RoGAT: a robust GNN combined revised GAT with adjusted graphs

Graph Neural Networks(GNNs) are useful deep learning models to deal with the non-Euclid data. However, recent works show that GNNs are vulnerable to adversarial attacks. Small perturbations can lead to poor performance in many GNNs, such as Graph attention networks(GATs). Therefore, enhancing the robustness of GNNs is a critical problem. Robust GAT(RoGAT) is proposed to improve the robustness of GNNs in this paper, . Note that the original GAT uses the attention mechanism for different edges but is still sensitive to the perturbation, RoGAT adjusts the edges' weight to adjust the attention scores progressively. Firstly, RoGAT tunes the edges weight based on the assumption that the adjacent nodes should have similar nodes. Secondly, RoGAT further tunes the features to eliminate feature's noises since even for the clean graph, there exists some unreasonable data. Then, we trained the adjusted GAT model to defense the adversarial attacks. Different experiments against targeted and untargeted attacks demonstrate that RoGAT outperforms significantly than most the state-of-the-art defense methods. The implementation of RoGAT based on the DeepRobust repository for adversarial attacks.

[1]  M. McPherson,et al.  Birds of a Feather: Homophily in Social Networks , 2001 .

[2]  Saba A. Al-Sayouri,et al.  All You Need Is Low (Rank): Defending Against Adversarial Attacks on Graphs , 2020, WSDM.

[3]  Pietro Liò,et al.  Graph Attention Networks , 2017, ICLR.

[4]  Takanori Maehara,et al.  Revisiting Graph Neural Networks: All We Have is Low-Pass Filters , 2019, ArXiv.

[5]  Jiliang Tang,et al.  DeepRobust: A PyTorch Library for Adversarial Attacks and Defenses , 2020, ArXiv.

[6]  Stephan Gunnemann,et al.  Adversarial Attacks on Graph Neural Networks via Meta Learning , 2019, ICLR.

[7]  Suhang Wang,et al.  Graph Structure Learning for Robust Graph Neural Networks , 2020, KDD.

[8]  Patrice Marcotte,et al.  An overview of bilevel optimization , 2007, Ann. Oper. Res..

[9]  Joan Bruna,et al.  Spectral Networks and Locally Connected Networks on Graphs , 2013, ICLR.

[10]  Ah Chung Tsoi,et al.  The Graph Neural Network Model , 2009, IEEE Transactions on Neural Networks.

[11]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[12]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[13]  Jure Leskovec,et al.  Inductive Representation Learning on Large Graphs , 2017, NIPS.

[14]  Samuel S. Schoenholz,et al.  Neural Message Passing for Quantum Chemistry , 2017, ICML.

[15]  Jun Wang,et al.  Adaptive Structural Fingerprints for Graph Attention Networks , 2020, ICLR.

[16]  Sijia Liu,et al.  Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective , 2019, IJCAI.

[17]  Xavier Bresson,et al.  Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering , 2016, NIPS.

[18]  Le Song,et al.  Adversarial Attack on Graph Structured Data , 2018, ICML.

[19]  Liming Zhu,et al.  Adversarial Examples on Graph Data: Deep Insights into Attack and Defense , 2019 .

[20]  Xiang Zhang,et al.  GNNGuard: Defending Graph Neural Networks against Adversarial Attacks , 2020, NeurIPS.

[21]  Wenwu Zhu,et al.  Robust Graph Convolutional Networks Against Adversarial Attacks , 2019, KDD.

[22]  Stephan Günnemann,et al.  Adversarial Attacks on Neural Networks for Graph Data , 2018, KDD.

[23]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[24]  Prasenjit Mitra,et al.  Transferring Robustness for Graph Neural Network Against Poisoning Attacks , 2019, WSDM.