research-article

Robust Mid-Pass Filtering Graph Convolutional Networks

Authors:

Jincheng Huang,

Dongmei ZhangAuthors Info & Claims

WWW '23: Proceedings of the ACM Web Conference 2023

Pages 328 - 338

https://doi.org/10.1145/3543507.3583335

Published: 30 April 2023 Publication History

Abstract

Graph convolutional networks (GCNs) are currently the most promising paradigm for dealing with graph-structure data, while recent studies have also shown that GCNs are vulnerable to adversarial attacks. Thus developing GCN models that are robust to such attacks become a hot research topic. However, the structural purification learning-based or robustness constraints-based defense GCN methods are usually designed for specific data or attacks, and introduce additional objective that is not for classification. Extra training overhead is also required in their design. To address these challenges, we conduct in-depth explorations on mid-frequency signals on graphs and propose a simple yet effective Mid-pass filter GCN (Mid-GCN). Theoretical analyses guarantee the robustness of signals through the mid-pass filter, and we also shed light on the properties of different frequency signals under adversarial attacks. Extensive experiments on six benchmark graph data further verify the effectiveness of our designed Mid-GCN in node classification accuracy compared to state-of-the-art GCNs under various adversarial attack strategies.

References

[1]

Deyu Bo, Xiao Wang, Chuan Shi, and Huawei Shen. 2021. Beyond Low-frequency Information in Graph Convolutional Networks. In Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI2021. AAAI Press, 3950–3957.

[2]

Aleksandar Bojchevski and Stephan Günnemann. 2017. Deep gaussian embedding of graphs: Unsupervised inductive learning via ranking. arXiv preprint arXiv:1707.03815 (2017).

[3]

Joan Bruna, Wojciech Zaremba, Arthur Szlam, and Yann LeCun. 2013. Spectral networks and locally connected networks on graphs. arXiv preprint arXiv:1312.6203 (2013).

[4]

Heng Chang, Yu Rong, Tingyang Xu, Yatao Bian, Shiji Zhou, Xin Wang, Junzhou Huang, and Wenwu Zhu. 2021. Not all low-pass filters are robust in graph convolutional networks. Advances in Neural Information Processing Systems 34 (2021), 25058–25071.

[5]

Zhixian Chen, Tengfei Ma, and Yang Wang. 2022. When Does A Spectral Graph Neural Network Fail in Node Classification¿arXiv preprint arXiv:2202.07902 (2022).

[6]

Eli Chien, Jianhao Peng, Pan Li, and Olgica Milenkovic. 2021. Adaptive Universal Generalized PageRank Graph Neural Network. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021.

[7]

Fan RK Chung and Fan Chung Graham. 1997. Spectral graph theory. Vol. 92. American Mathematical Soc.

[8]

Connor W Coley, Wengong Jin, Luke Rogers, Timothy F Jamison, Tommi S Jaakkola, William H Green, Regina Barzilay, and Klavs F Jensen. 2019. A graph-convolutional neural network model for the prediction of chemical reactivity. Chemical science 10, 2 (2019), 370–377.

[9]

Hanjun Dai, Hui Li, Tian Tian, Xin Huang, Lin Wang, Jun Zhu, and Le Song. 2018. Adversarial attack on graph structured data. In International conference on machine learning. PMLR, 1115–1124.

[10]

Michaël Defferrard, Xavier Bresson, and Pierre Vandergheynst. 2016. Convolutional neural networks on graphs with fast localized spectral filtering. Advances in neural information processing systems 29 (2016), 3844–3852.

[11]

Negin Entezari, Saba A Al-Sayouri, Amirali Darvishzadeh, and Evangelos E Papalexakis. 2020. All you need is low (rank) defending against adversarial attacks on graphs. In Proceedings of the 13th International Conference on Web Search and Data Mining. 169–177.

Digital Library

[12]

Fred X Han, Di Niu, Kunfeng Lai, Weidong Guo, Yancheng He, and Yu Xu. 2019. Inferring search queries from web documents via a graph-augmented sequence to attention network. In The World Wide Web Conference. 2792–2798.

Digital Library

[13]

Mingguo He, Zhewei Wei, Hongteng Xu, 2021. Bernnet: Learning arbitrary graph spectral filters via bernstein approximation. Advances in Neural Information Processing Systems 34 (2021), 14239–14251.

[14]

Jincheng Huang, Ping Li, Rui Huang, and Chen Na. 2022. Learning heterophilious edge to drop: A general framework for boosting graph neural networks. arXiv preprint arXiv:2205.11322 (2022).

[15]

Wei Jin, Yao Ma, Xiaorui Liu, Xianfeng Tang, Suhang Wang, and Jiliang Tang. 2020. Graph structure learning for robust graph neural networks. In Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining. 66–74.

Digital Library

[16]

Steven Kearnes, Kevin McCloskey, Marc Berndl, Vijay Pande, and Patrick Riley. 2016. Molecular graph convolutions: moving beyond fingerprints. Journal of computer-aided molecular design 30, 8 (2016), 595–608.

[17]

Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings.

[18]

Johannes Klicpera, Aleksandar Bojchevski, and Stephan Günnemann. 2018. Predict then propagate: Graph neural networks meet personalized pagerank. arXiv preprint arXiv:1810.05997 (2018).

[19]

Yehuda Koren. 2003. On spectral graph drawing. In International Computing and Combinatorics Conference. 496–508.

[20]

Runlin Lei, Zhen Wang, Yaliang Li, Bolin Ding, and Zhewei Wei. 2022. EvenNet: Ignoring Odd-Hop Neighbors Improves Robustness of Graph Neural Networks. arXiv preprint arXiv:2205.13892 (2022).

[21]

Yaxin Li, Wei Jin, Han Xu, and Jiliang Tang. 2020. Deeprobust: A pytorch library for adversarial attacks and defenses. arXiv preprint arXiv:2005.06149 (2020).

[22]

Xuanqing Liu, Si Si, Xiaojin Zhu, Yang Li, and Cho-Jui Hsieh. 2019. A unified framework for data poisoning attack to graph-based semi-supervised learning. arXiv preprint arXiv:1910.14147 (2019).

[23]

Yao Ma, Xiaorui Liu, Tong Zhao, Yozen Liu, Jiliang Tang, and Neil Shah. 2021. A unified view on graph neural networks as graph signal denoising. In Proceedings of the 30th ACM International Conference on Information & Knowledge Management. 1202–1211.

Digital Library

[24]

Yao Ma, Suhang Wang, Tyler Derr, Lingfei Wu, and Jiliang Tang. 2019. Attacking graph convolutional networks via rewiring. arXiv preprint arXiv:1906.03750 (2019).

[25]

Yimeng Min, Frederik Wenkel, and Guy Wolf. 2020. Scattering gcn: Overcoming oversmoothness in graph convolutional networks. Advances in Neural Information Processing Systems 33 (2020), 14498–14508.

[26]

CHEN Na, HUANG Jincheng, and LI Ping. 2022. Graph Neural Network Defense Combined with Contrastive Learning. Journal of Frontiers of Computer Science & Technology (2022).

[27]

Hoang Nt and Takanori Maehara. 2019. Revisiting graph neural networks: All we have is low-pass filters. arXiv preprint arXiv:1905.09550 (2019).

[28]

Hongbin Pei, Bingzhe Wei, Kevin Chen-Chuan Chang, Yu Lei, and Bo Yang. 2020. Geom-GCN: Geometric Graph Convolutional Networks. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net. https://openreview.net/forum¿id=S1e2agrFvS

[29]

Benedek Rozemberczki, Carl Allen, and Rik Sarkar. 2021. Multi-scale attributed node embedding. Journal of Complex Networks 9, 2 (2021), cnab014.

[30]

David I Shuman, Sunil K. Narang, Pascal Frossard, Antonio Ortega, and Pierre Vandergheynst. 2013. The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains. IEEE Signal Processing Magazine 30, 3 (2013), 83–98. https://doi.org/10.1109/MSP.2012.2235192

[31]

Jie Tang, Jimeng Sun, Chi Wang, and Zi Yang. 2009. Social influence analysis in large-scale networks. In Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining. 807–816.

Digital Library

[32]

Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. 2018. Graph Attention Networks. In 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings. OpenReview.net.

[33]

Xiyuan Wang and Muhan Zhang. 2022. How Powerful are Spectral Graph Neural Networks. arXiv preprint arXiv:2205.11172 (2022).

[34]

Felix Wu, Amauri Souza, Tianyi Zhang, Christopher Fifty, Tao Yu, and Kilian Weinberger. 2019. Simplifying graph convolutional networks. In International conference on machine learning. PMLR, 6861–6871.

[35]

Huijun Wu, Chen Wang, Yuriy Tyshetskiy, Andrew Docherty, Kai Lu, and Liming Zhu. 2019. Adversarial examples on graph data: Deep insights into attack and defense. arXiv preprint arXiv:1903.01610 (2019).

[36]

Li Zhang and Haiping Lu. 2020. A feature-importance-aware and robust aggregator for GCN. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management. 1813–1822.

Digital Library

[37]

Wentao Zhang, Yu Shen, Zheyu Lin, Yang Li, Xiaosen Li, Wen Ouyang, Yangyu Tao, Zhi Yang, and Bin Cui. 2022. Pasca: A graph neural architecture search system under the scalable paradigm. In Proceedings of the ACM Web Conference 2022. 1817–1828.

Digital Library

[38]

Xiang Zhang and Marinka Zitnik. 2020. Gnnguard: Defending graph neural networks against adversarial attacks. Advances in neural information processing systems 33 (2020), 9263–9275.

[39]

Jialin Zhao, Yuxiao Dong, Ming Ding, Evgeny Kharlamov, and Jie Tang. 2021. Adaptive Diffusion in Graph Neural Networks. Advances in Neural Information Processing Systems 34 (2021), 23321–23333.

[40]

Ling Zhao, Yujiao Song, Chao Zhang, Yu Liu, Pu Wang, Tao Lin, Min Deng, and Haifeng Li. 2019. T-gcn: A temporal graph convolutional network for traffic prediction. IEEE Transactions on Intelligent Transportation Systems 21, 9 (2019), 3848–3858.

[41]

Chuanpan Zheng, Xiaoliang Fan, Cheng Wang, and Jianzhong Qi. 2020. Gman: A graph multi-attention network for traffic prediction. In Proceedings of the AAAI conference on artificial intelligence, Vol. 34. 1234–1241.

[42]

Qinkai Zheng, Xu Zou, Yuxiao Dong, Yukuo Cen, Da Yin, Jiarong Xu, Yang Yang, and Jie Tang. 2021. Graph robustness benchmark: Benchmarking the adversarial robustness of graph machine learning. arXiv preprint arXiv:2111.04314 (2021).

[43]

Dingyuan Zhu, Ziwei Zhang, Peng Cui, and Wenwu Zhu. 2019. Robust graph convolutional networks against adversarial attacks. In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining. 1399–1407.

Digital Library

[44]

Jiong Zhu, Junchen Jin, Donald Loveland, Michael T Schaub, and Danai Koutra. 2022. How does Heterophily Impact the Robustness of Graph Neural Networks¿ Theoretical Connections and Practical Implications. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 2637–2647.

Digital Library

[45]

Daniel Zügner, Amir Akbarnejad, and Stephan Günnemann. 2018. Adversarial attacks on neural networks for graph data. In Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining. 2847–2856.

Digital Library

[46]

Daniel Zügner and Stephan Günnemann. 2019. Adversarial Attacks on Graph Neural Networks via Meta Learning. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019.

[47]

Daniel Zügner and Stephan Günnemann. 2019. Certifiable robustness and robust training for graph convolutional networks. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 246–256.

Digital Library

Cited By

Zhang AHuang JLi PZhang K(2024)Building Shortcuts between Distant Nodes with Biaffine Mapping for Graph Convolutional NetworksACM Transactions on Knowledge Discovery from Data10.1145/365011318:6(1-21)Online publication date: 12-Apr-2024
https://dl.acm.org/doi/10.1145/3650113
Zhang JWang YYang XZhu E(2024)A Fully Test-time Training Framework for Semi-supervised Node Classification on Out-of-Distribution GraphsACM Transactions on Knowledge Discovery from Data10.1145/364950718:7(1-19)Online publication date: 19-Jun-2024
https://dl.acm.org/doi/10.1145/3649507
Yang XWang YLiu YWen YMeng LZhou SLiu XZhu E(2024)Mixed Graph Contrastive Network for Semi-supervised Node ClassificationACM Transactions on Knowledge Discovery from Data10.1145/364154918:7(1-19)Online publication date: 19-Jun-2024
https://dl.acm.org/doi/10.1145/3641549
Show More Cited By

Index Terms

Robust Mid-Pass Filtering Graph Convolutional Networks
1. Computing methodologies
  1. Artificial intelligence
2. Mathematics of computing
  1. Discrete mathematics
    1. Graph theory
      1. Spectra of graphs

Recommendations

Graph Structure Learning for Robust Graph Neural Networks
KDD '20: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining

Graph Neural Networks (GNNs) are powerful tools in representation learning for graphs. However, recent studies show that GNNs are vulnerable to carefully-crafted perturbations, called adversarial attacks. Adversarial attacks can easily fool GNNs in ...
Robust Graph Convolutional Networks Against Adversarial Attacks
KDD '19: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining

Graph Convolutional Networks (GCNs) are an emerging type of neural network model on graphs which have achieved state-of-the-art performance in the task of node classification. However, recent studies show that GCNs are vulnerable to adversarial attacks, ...
Enhancing Robustness of Graph Convolutional Networks via Dropping Graph Connections
Machine Learning and Knowledge Discovery in Databases
Abstract
Graph convolutional networks (GCNs) have emerged as one of the most popular neural networks for a variety of tasks over graphs. Despite their remarkable learning and inference ability, GCNs are still vulnerable to adversarial attacks that ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Conferences

WWW '23: Proceedings of the ACM Web Conference 2023

April 2023

4293 pages

ISBN:9781450394161

DOI:10.1145/3543507

Copyright © 2023 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Sponsors

SIGWEB: ACM Special Interest Group on Hypertext, Hypermedia, and Web

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 30 April 2023

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

WWW '23

Sponsor:

SIGWEB

WWW '23: The ACM Web Conference 2023

April 30 - May 4, 2023

TX, Austin, USA

Acceptance Rates

Overall Acceptance Rate 1,899 of 8,196 submissions, 23%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

10
Total Citations
View Citations
289
Total Downloads

Downloads (Last 12 months)168
Downloads (Last 6 weeks)6

Reflects downloads up to 22 Sep 2024

Other Metrics

View Author Metrics

Citations

Cited By

Zhang AHuang JLi PZhang K(2024)Building Shortcuts between Distant Nodes with Biaffine Mapping for Graph Convolutional NetworksACM Transactions on Knowledge Discovery from Data10.1145/365011318:6(1-21)Online publication date: 12-Apr-2024
https://dl.acm.org/doi/10.1145/3650113
Zhang JWang YYang XZhu E(2024)A Fully Test-time Training Framework for Semi-supervised Node Classification on Out-of-Distribution GraphsACM Transactions on Knowledge Discovery from Data10.1145/364950718:7(1-19)Online publication date: 19-Jun-2024
https://dl.acm.org/doi/10.1145/3649507
Yang XWang YLiu YWen YMeng LZhou SLiu XZhu E(2024)Mixed Graph Contrastive Network for Semi-supervised Node ClassificationACM Transactions on Knowledge Discovery from Data10.1145/364154918:7(1-19)Online publication date: 19-Jun-2024
https://dl.acm.org/doi/10.1145/3641549
Zhong LLin RLi JWang SChen ZBaeza-Yates RBonchi F(2024)Bridging and Compressing Feature and Semantic Spaces for Robust Graph Neural Networks: An Information Theory PerspectiveProceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining10.1145/3637528.3671870(4571-4582)Online publication date: 25-Aug-2024
https://dl.acm.org/doi/10.1145/3637528.3671870
Yuan LJiang PHou WHuang W(2024)G-MLP: Graph Multi-Layer Perceptron for Node Classification Using Contrastive LearningIEEE Access10.1109/ACCESS.2024.343258312(104909-104919)Online publication date: 2024
https://doi.org/10.1109/ACCESS.2024.3432583
Zhu YHuang JChen YAmor RWitbrock M(2024)A graph transformer defence against graph perturbation by a flexible-pass filterInformation Fusion10.1016/j.inffus.2024.102296107:COnline publication date: 2-Jul-2024
https://dl.acm.org/doi/10.1016/j.inffus.2024.102296
Shu KMa HYang JZhang D(2024)GraphSmin: Imbalanced dissolved gas analysis with contrastive dual-channel graph filtersAdvanced Engineering Informatics10.1016/j.aei.2024.10283962(102839)Online publication date: Oct-2024
https://doi.org/10.1016/j.aei.2024.102839
Wang HChen JDu LFu QHan SSong XElkind E(2023)Causal-based supervision of attention in graph neural networkProceedings of the Thirty-Second International Joint Conference on Artificial Intelligence10.24963/ijcai.2023/257(2315-2323)Online publication date: 19-Aug-2023
https://dl.acm.org/doi/10.24963/ijcai.2023/257
Li Z(2023)Analysis and Applications of 2D Discrete Fourier Transform in Image Denoising and Edge Detection2023 4th International Conference on Computer Engineering and Intelligent Control (ICCEIC)10.1109/ICCEIC60201.2023.10426668(120-129)Online publication date: 20-Oct-2023
https://doi.org/10.1109/ICCEIC60201.2023.10426668
Yao LGuo DWang XZhu LFeng JZhang Y(2023)A double-layer attentive graph convolution networks based on transfer learning for dynamic graph classificationInternational Journal of Machine Learning and Cybernetics10.1007/s13042-023-01944-015:3(863-877)Online publication date: 18-Aug-2023
https://doi.org/10.1007/s13042-023-01944-0

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

HTML Format

View this article in HTML Format.

Media

Figures

Other

Tables

View Table of Contents