{"type":"ScholarlyArticle","title":"CGMN: A Contrastive Graph Matching Network for Self-Supervised Graph Similarity Learning","authors":[{"name":"Di Jin","slug":"di-jin","given":"Di","family":"Jin","affiliation":"College of Intelligence and Computing , Tianjin University , Tianjin , China"},{"name":"Luzhi Wang","slug":"luzhi-wang","given":"Luzhi","family":"Wang","affiliation":"College of Intelligence and Computing , Tianjin University , Tianjin , China"},{"name":"Yizhen Zheng","slug":"yizhen-zheng","given":"Yizhen","family":"Zheng","affiliation":"Department of Data Science and AI , Faculty of IT , Monash University , Australia"},{"name":"Xiang Li","slug":"xiang-li","given":"Xiang","family":"Li","affiliation":"Meituan , Beijing , China"},{"name":"Fei Jiang","slug":"fei-jiang","given":"Fei","family":"Jiang","affiliation":"Meituan , Beijing , China"},{"name":"Wei Lin","slug":"wei-lin","given":"Wei","family":"Lin","affiliation":"Meituan , Beijing , China"},{"name":"Shirui Pan","slug":"shirui-pan","given":"Shirui","family":"Pan","affiliation":"Department of Data Science and AI , Faculty of IT , Monash University , Australia"}],"abstract":"Graph similarity learning refers to calculating the similarity score between two graphs, which is required in many realistic applications, such as visual tracking, graph classification, and collaborative filtering. As most of the existing graph neural networks yield effective graph representations of a single graph, little effort has been made for jointly learning two graph representations and calculating their similarity score. In addition, existing unsupervised graph similarity learning methods are mainly clustering-based, which ignores the valuable information embodied in graph pairs. To this end, we propose a contrastive graph matching network (CGMN) for self-supervised graph similarity learning in order to calculate the similarity between any two input graph objects. Specifically, we generate two augmented views for each graph in a pair respectively. Then, we employ two strategies, namely cross-view interaction and cross-graph interaction, for effective node representation learning. The former is resorted to strengthen the consistency of node representations in two views. The latter is utilized to identify node differences between different graphs. Finally, we transform node representations into graph-level representations via pooling operations for graph similarity computation. We have evaluated CGMN on eight real-world datasets, and the experiment results show that the proposed new approach is superior to the state-of-the-art methods in graph similarity learning downstream tasks.","doi":"10.24963/ijcai.2022/292","url":"https://ijcai.org/proceedings/2022/292","pdf":"https://ijcai.org/proceedings/2022/0292.pdf","markdown":"https://ijcai.org/proceedings/2022/292.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/292","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":"Data Mining","track":"Main Track","number":292,"pages":{"first":2101,"last":2107},"keywords":["Machine Learning: Self-supervised Learning","Data Mining: Mining Graphs"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38987025","length_sec":82,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38985168","length_sec":624,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Bai et al., 2019] Yunsheng Bai, Hao Ding, Song Bian, Ting Chen, Yizhou Sun, and Wei Wang. Simgnn: A neural net- work approach to fast graph similarity computation. In ICDM, pages 384-392, 2019.","title":"Simgnn: A neural network approach to fast graph similarity computation","authors":"Yunsheng Bai, Hao Ding, Song Bian, Ting Chen, Yizhou Sun, Wei Wang","year":"2019","venue":"ICDM","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bai et al., 2021] Yunsheng Bai, Derek Xu, Yizhou Sun, and Wei Wang. Glsearch: Maximum common subgraph detec- tion via learning to search. In ICML, 2021.","title":"Glsearch: Maximum common subgraph detection via learning to search","authors":"Yunsheng Bai, Derek Xu, Yizhou Sun, Wei Wang","year":"2021","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bunke, 1997] Horst Bunke. On a relation between graph edit distance and maximum common subgraph. Pattern Recognition Letters, 18(8):689-694, 1997.","title":"On a relation between graph edit distance and maximum common subgraph","authors":"Horst Bunke","year":"1997","venue":"Pattern Recognition Letters","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chen et al., 2020] Ting Chen, Simon Kornblith, Moham- mad Norouzi, and Geoffrey Hinton. A simple framework for contrastive learning of visual representations. In ICML, pages 1597-1607. PMLR, 2020.","title":"A simple framework for contrastive learning of visual representations","authors":"Ting Chen, Simon Kornblith, Mohammad Norouzi, Geoffrey Hinton","year":"2020","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Hassani and Khasahmadi, 2020] Kaveh Hassani and Amir Hosein Khasahmadi. Contrastive multi-view repre- sentation learning on graphs. In ICML, pages 4116-4126.","title":"Contrastive multi-view representation learning on graphs","authors":"Kaveh Hassani, Amir Hosein, Khasahmadi","year":null,"venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"PMLR, 2020.","title":null,"authors":"Pmlr","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[He et al., 2020] Kaiming He, Haoqi Fan, Yuxin Wu, Sain- ing Xie, and Ross Girshick. Momentum contrast for un- supervised visual representation learning. In CVPR, pages 9729-9738, 2020.","title":"Momentum contrast for unsupervised visual representation learning","authors":"Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, Ross Girshick","year":"2020","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hjelm et al., 2019] R. Devon Hjelm, Alex Fedorov, Samuel Lavoie-Marchildon, Karan Grewal, Philip Bachman, Adam Trischler, and Yoshua Bengio. Learning deep rep- resentations by mutual information estimation and maxi- mization. In ICLR, 2019.","title":"Learning deep representations by mutual information estimation and maximization","authors":"R, Devon Hjelm, Alex Fedorov, Samuel Lavoie-Marchildon, Karan Grewal, Philip Bachman, Adam Trischler, Yoshua Bengio","year":"2019","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Jia et al., 2021] Renqi Jia, Xiaofei Zhou, Linhua Dong, and Shirui Pan. Hypergraph convolutional network for group recommendation. In ICDM, pages 260-269. IEEE, 2021.","title":"Hypergraph convolutional network for group recommendation","authors":"Jia","year":"2021","venue":"ICDM","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Jin et al., 2021a] Di Jin, Cuiying Huo, Chundong Liang, and Liang Yang. Heterogeneous graph neural network via attribute completion. In WWW, pages 391-400, 2021.","title":"Heterogeneous graph neural network via attribute completion","authors":"Jin","year":"2021","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Jin et al., 2021b] Di Jin, Zhizhi Yu, Pengfei Jiao, Shirui Pan, Dongxiao He, Jia Wu, Philip Yu, and Weixiong Zhang. A survey of community detection approaches: From statistical modeling to deep learning. TKDE, DOI: 10.1109/TKDE.2021.3104155, 2021.","title":"A survey of community detection approaches: From statistical modeling to deep learning","authors":"Jin","year":"2021","venue":"TKDE","doi":"10.1109/tkde.2021.3104155","url":null,"internal_url":null},{"position":12,"raw":"[Jin et al., 2021c] Ming Jin, Yizhen Zheng, Yuan-Fang Li, Chen Gong, Chuan Zhou, and Shirui Pan. Multi-scale con- trastive siamese networks for self-supervised graph repre- sentation learning. In IJCAI, pages 1477-1483, 2021.","title":"Multi-scale contrastive siamese networks for self-supervised graph representation learning","authors":"Jin","year":"2021","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2021/204"},{"position":13,"raw":"[Kipf and Welling, 2017] Thomas N. Kipf and Max Welling. Semi-supervised classification with graph convolutional networks. In ICLR, 2017.","title":"Semi-supervised classification with graph convolutional networks","authors":"Thomas N Kipf, Max Welling","year":"2017","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Li et al., 2019] Yujia Li, Chenjie Gu, Thomas Dullien, Oriol Vinyals, and Pushmeet Kohli. Graph matching net- works for learning the similarity of graph structured ob- jects. In ICML, pages 3835-3845. PMLR, 2019.","title":"Graph matching networks for learning the similarity of graph structured objects","authors":"Yujia Li, Chenjie Gu, Thomas Dullien, Oriol Vinyals, Pushmeet Kohli","year":"2019","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Li et al., 2021] Junyi Li, Wei Jiang, Henry Han, Jing Liu, Bo Liu, and Yadong Wang. Scgslc: An unsupervised graph similarity learning framework for single-cell rna-seq data clustering. Computational Biology and Chemistry, 90:107415, 2021.","title":"Scgslc: An unsupervised graph similarity learning framework for single-cell rna-seq data clustering","authors":"Junyi Li, Wei Jiang, Henry Han, Jing Liu, Bo Liu, Yadong Wang","year":"2021","venue":"Computational Biology and Chemistry","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Ling et al., 2021] Xiang Ling, Lingfei Wu, Saizhuo Wang, Tengfei Ma, Fangli Xu, Alex X. Liu, Chunming Wu, and Shouling Ji. Multilevel graph matching networks for deep graph similarity learning. IEEE Transactions on Neural Networks and Learning Systems, pages 1-15, 2021.","title":"Multilevel graph matching networks for deep graph similarity learning","authors":"Xiang Ling, Lingfei Wu, Saizhuo Wang, Tengfei Ma, Fangli Xu, Alex X Liu, Chunming Wu, Shouling Ji","year":"2021","venue":"IEEE Transactions on Neural Networks and Learning Systems","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Neuhaus et al., 2006] Michel Neuhaus, Kaspar Riesen, and Horst Bunke. Fast suboptimal algorithms for the compu- tation of graph edit distance. In S+SSPR, pages 163-172. Springer, 2006.","title":"Fast suboptimal algorithms for the computation of graph edit distance","authors":"Michel Neuhaus, Kaspar Riesen, Horst Bunke","year":"2006","venue":"S+SSPR","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Riesen and Bunke, 2009] Kaspar Riesen and Horst Bunke. Approximate graph edit distance computation by means of bipartite graph matching. Image and Vision computing, 27(7):950-959, 2009.","title":"Approximate graph edit distance computation by means of bipartite graph matching","authors":"Bunke ; Riesen, Kaspar Riesen, Horst Bunke","year":"2009","venue":"Image and Vision computing","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Sanfeliu and Fu, 1983] Alberto Sanfeliu and King-Sun Fu. A distance measure between attributed relational graphs for pattern recognition. IEEE transactions on systems, man, and cybernetics, (3):353-362, 1983.","title":"A distance measure between attributed relational graphs for pattern recognition","authors":"Alberto Sanfeliu, King-Sun Fu","year":"1983","venue":"IEEE transactions on systems, man, and cybernetics","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Su et al., 2021] Yixin Su, Rui Zhang, Sarah M. Erfani, and Junhao Gan. Neural graph matching based collaborative filtering. In SIGIR, pages 849-858. ACM, 2021.","title":"Neural graph matching based collaborative filtering","authors":"Yixin Su, Rui Zhang, Sarah M Erfani, Junhao Gan","year":"2021","venue":"SIGIR","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Velickovic et al., 2019] Petar Velickovic, William Fedus, William L Hamilton, Pietro Liò, Yoshua Bengio, and R Devon Hjelm. Deep graph infomax. In ICLR, 2019.","title":"Deep graph infomax","authors":"Petar Velickovic, William Fedus, Pietro William L Hamilton, Yoshua Liò, Devon Bengio, Hjelm","year":"2019","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Wan et al., 2021] Sheng Wan, Shirui Pan, Ping Zhong, Xi- aojun Chang, Jian Yang, and Chen Gong. Dual interac- tive graph convolutional networks for hyperspectral image classification. IEEE Transactions on Geoscience and Re- mote Sensing, 60:1-14, 2021.","title":"Dual interactive graph convolutional networks for hyperspectral image classification","authors":"Sheng Wan, Shirui Pan, Ping Zhong, Xiaojun Chang, Jian Yang, Chen Gong","year":"2021","venue":"IEEE Transactions on Geoscience and Remote Sensing","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wang et al., 2020] Runzhong Wang, Junchi Yan, and Xi- aokang Yang. Graduated assignment for joint multi-graph matching and clustering with application to unsupervised graph matching network learning. In NeurIPS, 2020.","title":"Graduated assignment for joint multi-graph matching and clustering with application to unsupervised graph matching network learning","authors":"Wang","year":"2020","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Wang et al., 2021] Runzhong Wang, Tianqi Zhang, Tianshu Yu, Junchi Yan, and Xiaokang Yang. Combinatorial learn- ing of graph edit distance via dynamic embedding. In CVPR, pages 5241-5250, 2021.","title":"Combinatorial learning of graph edit distance via dynamic embedding","authors":"Wang","year":"2021","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Xu et al., 2017] Xiaojun Xu, Chang Liu, Qian Feng, Heng Yin, Le Song, and Dawn Song. Neural network-based graph embedding for cross-platform binary code similar- ity detection. In CCS, pages 363-376, 2017.","title":"Neural network-based graph embedding for cross-platform binary code similarity detection","authors":"Xiaojun Xu, Chang Liu, Qian Feng, Le Heng Yin, Dawn Song, Song","year":"2017","venue":"CCS","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Xu et al., 2019] Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. How powerful are graph neural net- works? In ICLR, 2019.","title":"How powerful are graph neural networks?","authors":"Xu","year":"2019","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Yu et al., 2021] Zhizhi Yu, Di Jin, Ziyang Liu, Dongxiao He, Xiao Wang, Hanghang Tong, and Jiawei Han. As-gcn: Adaptive semantic architecture of graph convolutional net- works for text-rich networks. In ICDM, 2021.","title":"As-gcn: Adaptive semantic architecture of graph convolutional networks for text-rich networks","authors":"Zhizhi Yu, Di Jin, Ziyang Liu, Dongxiao He, Xiao Wang, Hanghang Tong, Jiawei Han","year":"2021","venue":"ICDM","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Zhang et al., 2021] Zhen Zhang, Jiajun Bu, Martin Ester, Zhao Li, Chengwei Yao, Zhi Yu, and Can Wang. H2mn: Graph similarity learning with hierarchical hypergraph matching networks. In SIGKDD, pages 2274-2284, 2021.","title":"H2mn: Graph similarity learning with hierarchical hypergraph matching networks","authors":"Zhen Zhang, Jiajun Bu, Martin Ester, Zhao Li, Chengwei Yao, Zhi Yu, Can Wang","year":"2021","venue":"SIGKDD","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Zhu et al., 2020] Yanqiao Zhu, Yichen Xu, Feng Yu, Qiang Liu, Shu Wu, and Liang Wang. Deep graph contrastive representation learning. In ICML, 2020.","title":"Deep graph contrastive representation learning","authors":"Yanqiao Zhu, Yichen Xu, Feng Yu, Qiang Liu, Shu Wu, Liang Wang","year":"2020","venue":"ICML","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}