- Title
- Robust graph neural networks via ensemble learning
- Creator
- Lin, Qi; Yu, Shuo; Sun, Ke; Zhao, Wenhong; Alfarraj, Osama; Tolba, Amr; Xia, Feng
- Date
- 2022
- Type
- Text; Journal article
- Identifier
- http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/191020
- Identifier
- vital:17737
- Identifier
-
https://doi.org/10.3390/math10081300
- Identifier
- ISSN:2227-7390 (ISSN)
- Abstract
- 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.
- Publisher
- MDPI
- Relation
- Mathematics Vol. 10, no. 8 (2022), p.
- Rights
- All metadata describing materials held in, or linked to, the repository is freely available under a CC0 licence
- Rights
- https://creativecommons.org/licenses/by/4.0/
- Rights
- Copyright © 2022 by the authors
- Rights
- Open Access
- Subject
- 49 Mathematical Sciences; Ensemble learning; Graph learning; Graph neural networks; Knowledge passing; Multilayer dropnode propagation
- Full Text
- Reviewed
- Funder
- This work was funded by the Researchers Supporting Project No. RSP-2021/102 at King Saud University, Riyadh, Saudi Arabia.
- Hits: 1144
- Visitors: 1187
- Downloads: 48
Thumbnail | File | Description | Size | Format | |||
---|---|---|---|---|---|---|---|
View Details Download | SOURCE1 | Published version | 1 MB | Adobe Acrobat PDF | View Details Download |