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.
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.
- «
- ‹
- 1
- ›
- »