{"type":"ScholarlyArticle","title":"Bilinear Graph Neural Network with Neighbor Interactions","authors":[{"name":"Hongmin Zhu","slug":"hongmin-zhu","given":"Hongmin","family":"Zhu","affiliation":"University of Science and Technology of China"},{"name":"Fuli Feng","slug":"fuli-feng","given":"Fuli","family":"Feng","affiliation":"National University of Singapore"},{"name":"Xiangnan He","slug":"xiangnan-he","given":"Xiangnan","family":"He","affiliation":"University of Science and Technology of China"},{"name":"Xiang Wang","slug":"xiang-wang","given":"Xiang","family":"Wang","affiliation":"National University of Singapore"},{"name":"Yan Li","slug":"yan-li","given":"Yan","family":"Li","affiliation":"Beijing Kuaishou Technology Co., Ltd. Beijing , China"},{"name":"Kai Zheng","slug":"kai-zheng","given":"Kai","family":"Zheng","affiliation":"University of Electronic Science and Technology of China"},{"name":"Yongdong Zhang","slug":"yongdong-zhang","given":"Yongdong","family":"Zhang","affiliation":"University of Science and Technology of China"}],"abstract":"Graph Neural Network (GNN) is a powerful model to learn representations and make predictions on graph data. Existing efforts on GNN have largely defined the graph convolution as a weighted sum of the features of the connected nodes to form the representation of the target node. Nevertheless, the operation of weighted sum assumes the neighbor nodes are independent of each other, and ignores the possible interactions between them. When such interactions exist, such as the co-occurrence of two neighbor nodes is a strong signal of the target node's characteristics, existing GNN models may fail to capture the signal. In this work, we argue the importance of modeling the interactions between neighbor nodes in GNN. We propose a new graph convolution operator, which augments the weighted sum with pairwise interactions of the representations of neighbor nodes. We term this framework as Bilinear Graph Neural Network (BGNN), which improves GNN representation ability with bilinear interactions between neighbor nodes. In particular, we specify two BGNN models named BGCN and BGAT, based on the well-known GCN and GAT, respectively. Empirical results on three public benchmarks of semi-supervised node classification verify the effectiveness of BGNN --- BGCN (BGAT) outperforms GCN (GAT) by 1.6% (1.5%) in classification accuracy. Codes are available at: https://github.com/zhuhm1996/bgnn.","doi":"10.24963/ijcai.2020/202","url":"https://ijcai.org/proceedings/2020/202","pdf":"https://ijcai.org/proceedings/2020/0202.pdf","markdown":"https://ijcai.org/proceedings/2020/202.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/202","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Data Mining","track":"Main track","number":202,"pages":{"first":1452,"last":1458},"keywords":["Data Mining: Mining Graphs, Semi Structured Data, Complex Data","Data Mining: Classification, Semi-Supervised Learning"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/24011/file_24011.m3u8","length_sec":284,"provider":"hls"}],"references":[{"position":1,"raw":"[Atwood and Towsley, 2016] James Atwood and Don Towsley. Diffusion-convolutional neural networks. In NeurIPS, pages 1993-2001, 2016.","title":"Diffusion-convolutional neural networks","authors":"Towsley Atwood, James Atwood, Don Towsley","year":"2016","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Beutel et al., 2018] Alex Beutel, Paul Covington, Sagar Jain, Can Xu, Jia Li, Vince Gatto, and Ed H Chi. Latent cross: Making use of context in recurrent recommender systems. In WSDM, pages 46-54, 2018.","title":"Latent cross: Making use of context in recurrent recommender systems","authors":"Alex Beutel, Paul Covington, Sagar Jain, Can Xu, Jia Li, Vince Gatto, Ed H Chi","year":"2018","venue":"WSDM","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bronstein et al., 2017] Michael M Bronstein, Joan Bruna, Yann LeCun, Arthur Szlam, and Pierre Vandergheynst. Geometric deep learning: going beyond euclidean data. IEEE Signal Processing Mag, 34(4):18-42, 2017.","title":"Geometric deep learning: going beyond euclidean data","authors":"Joan Michael M Bronstein, Yann Bruna, Arthur Lecun, Pierre Szlam, Vandergheynst","year":"2017","venue":"IEEE Signal Processing Mag","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Bruna et al., 2014] Joan Bruna, Wojciech Zaremba, Arthur Szlam, and Yann LeCun. Spectral networks and locally connected networks on graphs. ICLR, 2014.","title":"Spectral networks and locally connected networks on graphs","authors":"Joan Bruna, Wojciech Zaremba, Arthur Szlam, Yann Lecun","year":"2014","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chami et al., 2019] Ines Chami, Zhitao Ying, Christopher Ré, and Jure Leskovec. Hyperbolic graph convolutional neural networks. In NeurIPS, pages 4869-4880, 2019.","title":"Hyperbolic graph convolutional neural networks","authors":"Ines Chami, Zhitao Ying, Christopher Ré, Jure Leskovec","year":"2019","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Chen et al., 2018] Jie Chen, Tengfei Ma, and Cao Xiao. Fastgcn: fast learning with graph convolutional networks via importance sampling. ICLR, 2018.","title":"Fastgcn: fast learning with graph convolutional networks via importance sampling","authors":"Jie Chen, Tengfei Ma, Cao Xiao","year":"2018","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Defferrard et al., 2016] Michaël Defferrard, Xavier Bres- son, and Pierre Vandergheynst. Convolutional neural net- works on graphs with fast localized spectral filtering. In NeurIPS, pages 3844-3852, 2016.","title":"Convolutional neural networks on graphs with fast localized spectral filtering","authors":"Michaël Defferrard, Xavier Bresson, Pierre Vandergheynst","year":"2016","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Feng et al., 2019] Fuli Feng, Xiangnan He, Xiang Wang, Cheng Luo, Yiqun Liu, and Tat-Seng Chua. Temporal re- lational ranking for stock prediction. ACM Transactions on Information Systems (TOIS), 37(2):1-30, 2019.","title":"Temporal relational ranking for stock prediction","authors":"Fuli Feng, Xiangnan He, Xiang Wang, Cheng Luo, Yiqun Liu, Tat-Seng Chua","year":"2019","venue":"ACM Transactions on Information Systems (TOIS)","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Feurer et al., 2015] Matthias Feurer, Aaron Klein, Katha- rina Eggensperger, Jost Springenberg, Manuel Blum, and Frank Hutter. Efficient and robust automated machine learning. In NeurIPS, pages 2962-2970, 2015.","title":"Efficient and robust automated machine learning","authors":"Matthias Feurer, Aaron Klein, Katharina Eggensperger, Jost Springenberg, Manuel Blum, Frank Hutter","year":"2015","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Hamilton et al., 2017] Will Hamilton, Zhitao Ying, and Jure Leskovec. Inductive representation learning on large graphs. In NeurIPS, pages 1024-1034, 2017.","title":"Inductive representation learning on large graphs","authors":"Hamilton","year":"2017","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[He and Chua, 2017] Xiangnan He and Tat-Seng Chua. Neu- ral factorization machines for sparse predictive analytics. In SIGIR, pages 355-364, 2017.","title":"Xiangnan He and Tat-Seng Chua. Neural factorization machines for sparse predictive analytics","authors":"Chua He","year":"2017","venue":"SIGIR","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[He et al., 2016] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recog- nition. In CVPR, pages 770-778, 2016.","title":"Deep residual learning for image recognition","authors":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[He et al., 2020] Xiangnan He, Kuan Deng, Xiang Wang, Yan Li, Yongdong Zhang, and Meng Wang. Lightgcn: Simplifying and powering graph convolution network for recommendation. In SIGIR, 2020.","title":"Lightgcn: Simplifying and powering graph convolution network for recommendation","authors":"He","year":"2020","venue":"SIGIR","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kampffmeyer et al., 2019] Michael Kampffmeyer, Yinbo Chen, Xiaodan Liang, Hao Wang, Yujia Zhang, and Eric P Xing. Rethinking knowledge graph propagation for zero- shot learning. In CVPR, pages 11487-11496, 2019.","title":"Rethinking knowledge graph propagation for zeroshot learning","authors":"Michael Kampffmeyer, Yinbo Chen, Xiaodan Liang, Hao Wang, Yujia Zhang, Eric P Xing","year":"2019","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Kipf and Welling, 2017] Thomas N Kipf and Max Welling. Semi-supervised classification with graph convolutional networks. ICLR, 2017.","title":"Semi-supervised classification with graph convolutional networks","authors":"N Thomas, Max Kipf, Welling","year":"2017","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Li et al., 2018] Qimai Li, Zhichao Han, and Xiao-Ming Wu. Deeper insights into graph convolutional networks for semi-supervised learning. In AAAI, 2018.","title":"Deeper insights into graph convolutional networks for semi-supervised learning","authors":"Li","year":"2018","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Liao et al., 2019] Renjie Liao, Zhizhen Zhao, Raquel Urta- sun, and Richard Zemel. Lanczosnet: Multi-scale deep graph convolutional networks. In ICLR, 2019.","title":"Lanczosnet: Multi-scale deep graph convolutional networks","authors":"Renjie Liao, Zhizhen Zhao, Raquel Urtasun, Richard Zemel","year":"2019","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Park and Neville, 2019] Hogun Park and Jennifer Neville. Exploiting interaction links for node classification with deep graph neural networks. In IJCAI, pages 3223-3230, 2019.","title":"Exploiting interaction links for node classification with deep graph neural networks","authors":"Neville ; Park, Hogun Park, Jennifer Neville","year":"2019","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2019/447"},{"position":19,"raw":"[Perozzi et al., 2014] Bryan Perozzi, Rami Al-Rfou, and Steven Skiena. Deepwalk: Online learning of social rep- resentations. In KDD, pages 701-710, 2014.","title":"Deepwalk: Online learning of social representations","authors":"Bryan Perozzi, Rami Al-Rfou, Steven Skiena","year":"2014","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Rendle, 2010] Steffen Rendle. Factorization machines. In ICDM, pages 995-1000, 2010.","title":"Factorization machines","authors":"Steffen Rendle","year":"2010","venue":"ICDM","doi":null,"url":null,"internal_url":null},{"position":21,"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, 29(3):93-93, 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":22,"raw":"[Veličković et al., 2018] Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. Graph attention networks. ICLR, 2018.","title":"Graph attention networks","authors":"Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, Yoshua Bengio","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Veličković et al., 2019] Petar Veličković, 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 Veličković, William Fedus, William L Hamilton, Pietro Liò, Yoshua Bengio, Devon Hjelm","year":"2019","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Wang et al., 2019] Xiang Wang, Xiangnan He, Meng Wang, Fuli Feng, and Tat-Seng Chua. Neural graph col- laborative filtering. In SIGIR, pages 165-174, 2019.","title":"Neural graph collaborative filtering","authors":"Xiang Wang, Xiangnan He, Meng Wang, Fuli Feng, Tat-Seng Chua","year":"2019","venue":"SIGIR","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Weston et al., 2012] Jason Weston, Frédéric Ratle, Hossein Mobahi, and Ronan Collobert. Deep learning via semi- supervised embedding. In Neural Networks: Tricks of the Trade, pages 639-655. Springer, 2012.","title":"Deep learning via semisupervised embedding","authors":"Jason Weston, Frédéric Ratle, Hossein Mobahi, Ronan Collobert","year":"2012","venue":"Neural Networks: Tricks of the Trade","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Wu et al., 2019] Felix Wu, Tianyi Zhang, Amauri Holanda de Souza Jr, Christopher Fifty, Tao Yu, and Kilian Q Weinberger. Simplifying graph convolutional networks. ICML, pages 6861-6871, 2019.","title":"Simplifying graph convolutional networks","authors":"Felix Wu, Tianyi Zhang, Amauri Holanda De Souza, Christopher Fifty, Tao Yu, Kilian Q Weinberger","year":"2019","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Xinyi and Chen, 2019] Zhang Xinyi and Lihui Chen. Cap- sule graph neural network. In ICLR, 2019.","title":"Capsule graph neural network","authors":"Zhang Xinyi, Lihui Chen","year":"2019","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Xu et al., 2018] Keyulu Xu, Chengtao Li, Yonglong Tian, Tomohiro Sonobe, Ken-ichi Kawarabayashi, and Stefanie Jegelka. Representation learning on graphs with jumping knowledge networks. ICML, pages 8676-8685, 2018.","title":"Representation learning on graphs with jumping knowledge networks","authors":"Xu","year":"2018","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Xu et al., 2019a] Bingbing Xu, Huawei Shen, Qi Cao, Yunqi Qiu, and Xueqi Cheng. Graph wavelet neural net- work. In ICLR, 2019.","title":"Graph wavelet neural network","authors":"Xu","year":"2019","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Xu et al., 2019b] Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. How powerful are graph neural net- works? ICLR, 2019.","title":"How powerful are graph neural networks? ICLR","authors":"Xu","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Yang et al., 2016] Zhilin Yang, William W Cohen, and Rus- lan Salakhutdinov. Revisiting semi-supervised learning with graph embeddings. ICML, pages 86-94, 2016.","title":"Revisiting semi-supervised learning with graph embeddings","authors":"Zhilin Yang, William W Cohen, Ruslan Salakhutdinov","year":"2016","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Zhang et al., 2018] Ziwei Zhang, Peng Cui, and Wenwu Zhu. Deep learning on graphs: A survey. arXiv preprint arXiv:1812.04202, 2018.","title":"Deep learning on graphs: A survey","authors":"Ziwei Zhang, Peng Cui, Wenwu Zhu","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}