{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,7,22]],"date-time":"2022-07-22T14:40:24Z","timestamp":1658500824397},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","funder":[{"name":"CCF- Ant Group Research Fund"},{"name":"the Fundamental Research Funds for the Central Universities","award":["2021RC28"]},{"name":"the National Natural Science Foundation of China","award":["No. U20B2045, 62192784, 62172052, 61772082, 62002029, U1936104"]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,4,25]]},"DOI":"10.1145\/3485447.3512172","type":"proceedings-article","created":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T05:13:07Z","timestamp":1650863587000},"source":"Crossref","is-referenced-by-count":0,"title":["Confidence May Cheat: Self-Training on Graph Neural Networks under Distribution Shift"],"prefix":"10.1145","author":[{"given":"Hongrui","family":"Liu","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications, China"}]},{"given":"Binbin","family":"Hu","sequence":"additional","affiliation":[{"name":"Ant Group, China"}]},{"given":"Xiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, China and Peng Cheng Laboratory, China"}]},{"given":"Chuan","family":"Shi","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, China and Peng Cheng Laboratory, China"}]},{"given":"Zhiqiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Ant Group, China"}]},{"given":"Jun","family":"Zhou","sequence":"additional","affiliation":[{"name":"Ant Group, China"}]}],"member":"320","published-online":{"date-parts":[[2022,4,25]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Antonin Berthon Bo Han Gang Niu Tongliang Liu and Masashi Sugiyama. 2021. Confidence scores make instance-dependent label-noise learning possible. In ICML. 825\u2013836. Antonin Berthon Bo Han Gang Niu Tongliang Liu and Masashi Sugiyama. 2021. Confidence scores make instance-dependent label-noise learning possible. In ICML. 825\u2013836."},{"key":"e_1_3_2_1_2_1","unstructured":"Charles Blundell Julien Cornebise Koray Kavukcuoglu and Daan Wierstra. 2015. Weight uncertainty in neural network. In ICML. 1613\u20131622. Charles Blundell Julien Cornebise Koray Kavukcuoglu and Daan Wierstra. 2015. Weight uncertainty in neural network. In ICML. 1613\u20131622."},{"key":"e_1_3_2_1_3_1","unstructured":"Aleksandar Bojchevski and Stephan G\u00fcnnemann. 2018. Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking. In ICLR. Aleksandar Bojchevski and Stephan G\u00fcnnemann. 2018. Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking. In ICLR."},{"key":"e_1_3_2_1_4_1","unstructured":"Joan Bruna Wojciech Zaremba Arthur Szlam and Yann LeCun. 2014. Spectral Networks and Locally Connected Networks on Graphs. In ICLR. Joan Bruna Wojciech Zaremba Arthur Szlam and Yann LeCun. 2014. Spectral Networks and Locally Connected Networks on Graphs. In ICLR."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Mathilde Caron Piotr Bojanowski Armand Joulin and Matthijs Douze. 2018. Deep clustering for unsupervised learning of visual features. In ECCV. 132\u2013149. Mathilde Caron Piotr Bojanowski Armand Joulin and Matthijs Douze. 2018. Deep clustering for unsupervised learning of visual features. In ECCV. 132\u2013149.","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"e_1_3_2_1_6_1","volume-title":"Elements of information theory","author":"Cover M","unstructured":"Thomas\u00a0 M Cover . 1999. Elements of information theory . John Wiley & Sons . Thomas\u00a0M Cover. 1999. Elements of information theory. John Wiley & Sons."},{"key":"e_1_3_2_1_7_1","unstructured":"Micha\u00ebl Defferrard Xavier Bresson and Pierre Vandergheynst. 2016. Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering. In NIPS. 3837\u20133845. Micha\u00ebl Defferrard Xavier Bresson and Pierre Vandergheynst. 2016. Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering. In NIPS. 3837\u20133845."},{"key":"e_1_3_2_1_8_1","volume-title":"SLADE: A Self-Training Framework for Distance Metric Learning. In CVPR. 9644\u20139653.","author":"Duan Jiali","year":"2020","unstructured":"Jiali Duan , Yen-Liang Lin , Son\u00a0Dinh Tran , Larry\u00a0 S. Davis , and C.-C.\u00a0 Jay Kuo . 2020 . SLADE: A Self-Training Framework for Distance Metric Learning. In CVPR. 9644\u20139653. Jiali Duan, Yen-Liang Lin, Son\u00a0Dinh Tran, Larry\u00a0S. Davis, and C.-C.\u00a0Jay Kuo. 2020. SLADE: A Self-Training Framework for Distance Metric Learning. In CVPR. 9644\u20139653."},{"key":"e_1_3_2_1_9_1","unstructured":"Yarin Gal and Zoubin Ghahramani. 2016. Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In ICML. 1050\u20131059. Yarin Gal and Zoubin Ghahramani. 2016. Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In ICML. 1050\u20131059."},{"key":"e_1_3_2_1_10_1","unstructured":"Jacob Goldberger and Ehud Ben-Reuven. 2017. Training deep neural-networks using a noise adaptation layer. In ICLR. Jacob Goldberger and Ehud Ben-Reuven. 2017. Training deep neural-networks using a noise adaptation layer. In ICLR."},{"key":"e_1_3_2_1_11_1","unstructured":"Alex Graves. 2011. Practical variational inference for neural networks. In NIPS. 2348\u20132356. Alex Graves. 2011. Practical variational inference for neural networks. In NIPS. 2348\u20132356."},{"key":"e_1_3_2_1_12_1","unstructured":"William\u00a0L Hamilton Rex Ying and Jure Leskovec. 2017. Inductive representation learning on large graphs. In NIPS. 1025\u20131035. William\u00a0L Hamilton Rex Ying and Jure Leskovec. 2017. Inductive representation learning on large graphs. In NIPS. 1025\u20131035."},{"key":"e_1_3_2_1_13_1","unstructured":"Arman Hasanzadeh Ehsan Hajiramezanali Shahin Boluki Mingyuan Zhou Nick Duffield Krishna Narayanan and Xiaoning Qian. 2020. Bayesian graph neural networks with adaptive connection sampling. In ICML. 4094\u20134104. Arman Hasanzadeh Ehsan Hajiramezanali Shahin Boluki Mingyuan Zhou Nick Duffield Krishna Narayanan and Xiaoning Qian. 2020. Bayesian graph neural networks with adaptive connection sampling. In ICML. 4094\u20134104."},{"key":"e_1_3_2_1_14_1","unstructured":"Junxian He Jiatao Gu Jiajun Shen and Marc\u2019Aurelio Ranzato. 2020. Revisiting Self-Training for Neural Sequence Generation. In ICLR. Junxian He Jiatao Gu Jiajun Shen and Marc\u2019Aurelio Ranzato. 2020. Revisiting Self-Training for Neural Sequence Generation. In ICLR."},{"key":"e_1_3_2_1_15_1","unstructured":"Jose Hernandez-Lobato Yingzhen Li Mark Rowland Thang Bui Daniel Hern\u00e1ndez-Lobato and Richard Turner. 2016. Black-box alpha divergence minimization. In ICML. 1511\u20131520. Jose Hernandez-Lobato Yingzhen Li Mark Rowland Thang Bui Daniel Hern\u00e1ndez-Lobato and Richard Turner. 2016. Black-box alpha divergence minimization. In ICML. 1511\u20131520."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1965.1053799"},{"key":"e_1_3_2_1_17_1","volume-title":"Kipf and Max Welling","author":"N.","year":"2017","unstructured":"Thomas\u00a0 N. Kipf and Max Welling . 2017 . Semi-Supervised Classification with Graph Convolutional Networks. In ICLR. Thomas\u00a0N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In ICLR."},{"key":"e_1_3_2_1_18_1","unstructured":"Johannes Klicpera Aleksandar Bojchevski and Stephan G\u00fcnnemann. 2019. Predict then Propagate: Graph Neural Networks meet Personalized PageRank. In ICLR. Johannes Klicpera Aleksandar Bojchevski and Stephan G\u00fcnnemann. 2019. Predict then Propagate: Graph Neural Networks meet Personalized PageRank. In ICLR."},{"key":"e_1_3_2_1_19_1","volume-title":"ICML Workshop.","author":"Lee Dong-Hyun","year":"2013","unstructured":"Dong-Hyun Lee 2013 . Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks . In ICML Workshop. Dong-Hyun Lee 2013. Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In ICML Workshop."},{"key":"e_1_3_2_1_20_1","unstructured":"Qimai Li Zhichao Han and Xiao-Ming Wu. 2018. Deeper Insights Into Graph Convolutional Networks for Semi-Supervised Learning. In AAAI. 3538\u20133545. Qimai Li Zhichao Han and Xiao-Ming Wu. 2018. Deeper Insights Into Graph Convolutional Networks for Semi-Supervised Learning. In AAAI. 3538\u20133545."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Zaiqiao Meng Shangsong Liang Hongyan Bao and Xiangliang Zhang. 2019. Co-embedding attributed networks. In WSDM. 393\u2013401. Zaiqiao Meng Shangsong Liang Hongyan Bao and Xiangliang Zhang. 2019. Co-embedding attributed networks. In WSDM. 393\u2013401.","DOI":"10.1145\/3289600.3291015"},{"key":"e_1_3_2_1_22_1","unstructured":"Subhabrata Mukherjee and Ahmed Awadallah. 2020. Uncertainty-aware self-training for few-shot text classification. In NIPS. Subhabrata Mukherjee and Ahmed Awadallah. 2020. Uncertainty-aware self-training for few-shot text classification. In NIPS."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Giorgio Patrini Alessandro Rozza Aditya Krishna\u00a0Menon Richard Nock and Lizhen Qu. 2017. Making deep neural networks robust to label noise: A loss correction approach. In CVPR. 1944\u20131952. Giorgio Patrini Alessandro Rozza Aditya Krishna\u00a0Menon Richard Nock and Lizhen Qu. 2017. Making deep neural networks robust to label noise: A loss correction approach. In CVPR. 1944\u20131952.","DOI":"10.1109\/CVPR.2017.240"},{"key":"e_1_3_2_1_24_1","volume-title":"Dropedge: Towards deep graph convolutional networks on node classification. arXiv preprint arXiv:1907.10903(2019).","author":"Rong Yu","year":"2019","unstructured":"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). 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)."},{"key":"e_1_3_2_1_25_1","volume-title":"Collective classification in network data. AI magazine 29, 3","author":"Sen Prithviraj","year":"2008","unstructured":"Prithviraj Sen , Galileo Namata , Mustafa Bilgic , Lise Getoor , Brian Galligher , and Tina Eliassi-Rad . 2008. Collective classification in network data. AI magazine 29, 3 ( 2008 ), 93\u201393. Prithviraj Sen, Galileo Namata, Mustafa Bilgic, Lise Getoor, Brian Galligher, and Tina Eliassi-Rad. 2008. Collective classification in network data. AI magazine 29, 3 (2008), 93\u201393."},{"key":"e_1_3_2_1_26_1","unstructured":"Sainbayar Sukhbaatar Joan Bruna Manohar Paluri Lubomir Bourdev and Rob Fergus. 2014. Training convolutional networks with noisy labels. arXiv preprint arXiv:1406.2080(2014). Sainbayar Sukhbaatar Joan Bruna Manohar Paluri Lubomir Bourdev and Rob Fergus. 2014. Training convolutional networks with noisy labels. arXiv preprint arXiv:1406.2080(2014)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Ke Sun Zhouchen Lin and Zhanxing Zhu. 2020. Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labeled Nodes. In AAAI. 5892\u20135899. Ke Sun Zhouchen Lin and Zhanxing Zhu. 2020. Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labeled Nodes. In AAAI. 5892\u20135899.","DOI":"10.1609\/aaai.v34i04.6048"},{"key":"e_1_3_2_1_28_1","volume-title":"Visualizing data using t-SNE.Journal of machine learning research 9, 11","author":"Maaten Laurens Van\u00a0der","year":"2008","unstructured":"Laurens Van\u00a0der Maaten and Geoffrey Hinton . 2008. Visualizing data using t-SNE.Journal of machine learning research 9, 11 ( 2008 ). Laurens Van\u00a0der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE.Journal of machine learning research 9, 11 (2008)."},{"key":"e_1_3_2_1_29_1","unstructured":"Petar Veli\u010dkovi\u0107 Guillem Cucurull Arantxa Casanova Adriana Romero Pietro Lio and Yoshua Bengio. 2017. Graph attention networks. ICLR. Petar Veli\u010dkovi\u0107 Guillem Cucurull Arantxa Casanova Adriana Romero Pietro Lio and Yoshua Bengio. 2017. Graph attention networks. ICLR."},{"key":"e_1_3_2_1_30_1","volume-title":"Advances in Neural Information Processing Systems 34","author":"Wang Xiao","year":"2021","unstructured":"Xiao Wang , Hongrui Liu , Chuan Shi , and Cheng Yang . 2021. Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibration . Advances in Neural Information Processing Systems 34 ( 2021 ). Xiao Wang, Hongrui Liu, Chuan Shi, and Cheng Yang. 2021. Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibration. Advances in Neural Information Processing Systems 34 (2021)."},{"key":"e_1_3_2_1_31_1","unstructured":"Felix Wu Amauri Souza Tianyi Zhang Christopher Fifty Tao Yu and Kilian Weinberger. 2019. Simplifying graph convolutional networks. In ICML. 6861\u20136871. Felix Wu Amauri Souza Tianyi Zhang Christopher Fifty Tao Yu and Kilian Weinberger. 2019. Simplifying graph convolutional networks. In ICML. 6861\u20136871."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"e_1_3_2_1_34_1","unstructured":"Keyulu Xu Weihua Hu Jure Leskovec and Stefanie Jegelka. 2019. How Powerful are Graph Neural Networks. In ICLR. Keyulu Xu Weihua Hu Jure Leskovec and Stefanie Jegelka. 2019. How Powerful are Graph Neural Networks. In ICLR."},{"key":"e_1_3_2_1_35_1","volume-title":"Deep learning on graphs: A survey","author":"Zhang Ziwei","year":"2020","unstructured":"Ziwei Zhang , Peng Cui , and Wenwu Zhu . 2020. Deep learning on graphs: A survey . IEEE Transactions on Knowledge and Data Engineering ( 2020 ). Ziwei Zhang, Peng Cui, and Wenwu Zhu. 2020. Deep learning on graphs: A survey. IEEE Transactions on Knowledge and Data Engineering (2020)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.01.001"},{"key":"e_1_3_2_1_37_1","unstructured":"Ziang Zhou Jieming Shi Shengzhong Zhang Zengfeng Huang and Qing Li. 2019. Effective Semi-Supervised Node Classification on Few-Labeled Graph Data. arXiv preprint arXiv:1910.02684(2019). Ziang Zhou Jieming Shi Shengzhong Zhang Zengfeng Huang and Qing Li. 2019. Effective Semi-Supervised Node Classification on Few-Labeled Graph Data. arXiv preprint arXiv:1910.02684(2019)."}],"event":{"name":"WWW '22: The ACM Web Conference 2022","location":"Virtual Event, Lyon France","acronym":"WWW '22","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2022"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3485447.3512172","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,22]],"date-time":"2022-07-22T14:27:45Z","timestamp":1658500065000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3485447.3512172"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,25]]},"references-count":37,"alternative-id":["10.1145\/3485447.3512172","10.1145\/3485447"],"URL":"http:\/\/dx.doi.org\/10.1145\/3485447.3512172","relation":{},"published":{"date-parts":[[2022,4,25]]}}}