. Recently, increasing attention has been paid on network feature learning, which could map discrete features to continued space. Unfortunately, current studies fail to fully preserve the structural information in the feature space due to random negative sampling strategy during training. To tackle this problem, we study the problem of feature learning and novelty propose a force-based graph learning model named GForce inspired by the spring-electrical model. GForce assumes that nodes are in attractive forces and repulsive forces, thus leading to the same representation with the original structural information in feature learning. Comprehensive experiments on three benchmark datasets demonstrate the effectiveness of the proposed framework. Furthermore, GForce opens up opportunities to use physics models to model node interaction for graph learning. © 2020 IEEE.
- Authors: Sun, Ke , Liu, Jiaying , Yu, Shuo , Xu, Bo , Xia, Feng
- Date: 2020
- Type: Text , Conference paper
- Relation: 8th IEEE International Conference on Big Data, Big Data 2020 p. 2987-2994
- Full Text:
- Reviewed:
- Description: Features representation leverages the great power in network analysis tasks. However, most features are discrete which poses tremendous challenges to effective use. Recently, increasing attention has been paid on network feature learning, which could map discrete features to continued space. Unfortunately, current studies fail to fully preserve the structural information in the feature space due to random negative sampling strategy during training. To tackle this problem, we study the problem of feature learning and novelty propose a force-based graph learning model named GForce inspired by the spring-electrical model. GForce assumes that nodes are in attractive forces and repulsive forces, thus leading to the same representation with the original structural information in feature learning. Comprehensive experiments on three benchmark datasets demonstrate the effectiveness of the proposed framework. Furthermore, GForce opens up opportunities to use physics models to model node interaction for graph learning. © 2020 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.
Network representation learning: From traditional feature learning to deep learning
- Sun, Ke, Wang, Lei, Xu, Bo, Zhao, Wenhong, Teng, Shyh, Xia, Feng
- Authors: Sun, Ke , Wang, Lei , Xu, Bo , Zhao, Wenhong , Teng, Shyh , Xia, Feng
- Date: 2020
- Type: Text , Journal article
- Relation: IEEE Access Vol. 8, no. (2020), p. 205600-205617
- Full Text:
- Reviewed:
- Description: Network representation learning (NRL) is an effective graph analytics technique and promotes users to deeply understand the hidden characteristics of graph data. It has been successfully applied in many real-world tasks related to network science, such as social network data processing, biological information processing, and recommender systems. Deep Learning is a powerful tool to learn data features. However, it is non-trivial to generalize deep learning to graph-structured data since it is different from the regular data such as pictures having spatial information and sounds having temporal information. Recently, researchers proposed many deep learning-based methods in the area of NRL. In this survey, we investigate classical NRL from traditional feature learning method to the deep learning-based model, analyze relationships between them, and summarize the latest progress. Finally, we discuss open issues considering NRL and point out the future directions in this field. © 2020 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.
- Authors: Sun, Ke , Wang, Lei , Xu, Bo , Zhao, Wenhong , Teng, Shyh , Xia, Feng
- Date: 2020
- Type: Text , Journal article
- Relation: IEEE Access Vol. 8, no. (2020), p. 205600-205617
- Full Text:
- Reviewed:
- Description: Network representation learning (NRL) is an effective graph analytics technique and promotes users to deeply understand the hidden characteristics of graph data. It has been successfully applied in many real-world tasks related to network science, such as social network data processing, biological information processing, and recommender systems. Deep Learning is a powerful tool to learn data features. However, it is non-trivial to generalize deep learning to graph-structured data since it is different from the regular data such as pictures having spatial information and sounds having temporal information. Recently, researchers proposed many deep learning-based methods in the area of NRL. In this survey, we investigate classical NRL from traditional feature learning method to the deep learning-based model, analyze relationships between them, and summarize the latest progress. Finally, we discuss open issues considering NRL and point out the future directions in this field. © 2020 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.
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.
Robust graph neural networks via ensemble learning
- Lin, Qi, Yu, Shuo, Sun, Ke, Zhao, Wenhong, Alfarraj, Osama, Tolba, Amr, Xia, Feng
- Authors: Lin, Qi , Yu, Shuo , Sun, Ke , Zhao, Wenhong , Alfarraj, Osama , Tolba, Amr , Xia, Feng
- Date: 2022
- Type: Text , Journal article
- Relation: Mathematics Vol. 10, no. 8 (2022), p.
- Full Text:
- Reviewed:
- Description: Graph neural networks (GNNs) have demonstrated a remarkable ability in the task of semi-supervised node classification. However, most existing GNNs suffer from the nonrobustness issues, which poses a great challenge for applying GNNs into sensitive scenarios. Some researchers concentrate on constructing an ensemble model to mitigate the nonrobustness issues. Nevertheless, these methods ignore the interaction among base models, leading to similar graph representations. Moreover, due to the deterministic propagation applied in most existing GNNs, each node highly relies on its neighbors, leaving the nodes to be sensitive to perturbations. Therefore, in this paper, we propose a novel framework of graph ensemble learning based on knowledge passing (called GEL) to address the above issues. In order to achieve interaction, we consider the predictions of prior models as knowledge to obtain more reliable predictions. Moreover, we design a multilayer DropNode propagation strategy to reduce each node’s dependence on particular neighbors. This strategy also empowers each node to aggregate information from diverse neighbors, alleviating oversmoothing issues. We conduct experiments on three benchmark datasets, including Cora, Citeseer, and Pubmed. GEL outperforms GCN by more than 5% in terms of accuracy across all three datasets and also performs better than other state-of-the-art baselines. Extensive experimental results also show that the GEL alleviates the nonrobustness and oversmoothing issues. © 2022 by the authors. Licensee MDPI, Basel, Switzerland.
- Authors: Lin, Qi , Yu, Shuo , Sun, Ke , Zhao, Wenhong , Alfarraj, Osama , Tolba, Amr , Xia, Feng
- Date: 2022
- Type: Text , Journal article
- Relation: Mathematics Vol. 10, no. 8 (2022), p.
- Full Text:
- Reviewed:
- Description: Graph neural networks (GNNs) have demonstrated a remarkable ability in the task of semi-supervised node classification. However, most existing GNNs suffer from the nonrobustness issues, which poses a great challenge for applying GNNs into sensitive scenarios. Some researchers concentrate on constructing an ensemble model to mitigate the nonrobustness issues. Nevertheless, these methods ignore the interaction among base models, leading to similar graph representations. Moreover, due to the deterministic propagation applied in most existing GNNs, each node highly relies on its neighbors, leaving the nodes to be sensitive to perturbations. Therefore, in this paper, we propose a novel framework of graph ensemble learning based on knowledge passing (called GEL) to address the above issues. In order to achieve interaction, we consider the predictions of prior models as knowledge to obtain more reliable predictions. Moreover, we design a multilayer DropNode propagation strategy to reduce each node’s dependence on particular neighbors. This strategy also empowers each node to aggregate information from diverse neighbors, alleviating oversmoothing issues. We conduct experiments on three benchmark datasets, including Cora, Citeseer, and Pubmed. GEL outperforms GCN by more than 5% in terms of accuracy across all three datasets and also performs better than other state-of-the-art baselines. Extensive experimental results also show that the GEL alleviates the nonrobustness and oversmoothing issues. © 2022 by the authors. Licensee MDPI, Basel, Switzerland.
- «
- ‹
- 1
- ›
- »