Confidence May Cheat: Self-Training on Graph Neural Networks under Distribution Shift
暂无分享,去创建一个
Xiao Wang | Zhiqiang Zhang | Jun Zhou | Hongrui Liu | Binbin Hu | Chuan Shi | Xiao Wang | Zhiqiang Zhang | Jun Zhou | Binbin Hu | Chuan Shi | Hongrui Liu
[1] Xiaoning Qian,et al. Bayesian Graph Neural Networks with Adaptive Connection Sampling , 2020, ICML.
[2] H. J. Scudder,et al. Probability of error of some adaptive pattern-recognition machines , 1965, IEEE Trans. Inf. Theory.
[3] Stephan Günnemann,et al. Predict then Propagate: Graph Neural Networks meet Personalized PageRank , 2018, ICLR.
[4] Jure Leskovec,et al. How Powerful are Graph Neural Networks? , 2018, ICLR.
[5] Subhabrata Mukherjee,et al. Uncertainty-aware Self-training for Few-shot Text Classification , 2020, NeurIPS.
[6] Philip S. Yu,et al. A Comprehensive Survey on Graph Neural Networks , 2019, IEEE Transactions on Neural Networks and Learning Systems.
[7] Geoffrey E. Hinton,et al. Visualizing Data using t-SNE , 2008 .
[8] Jacob Goldberger,et al. Training deep neural-networks using a noise adaptation layer , 2016, ICLR.
[9] Longin Jan Latecki,et al. Rank-based self-training for graph convolutional networks , 2021, Inf. Process. Manag..
[10] Tingyang Xu,et al. DropEdge: Towards Deep Graph Convolutional Networks on Node Classification , 2020, ICLR.
[11] Thomas M. Cover,et al. Elements of Information Theory , 2005 .
[12] Jiajun Shen,et al. Revisiting Self-Training for Neural Sequence Generation , 2020, ICLR.
[13] Zhanxing Zhu,et al. Multi-Stage Self-Supervised Learning for Graph Convolutional Networks , 2020, AAAI.
[14] Joan Bruna,et al. Training Convolutional Networks with Noisy Labels , 2014, ICLR 2014.
[15] Zhiyuan Liu,et al. Graph Neural Networks: A Review of Methods and Applications , 2018, AI Open.
[16] Joan Bruna,et al. Spectral Networks and Locally Connected Networks on Graphs , 2013, ICLR.
[17] Dong-Hyun Lee,et al. Pseudo-Label : The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks , 2013 .
[18] Max Welling,et al. Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.
[19] Xiangliang Zhang,et al. Co-Embedding Attributed Networks , 2019, WSDM.
[20] Michael J. Watts,et al. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS Publication Information , 2020, IEEE Transactions on Neural Networks and Learning Systems.
[21] Jure Leskovec,et al. Inductive Representation Learning on Large Graphs , 2017, NIPS.
[22] Zoubin Ghahramani,et al. Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning , 2015, ICML.
[23] Stephan Günnemann,et al. Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking , 2017, ICLR.
[24] Richard Nock,et al. Making Deep Neural Networks Robust to Label Noise: A Loss Correction Approach , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
[25] Xiao Wang,et al. Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibration , 2021, NeurIPS.
[26] Alex Graves,et al. Practical Variational Inference for Neural Networks , 2011, NIPS.
[27] Xiao-Ming Wu,et al. Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning , 2018, AAAI.
[28] Julien Cornebise,et al. Weight Uncertainty in Neural Network , 2015, ICML.
[29] Daniel Hernández-Lobato,et al. Black-Box Alpha Divergence Minimization , 2015, ICML.
[30] Gang Niu,et al. Confidence Scores Make Instance-dependent Label-noise Learning Possible , 2019, ICML.
[31] Xavier Bresson,et al. Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering , 2016, NIPS.
[32] Matthijs Douze,et al. Deep Clustering for Unsupervised Learning of Visual Features , 2018, ECCV.
[33] Lise Getoor,et al. Collective Classification in Network Data , 2008, AI Mag..
[34] Kilian Q. Weinberger,et al. Simplifying Graph Convolutional Networks , 2019, ICML.
[35] C.-C. Jay Kuo,et al. SLADE: A Self-Training Framework For Distance Metric Learning , 2020, ArXiv.
[36] Wenwu Zhu,et al. Deep Learning on Graphs: A Survey , 2018, IEEE Transactions on Knowledge and Data Engineering.