{"type":"ScholarlyArticle","title":"RoboGNN: Robustifying Node Classification under Link Perturbation","authors":[{"name":"Sheng Guan","slug":"sheng-guan","given":"Sheng","family":"Guan","affiliation":"Case Western Reserve University"},{"name":"Hanchao Ma","slug":"hanchao-ma","given":"Hanchao","family":"Ma","affiliation":"Case Western Reserve University"},{"name":"Yinghui Wu","slug":"yinghui-wu","given":"Yinghui","family":"Wu","affiliation":"Case Western Reserve University"}],"abstract":"Graph neural networks (GNNs) have emerged as powerful approaches for graph representation learning and node classification. Nevertheless, they can be vulnerable (sensitive) to link perturbations due to structural noise or adversarial attacks. This paper introduces RoboGNN, a novel framework that simultaneously robustifies an input classifier to a counterpart with certifiable robustness, and suggests desired graph representation with auxiliary links to ensure the robustness guarantee. (1) We introduce (p,θ)-robustness, which characterizes the robustness guarantee of a GNN-based classifier if its performance is insensitive for at least θ fraction of a targeted set of nodes under any perturbation of a set of vulnerable links up to a bounded size p. (2) We present a co-learning framework that interacts model learning with graph structural learning to robustify an input model M to a (p,θ)-robustness counterpart. The framework also outputs the desired graph structures that ensure the robustness. Using real-world benchmark graphs, we experimentally verify that roboGNN can effectively robustify representative GNNs with guaranteed robustness, and desirable gains on accuracy.","doi":"10.24963/ijcai.2022/420","url":"https://ijcai.org/proceedings/2022/420","pdf":"https://ijcai.org/proceedings/2022/0420.pdf","markdown":"https://ijcai.org/proceedings/2022/420.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/420","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Machine Learning","track":"Main Track","number":420,"pages":{"first":3029,"last":3035},"keywords":["Machine Learning: Adversarial Machine Learning","Data Mining: Mining Graphs","Machine Learning: Classification"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986786","length_sec":108,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984929","length_sec":356,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Bojchevski and Günnemann, 2019] Aleksandar Bojchevski and Stephan Günnemann. Certifiable robustness to graph perturbations. In NeurIPS, 2019.","title":"Certifiable robustness to graph perturbations","authors":"Aleksandar Bojchevski, Stephan Günnemann","year":"2019","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bojchevski et al., 2020] Aleksandar Bojchevski, Johannes Klicpera, Bryan Perozzi, Amol Kapoor, Martin Blais, Benedek Rózemberczki, Michal Lukasik, and Stephan Günnemann. Scaling graph neural networks with approx- imate pagerank. In KDD, 2020.","title":"Scaling graph neural networks with approximate pagerank","authors":"Aleksandar Bojchevski, Johannes Klicpera, Bryan Perozzi, Amol Kapoor, Martin Blais, Benedek Rózemberczki, Michal Lukasik, Stephan Günnemann","year":"2020","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Cai and Wang, 2020] Chen Cai and Yusu Wang. A note on over-smoothing for graph neural networks. arXiv preprint arXiv:2006.13318, 2020.","title":"A note on over-smoothing for graph neural networks","authors":"Chen Cai, Yusu Wang","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Dai et al., 2018] Hanjun Dai, Hui Li, Tian Tian, Xin Huang, Lin Wang, Jun Zhu, and Le Song. Adversarial attack on graph structured data. arXiv preprint arXiv:1806.02371, 2018.","title":"Adversarial attack on graph structured data","authors":"Hanjun Dai, Hui Li, Tian Tian, Xin Huang, Lin Wang, Jun Zhu, Le Song","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Entezari et al., 2020] Negin Entezari, Saba A Al-Sayouri, Amirali Darvishzadeh, and Evangelos E Papalexakis. All you need is low (rank) defending against adversarial at- tacks on graphs. In WSDM, 2020.","title":"All you need is low (rank) defending against adversarial attacks on graphs","authors":"Negin Entezari, Saba A Al-Sayouri, Amirali Darvishzadeh, Evangelos E Papalexakis","year":"2020","venue":"WSDM","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Giles et al., 1998] C. Lee Giles, Kurt D. Bollacker, and Steve Lawrence. Citeseer: An automatic citation index- ing system. In Proceedings of the Third ACM Conference on Digital Libraries, 1998.","title":"Citeseer: An automatic citation indexing system","authors":"C Lee Giles, Kurt D Bollacker, Steve Lawrence","year":"1998","venue":"Proceedings of the Third ACM Conference on Digital Libraries","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Gori et al., 2005] Marco Gori, Gabriele Monfardini, and Franco Scarselli. A new model for learning in graph do- mains. In Proceedings. 2005 IEEE international joint con- ference on neural networks, volume 2, pages 729-734, 2005.","title":"A new model for learning in graph domains","authors":"Marco Gori, Gabriele Monfardini, Franco Scarselli","year":"2005","venue":"Proceedings. 2005 IEEE international joint conference on neural networks","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Guan et al., 2022] Sheng Guan, Hanchao Ma, and Yinghui Wu. Robognn: Robustifying node classification un- der link perturbation, full version. https://github.com/ CWRU-DB-Group/robognn/blob/main/full.pdf, 2022. Accessed: 2022-06-08.","title":"Robognn: Robustifying node classification under link perturbation, full version","authors":"Sheng Guan, Hanchao Ma, Yinghui Wu","year":"2022","venue":null,"doi":null,"url":"https://github.com/CWRU-DB-Group/robognn/blob/main/full.pdf","internal_url":null},{"position":9,"raw":"[Hamilton et al., 2017] Will Hamilton, Zhitao Ying, and Jure Leskovec. Inductive representation learning on large graphs. In Advances in Neural Information Processing Systems, 2017.","title":"Inductive representation learning on large graphs","authors":"Hamilton","year":"2017","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Harris and Harris, 2010] David Harris and Sarah Harris. Digital design and computer architecture. Morgan Kauf- mann, 2010.","title":"Digital design and computer architecture","authors":"David Harris, Sarah Harris","year":"2010","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Ioannidis and Giannakis, 2019] Vassilis N Ioannidis and Georgios B Giannakis. Edge dithering for robust adaptive graph convolutional networks. arXiv preprint arXiv:1910.09590, 2019.","title":"Edge dithering for robust adaptive graph convolutional networks","authors":"N Vassilis, Georgios B Ioannidis, Giannakis","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Jin et al., 2020] Wei Jin, Yao Ma, Xiaorui Liu, Xianfeng Tang, Suhang Wang, and Jiliang Tang. Graph structure learning for robust graph neural networks. KDD, 2020.","title":"Graph structure learning for robust graph neural networks","authors":"Wei Jin, Yao Ma, Xiaorui Liu, Xianfeng Tang, Suhang Wang, Jiliang Tang","year":"2020","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Kipf and Welling, 2016] Thomas N Kipf and Max Welling. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907, 2016.","title":"Semi-supervised classification with graph convolutional networks","authors":"N Thomas, Max Kipf, Welling","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Ma et al., 2021] Yao Ma, Xiaorui Liu, Tong Zhao, Yozen Liu, Jiliang Tang, and Neil Shah. A unified view on graph neural networks as graph signal denoising. In CIKM, 2021.","title":"A unified view on graph neural networks as graph signal denoising","authors":"Yao Ma, Xiaorui Liu, Tong Zhao, Yozen Liu, Jiliang Tang, Neil Shah","year":"2021","venue":"CIKM","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[McCallum et al., 2000] Andrew Kachites McCallum, Ka- mal Nigam, Jason Rennie, and Kristie Seymore. Automat- ing the construction of internet portals with machine learn- ing. Information Retrieval, 2000.","title":"Automating the construction of internet portals with machine learning","authors":"Andrew Kachites Mccallum, Kamal Nigam, Jason Rennie, Kristie Seymore","year":"2000","venue":"Information Retrieval","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Olsen et al., 2012] Martin Olsen, Anastasios Viglas, and Ilia Zvedeniouk. An approximation algorithm for the link building problem. arXiv preprint arXiv:1204.1369, 2012.","title":"An approximation algorithm for the link building problem","authors":"Martin Olsen, Anastasios Viglas, Ilia Zvedeniouk","year":"2012","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Paulheim, 2017] Heiko Paulheim. Knowledge graph refine- ment: A survey of approaches and evaluation methods. Se- mantic web, 2017.","title":"Knowledge graph refinement: A survey of approaches and evaluation methods","authors":"Heiko Paulheim","year":"2017","venue":"Semantic web","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Sen et al., 2008] Prithviraj Sen, Galileo Namata, Mustafa Bilgic, Lise Getoor, Brian Galligher, and Tina Eliassi-Rad. Collective classification in network data. AI magazine, 2008.","title":"Collective classification in network data","authors":"Prithviraj Sen, Galileo Namata, Mustafa Bilgic, Lise Getoor, Brian Galligher, Tina Eliassi-Rad","year":"2008","venue":"AI magazine","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Tran et al., 2017] Cong Tran, Won-Yong Shin, and Andreas Spitz. Community detection in partially observable social networks. arXiv preprint arXiv:1801.00132, 2017.","title":"Community detection in partially observable social networks","authors":"Cong Tran, Won-Yong Shin, Andreas Spitz","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Veličković et al., 2017] Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. Graph attention networks. arXiv preprint arXiv:1710.10903, 2017.","title":"Graph attention networks","authors":"Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, Yoshua Bengio","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Wu et al., 2019] Huijun Wu, Chen Wang, Yuriy Tyshetskiy, Andrew Docherty, Kai Lu, and Liming Zhu. Adversarial examples on graph data: Deep insights into attack and de- fense. IJCAI, 2019.","title":"Adversarial examples on graph data: Deep insights into attack and defense","authors":"Huijun Wu, Chen Wang, Yuriy Tyshetskiy, Andrew Docherty, Kai Lu, Liming Zhu","year":"2019","venue":"IJCAI","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Wu et al., 2020] Zonghan Wu, Shirui Pan, Fengwen Chen, Guodong Long, Chengqi Zhang, and S Yu Philip. A com- prehensive survey on graph neural networks. NeurIPS, 2020.","title":"A comprehensive survey on graph neural networks","authors":"Wu","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Xu et al., 2021] Zhe Xu, Boxin Du, and Hanghang Tong. Graph sanitation with application to node classification. arXiv preprint arXiv:2105.09384, 2021.","title":"Graph sanitation with application to node classification","authors":"Zhe Xu, Boxin Du, Hanghang Tong","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Yuan et al., 2017] Xiaoyong Yuan, Pan He, Qile Zhu, Ra- jendra Rana Bhat, and Xiaolin Li. Adversarial ex- amples: Attacks and defenses for deep learning. corr abs/1712.07107 (2017). arXiv preprint arXiv:1712.07107, 2017.","title":"Adversarial examples: Attacks and defenses for deep learning","authors":"Xiaoyong Yuan, Pan He, Qile Zhu, Rajendra, Rana Bhat, Xiaolin Li","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Zügner and Günnemann, 2019] Daniel Zügner and Stephan Günnemann. Adversarial attacks on graph neural networks via meta learning. ICLR, 2019.","title":"Adversarial attacks on graph neural networks via meta learning","authors":"Daniel Zügner, Stephan Günnemann","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Zügner et al., 2018] Daniel Zügner, Amir Akbarnejad, and Stephan Günnemann. Adversarial attacks on neural net- works for graph data. In KDD, 2018.","title":"Adversarial attacks on neural networks for graph data","authors":"Daniel Zügner, Amir Akbarnejad, Stephan Günnemann","year":"2018","venue":"KDD","doi":null,"url":null,"internal_url":"/proceedings/2019/872"}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}