ABSTRACT
Graph Neural Networks (GNNs) have achieved promising results for semi-supervised learning tasks on graphs such as node classification. Despite the great success of GNNs, many real-world graphs are often sparsely and noisily labeled, which could significantly degrade the performance of GNNs, as the noisy information could propagate to unlabeled nodes via graph structure. Thus, it is important to develop a label noise-resistant GNN for semi-supervised node classification. Though extensive studies have been conducted to learn neural networks with noisy labels, they mostly focus on independent and identically distributed data and assume a large number of noisy labels are available, which are not directly applicable for GNNs. Thus, we investigate a novel problem of learning a robust GNN with noisy and limited labels. To alleviate the negative effects of label noise, we propose to link the unlabeled nodes with labeled nodes of high feature similarity to bring more clean label information. Furthermore, accurate pseudo labels could be obtained by this strategy to provide more supervision and further reduce the effects of label noise. Our theoretical and empirical analysis verify the effectiveness of these two strategies under mild conditions. Extensive experiments on real-world datasets demonstrate the effectiveness of the proposed method in learning a robust GNN with noisy and limited labels.
Supplemental Material
- Joan Bruna, Wojciech Zaremba, Arthur Szlam, and Yann LeCun. 2014. Spectral networks and locally connected networks on graphs. ICLR (2014).Google Scholar
- Jie Chen, Tengfei Ma, and Cao Xiao. 2018. Fastgcn: fast learning with graph convolutional networks via importance sampling. ICLR (2018).Google Scholar
- Enyan Dai and Suhang Wang. 2021. Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information. In WSDM. 680--688.Google Scholar
- Michaël Defferrard, Xavier Bresson, and Pierre Vandergheynst. 2016. Convolutional neural networks on graphs with fast localized spectral filtering. In NeurIPS. 3844--3852.Google Scholar
- Hande Dong, Jiawei Chen, Fuli Feng, Xiangnan He, Shuxian Bi, Zhaolin Ding, and Peng Cui. 2020. On the Equivalence of Decoupled Graph Convolution Network and Label Propagation. arXiv preprint arXiv:2010.12408 (2020).Google Scholar
- Justin Gilmer, Samuel S Schoenholz, Patrick F Riley, Oriol Vinyals, and George E Dahl. 2017. Neural message passing for quantum chemistry. ICML (2017).Google Scholar
- Jacob Goldberger and Ehud Ben-Reuven. 2016. Training deep neural-networks using a noise adaptation layer. (2016).Google Scholar
- Chen Gong, Hengmin Zhang, Jian Yang, and Dacheng Tao. 2017. Learning with inadequate and incorrect supervision. In ICDM. IEEE, 889--894.Google Scholar
- Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. In NeurIPS. 1024--1034.Google Scholar
- Bo Han, Quanming Yao, Xingrui Yu, Gang Niu, Miao Xu, Weihua Hu, Ivor Tsang, and Masashi Sugiyama. 2018. Co-teaching: Robust training of deep neural networks with extremely noisy labels. arXiv preprint arXiv:1804.06872 (2018).Google Scholar
- Xiangnan He, Lizi Liao, Hanwang Zhang, Liqiang Nie, Xia Hu, and Tat-Seng Chua. 2017. Neural collaborative filtering. In WWW. 173--182.Google Scholar
- Mikael Henaff, Joan Bruna, and Yann LeCun. 2015. Deep convolutional networks on graph-structured data. arXiv preprint arXiv:1506.05163 (2015).Google Scholar
- Lu Jiang, Zhengyuan Zhou, Thomas Leung, Li-Jia Li, and Li Fei-Fei. 2018. Mentornet: Learning data-driven curriculum for very deep neural networks on corrupted labels. In International Conference on Machine Learning. PMLR, 2304--2313.Google Scholar
- Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).Google Scholar
- Thomas N Kipf and Max Welling. 2016a. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016).Google Scholar
- Thomas N Kipf and Max Welling. 2016b. Variational graph auto-encoders. arXiv preprint arXiv:1611.07308 (2016).Google Scholar
- Sneha Kudugunta and Emilio Ferrara. 2018. Deep neural networks for bot detection. Information Sciences, Vol. 467 (2018), 312--322.Google ScholarCross Ref
- Ron Levie, Federico Monti, Xavier Bresson, and Michael M Bronstein. 2018. Cayleynets: Graph convolutional neural networks with complex rational spectral filters. IEEE Transactions on Signal Processing, Vol. 67, 1 (2018), 97--109.Google ScholarDigital Library
- Junnan Li, Richard Socher, and Steven CH Hoi. 2020. Dividemix: Learning with noisy labels as semi-supervised learning. arXiv preprint arXiv:2002.07394 (2020).Google Scholar
- Qimai Li, Zhichao Han, and Xiao-Ming Wu. 2018. Deeper insights into graph convolutional networks for semi-supervised learning. AAAI (2018).Google Scholar
- Rui Li, Shengjie Wang, and Kevin Chen-Chuan Chang. 2012. Multiple location profiling for users and relationships from social network and content. arXiv preprint arXiv:1208.0288 (2012).Google Scholar
- Xingjun Ma, Yisen Wang, Michael E Houle, Shuo Zhou, Sarah Erfani, Shutao Xia, Sudanthi Wijewickrema, and James Bailey. 2018. Dimensionality-driven learning with noisy labels. In ICML. PMLR, 3355--3364.Google Scholar
- Eran Malach and Shai Shalev-Shwartz. 2017. Decoupling" when to update" from" how to update". arXiv preprint arXiv:1706.02613 (2017).Google Scholar
- 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
- Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In NeurIPS. 3111--3119.Google Scholar
- Mark Newman. 2018. Networks. Oxford university press.Google Scholar
- Duc Tam Nguyen, Chaithanya Kumar Mummadi, Thi Phuong Nhung Ngo, Thi Hoai Phuong Nguyen, Laura Beggel, and Thomas Brox. 2019. Self: Learning to filter noisy labels with self-ensembling. arXiv preprint arXiv:1910.01842 (2019).Google Scholar
- Mathias Niepert, Mohamed Ahmed, and Konstantin Kutzkov. 2016. Learning convolutional neural networks for graphs. In ICML. 2014--2023.Google Scholar
- Hoang NT, Choong Jun Jin, and Tsuyoshi Murata. 2019. Learning graph neural networks with noisy labels. arXiv preprint arXiv:1905.01591 (2019).Google Scholar
- Shirui Pan, Jia Wu, Xingquan Zhu, Chengqi Zhang, and Yang Wang. 2016. Tri-party deep network representation. Network, Vol. 11, 9 (2016), 12.Google Scholar
- Giorgio Patrini, Alessandro Rozza, Aditya Krishna Menon, Richard Nock, and Lizhen Qu. 2017. Making deep neural networks robust to label noise: A loss correction approach. In CVPR. 1944--1952.Google Scholar
- Scott Reed, Honglak Lee, Dragomir Anguelov, Christian Szegedy, Dumitru Erhan, and Andrew Rabinovich. 2014. Training deep neural networks on noisy labels with bootstrapping. arXiv preprint arXiv:1412.6596 (2014).Google Scholar
- Prithviraj Sen, Galileo Namata, Mustafa Bilgic, Lise Getoor, Brian Galligher, and Tina Eliassi-Rad. 2008. Collective classification in network data. AI magazine, Vol. 29, 3 (2008), 93--93.Google Scholar
- Xianfeng Tang, Yandong Li, Yiwei Sun, Huaxiu Yao, Prasenjit Mitra, and Suhang Wang. 2020 a. Transferring Robustness for Graph Neural Network Against Poisoning Attacks. In WSDM. 600--608.Google Scholar
- Xianfeng Tang, Huaxiu Yao, Yiwei Sun, Yiqi Wang, Jiliang Tang, Charu Aggarwal, Prasenjit Mitra, and Suhang Wang. 2020 b. Investigating and Mitigating Degree-Related Biases in Graph Convoltuional Networks. In CIKM. 1435--1444.Google Scholar
- Petar Velivc ković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2017. Graph attention networks. ICLR (2017).Google Scholar
- Daixin Wang, Jianbin Lin, Peng Cui, Quanhui Jia, Zhen Wang, Yanming Fang, Quan Yu, Jun Zhou, Shuang Yang, and Yuan Qi. 2019. A semi-supervised graph attentive network for financial fraud detection. ICDM (2019).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
- Rex Ying, Ruining He, Kaifeng Chen, Pong Eksombatchai, William L Hamilton, and Jure Leskovec. 2018. Graph convolutional neural networks for web-scale recommender systems. In SIGKDD. 974--983.Google Scholar
- Bing Yu, Haoteng Yin, and Zhanxing Zhu. 2017. Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. arXiv preprint arXiv:1709.04875 (2017).Google Scholar
- Xingrui Yu, Bo Han, Jiangchao Yao, Gang Niu, Ivor Tsang, and Masashi Sugiyama. 2019. How does disagreement help generalization against label corruption?. In International Conference on Machine Learning. PMLR, 7164--7173.Google Scholar
- Chiyuan Zhang, Samy Bengio, Moritz Hardt, Benjamin Recht, and Oriol Vinyals. 2016. Understanding deep learning requires rethinking generalization. arXiv preprint arXiv:1611.03530 (2016).Google Scholar
- Huan Zhang, Zhao Zhang, Mingbo Zhao, Qiaolin Ye, Min Zhang, and Meng Wang. 2020 b. Robust triple-matrix-recovery-based auto-weighted label propagation for classification. IEEE TNNLS, Vol. 31, 11 (2020), 4538--4552.Google Scholar
- Mengmei Zhang, Chuan Shi, Linmei Hu, and Xiao Wang. 2020 a. Adversarial Label-Flipping Attack and Defense for Graph Neural Networks. ICDM (2020).Google Scholar
- Tianxiang Zhao, Xianfeng Tang, Xiang Zhang, and Suhang Wang. 2020. Semi-Supervised Graph-to-Graph Translation. In CIKM. 1863--1872.Google Scholar
- Tianxiang Zhao, Xiang Zhang, and Suhang Wang. 2021. GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networks. In WSDM. 833--841.Google Scholar
Index Terms
- NRGNN: Learning a Label Noise Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphs
Recommendations
Collaborative Learning with Pseudo Labels for Robust Classification in the Presence of Noisy Labels
Computer Vision – ECCV 2020 WorkshopsAbstractSupervised learning depends on labels of dataset to train models with desired properties. Therefore, data containing mislabeled samples (a.k.a. noisy labels) can deteriorate supervised learning performance significantly as it makes models to be ...
Few-shot partial multi-label learning with synthetic features network
AbstractIn partial multi-label learning (PML) problems, each training sample is partially annotated with a candidate label set, among which only a subset of labels are valid. The major hardship for PML is that its training procedure is prone to be misled ...
Multi-teacher Self-training for Semi-supervised Node Classification with Noisy Labels
MM '23: Proceedings of the 31st ACM International Conference on MultimediaGraph neural networks (GNNs) have achieved promising results for semi-supervised learning tasks on the graph-structured data. However, most existing methods assume that the training data are with correct labels, but in the real world, the graph-...
Comments