ABSTRACT
Graph Neural Networks (GNNs) have proven to be powerful in many graph-based applications. However, they fail to generalize well under heterophilic setups, where neighbor nodes have different labels. To address this challenge, we employ a confidence ratio as a hyper-parameter, assuming that some of the edges are disassortative (heterophilic). Here, we propose a two-phased algorithm. Firstly, we determine edge coefficients through subgraph matching using a supplementary module. Then, we apply GNNs with a modified label propagation mechanism to utilize the edge coefficients effectively. Specifically, our supplementary module identifies a certain proportion of task-irrelevant edges based on a given confidence ratio. Using the remaining edges, we employ the widely used optimal transport to measure the similarity between two nodes with their subgraphs. Finally, using the coefficients as supplementary information on GNNs, we improve the label propagation mechanism which can prevent two nodes with smaller weights from being closer. The experiments on benchmark datasets show that our model alleviates over-smoothing and improves performance.
- Deyu Bo, Xiao Wang, Chuan Shi, and Huawei Shen. 2021. Beyond low-frequency information in graph convolutional networks. arXiv preprint arXiv:2101.00797 (2021).Google Scholar
- Thang D Bui, Sujith Ravi, and Vivek Ramavajjala. 2018. Neural graph learning: Training neural networks using graphs. In Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining. 64--71.Google ScholarDigital Library
- Ming Chen, Zhewei Wei, Zengfeng Huang, Bolin Ding, and Yaliang Li. 2020. Simple and deep graph convolutional networks. In International Conference on Machine Learning. PMLR, 1725--1735.Google Scholar
- Marco Cuturi and Arnaud Doucet. 2014. Fast computation of Wasserstein barycenters. In International conference on machine learning. PMLR, 685--693.Google Scholar
- Michaël Defferrard, Xavier Bresson, and Pierre Vandergheynst. 2016. Convolutional neural networks on graphs with fast localized spectral filtering. Advances in neural information processing systems, Vol. 29 (2016).Google Scholar
- Utkarsh Desai, Sambaran Bandyopadhyay, and Srikanth Tamilselvam. 2021. Graph neural network to dilute outliers for refactoring monolith application. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 72--80.Google ScholarCross Ref
- Yushun Dong, Kaize Ding, Brian Jalaian, Shuiwang Ji, and Jundong Li. 2021. Graph neural networks with adaptive frequency response filter. arXiv preprint arXiv:2104.12840 (2021).Google Scholar
- 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.Google ScholarDigital Library
- Wenqi Fan, Yao Ma, Qing Li, Yuan He, Eric Zhao, Jiliang Tang, and Dawei Yin. 2019. Graph neural networks for social recommendation. In The world wide web conference. 417--426.Google Scholar
- Alex Fout, Jonathon Byrd, Basir Shariat, and Asa Ben-Hur. 2017. Protein interface prediction using graph convolutional networks. Advances in neural information processing systems, Vol. 30 (2017).Google Scholar
- Justin Gilmer, Samuel S Schoenholz, Patrick F Riley, Oriol Vinyals, and George E Dahl. 2017. Neural message passing for quantum chemistry. In International conference on machine learning. PMLR, 1263--1272.Google Scholar
- Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. Advances in neural information processing systems, Vol. 30 (2017).Google Scholar
- David K Hammond, Pierre Vandergheynst, and Rémi Gribonval. 2011. Wavelets on graphs via spectral graph theory. Applied and Computational Harmonic Analysis, Vol. 30, 2 (2011), 129--150.Google ScholarCross Ref
- Wei Jin, Tyler Derr, Yiqi Wang, Yao Ma, Zitao Liu, and Jiliang Tang. 2021. Node similarity preserving graph convolutional networks. In Proceedings of the 14th ACM International Conference on Web Search and Data Mining. 148--156.Google ScholarDigital Library
- Dongkwan Kim and Alice Oh. 2022. How to find your friendly neighborhood: Graph attention design with self-supervision. arXiv preprint arXiv:2204.04879 (2022).Google Scholar
- Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016).Google Scholar
- Johannes Klicpera, Aleksandar Bojchevski, and Stephan Günnemann. 2018. Predict then propagate: Graph neural networks meet personalized pagerank. arXiv preprint arXiv:1810.05997 (2018).Google Scholar
- Soheil Kolouri, Navid Naderializadeh, Gustavo K Rohde, and Heiko Hoffmann. 2020. Wasserstein embedding for graph learning. arXiv preprint arXiv:2006.09430 (2020).Google Scholar
- Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep learning. nature, Vol. 521, 7553 (2015), 436--444.Google Scholar
- Qimai Li, Zhichao Han, and Xiao-Ming Wu. 2018. Deeper insights into graph convolutional networks for semi-supervised learning. In Thirty-Second AAAI conference on artificial intelligence.Google ScholarCross Ref
- Hongrui Liu, Binbin Hu, Xiao Wang, Chuan Shi, Zhiqiang Zhang, and Jun Zhou. 2022. Confidence May Cheat: Self-Training on Graph Neural Networks under Distribution Shift. In Proceedings of the ACM Web Conference 2022. 1248--1258.Google ScholarDigital Library
- Meng Liu, Zhengyang Wang, and Shuiwang Ji. 2021. Non-local graph neural networks. IEEE Transactions on Pattern Analysis and Machine Intelligence (2021).Google ScholarCross Ref
- Sitao Luan, Chenqing Hua, Qincheng Lu, Jiaqi Zhu, Mingde Zhao, Shuyuan Zhang, Xiao-Wen Chang, and Doina Precup. 2021. Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification? arXiv preprint arXiv:2109.05641 (2021).Google Scholar
- Dongsheng Luo, Wei Cheng, Wenchao Yu, Bo Zong, Jingchao Ni, Haifeng Chen, and Xiang Zhang. 2021a. Learning to drop: Robust graph neural network via topological denoising. In Proceedings of the 14th ACM International Conference on Web Search and Data Mining. 779--787.Google ScholarDigital Library
- Gongxu Luo, Jianxin Li, Jianlin Su, Hao Peng, Carl Yang, Lichao Sun, Philip S Yu, and Lifang He. 2021b. Graph entropy guided node embedding dimension selection for graph neural networks. arXiv preprint arXiv:2105.03178 (2021).Google Scholar
- Yao Ma, Xiaorui Liu, Neil Shah, and Jiliang Tang. 2021. Is Homophily a Necessity for Graph Neural Networks? arXiv preprint arXiv:2106.06134 (2021).Google Scholar
- Andrew Kachites McCallum, Kamal Nigam, Jason Rennie, and Kristie Seymore. 2000. Automating the construction of internet portals with machine learning. Information Retrieval, Vol. 3, 2 (2000), 127--163.Google ScholarDigital Library
- Miller McPherson, Lynn Smith-Lovin, and James M Cook. 2001. Birds of a feather: Homophily in social networks. Annual review of sociology, Vol. 27, 1 (2001), 415--444.Google Scholar
- Grégoire Mialon, Dexiong Chen, Alexandre d'Aspremont, and Julien Mairal. 2020. A trainable optimal transport embedding for feature aggregation and its relationship to attention. arXiv preprint arXiv:2006.12065 (2020).Google Scholar
- Shashank Pandit, Duen Horng Chau, Samuel Wang, and Christos Faloutsos. 2007. Netprobe: a fast and scalable system for fraud detection in online auction networks. In Proceedings of the 16th international conference on World Wide Web. 201--210.Google ScholarDigital Library
- Hongbin Pei, Bingzhe Wei, Kevin Chen-Chuan Chang, Yu Lei, and Bo Yang. 2020. Geom-gcn: Geometric graph convolutional networks. arXiv preprint arXiv:2002.05287 (2020).Google Scholar
- Gabriel Peyré, Marco Cuturi, et al. 2019. Computational optimal transport: With applications to data science. Foundations and Trends® in Machine Learning, Vol. 11, 5--6 (2019), 355--607.Google ScholarDigital Library
- Marius-Constantin Popescu, Valentina E Balas, Liliana Perescu-Popescu, and Nikos Mastorakis. 2009. Multilayer perceptron and neural networks. WSEAS Transactions on Circuits and Systems, Vol. 8, 7 (2009), 579--588.Google ScholarDigital Library
- Yu Rong, Wenbing Huang, Tingyang Xu, and Junzhou Huang. 2019. Dropedge: Towards deep graph convolutional networks on node classification. arXiv preprint arXiv:1907.10903 (2019).Google Scholar
- Benedek Rozemberczki, Ryan Davies, Rik Sarkar, and Charles Sutton. 2019. Gemsec: Graph embedding with self clustering. In Proceedings of the 2019 IEEE/ACM international conference on advances in social networks analysis and mining. 65--72.Google ScholarDigital Library
- Franco Scarselli, Marco Gori, Ah Chung Tsoi, Markus Hagenbuchner, and Gabriele Monfardini. 2008. The graph neural network model. IEEE transactions on neural networks, Vol. 20, 1 (2008), 61--80.Google ScholarDigital Library
- Richard Sinkhorn and Paul Knopp. 1967. Concerning nonnegative matrices and doubly stochastic matrices. Pacific J. Math., Vol. 21, 2 (1967), 343--348.Google ScholarCross Ref
- Otilia Stretcu, Krishnamurthy Viswanathan, Dana Movshovitz-Attias, Emmanouil Platanios, Sujith Ravi, and Andrew Tomkins. 2019. Graph agreement models for semi-supervised learning. Advances in Neural Information Processing Systems, Vol. 32 (2019).Google Scholar
- 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.Google ScholarDigital Library
- Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2017. Graph attention networks. stat, Vol. 1050 (2017), 20.Google Scholar
- Hongwei Wang and Jure Leskovec. 2020. Unifying graph convolutional neural networks and label propagation. arXiv preprint arXiv:2002.06755 (2020).Google Scholar
- Xiaolong Wang, Ross Girshick, Abhinav Gupta, and Kaiming He. 2018. Non-local neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition. 7794--7803.Google ScholarCross Ref
- Teng Xiao, Zhengyu Chen, Donglin Wang, and Suhang Wang. 2021. Learning how to propagate messages in graph neural networks. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 1894--1903.Google ScholarDigital Library
- Hongteng Xu, Dixin Luo, and Lawrence Carin. 2019a. Scalable Gromov-Wasserstein learning for graph partitioning and matching. Advances in neural information processing systems, Vol. 32 (2019).Google Scholar
- Hongteng Xu, Dixin Luo, Hongyuan Zha, and Lawrence Carin Duke. 2019b. Gromov-wasserstein learning for graph matching and node embedding. In International conference on machine learning. PMLR, 6932--6941.Google Scholar
- Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. 2018. How powerful are graph neural networks? arXiv preprint arXiv:1810.00826 (2018).Google Scholar
- Han Yang, Kaili Ma, and James Cheng. 2021a. Rethinking graph regularization for graph neural networks. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 4573--4581.Google ScholarCross Ref
- Liang Yang, Fan Wu, Yingkui Wang, Junhua Gu, and Yuanfang Guo. 2019. Masked Graph Convolutional Network. In IJCAI. 4070--4077.Google Scholar
- Tianmeng Yang, Yujing Wang, Zhihan Yue, Yaming Yang, Yunhai Tong, and Jing Bai. 2021b. Graph Pointer Neural Networks. arXiv preprint arXiv:2110.00973 (2021).Google Scholar
- Zhitao Ying, Dylan Bourgeois, Jiaxuan You, Marinka Zitnik, and Jure Leskovec. 2019. Gnnexplainer: Generating explanations for graph neural networks. Advances in neural information processing systems, Vol. 32 (2019).Google Scholar
- Lingxiao Zhao and Leman Akoglu. 2019. Pairnorm: Tackling oversmoothing in gnns. arXiv preprint arXiv:1909.12223 (2019).Google Scholar
- Cheng Zheng, Bo Zong, Wei Cheng, Dongjin Song, Jingchao Ni, Wenchao Yu, Haifeng Chen, and Wei Wang. 2020. Robust graph representation learning via neural sparsification. In International Conference on Machine Learning. PMLR, 11458--11468.Google Scholar
- Jiong Zhu, Yujun Yan, Lingxiao Zhao, Mark Heimann, Leman Akoglu, and Danai Koutra. 2020. Beyond homophily in graph neural networks: Current limitations and effective designs. Advances in Neural Information Processing Systems, Vol. 33 (2020), 7793--7804.Google Scholar
Index Terms
- Finding Heterophilic Neighbors via Confidence-based Subgraph Matching for Semi-supervised Node Classification
Recommendations
Semi-supervised Multi-label k-Nearest Neighbors Classification Algorithms
BRACIS '15: Proceedings of the 2015 Brazilian Conference on Intelligent Systems (BRACIS)Classification is one of the most traditional tasks in machine learning. In supervised learning for classification, the goal is to learn a classifier function using a completely labeled dataset. Semi-supervised learning modifies the learning algorithm ...
Semantic guide for semi-supervised few-shot multi-label node classification
AbstractWe study a new research problem named semi-supervised few-shot multi-label node classification which has the following characteristics: 1) the extreme imbalance between the number of labeled and unlabeled nodes that are connected on ...
GraFN: Semi-Supervised Node Classification on Graph with Few Labels via Non-Parametric Distribution Assignment
SIGIR '22: Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information RetrievalDespite the success of Graph Neural Networks (GNNs) on various applications, GNNs encounter significant performance degradation when the amount of supervision signals, i.e., number of labeled nodes, is limited, which is expected as GNNs are trained ...
Comments