Timezone: »
Poster
Are Anchor Points Really Indispensable in Label-Noise Learning?
Xiaobo Xia · Tongliang Liu · Nannan Wang · Bo Han · Chen Gong · Gang Niu · Masashi Sugiyama
Wed Dec 11 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #25
In label-noise learning, the \textit{noise transition matrix}, denoting the probabilities that clean labels flip into noisy labels, plays a central role in building \textit{statistically consistent classifiers}. Existing theories have shown that the transition matrix can be learned by exploiting \textit{anchor points} (i.e., data points that belong to a specific class almost surely). However, when there are no anchor points, the transition matrix will be poorly learned, and those previously consistent classifiers will significantly degenerate. In this paper, without employing anchor points, we propose a \textit{transition-revision} ($T$-Revision) method to effectively learn transition matrices, leading to better classifiers. Specifically, to learn a transition matrix, we first initialize it by exploiting data points that are similar to anchor points, having high \textit{noisy class posterior probabilities}. Then, we modify the initialized matrix by adding a \textit{slack variable}, which can be learned and validated together with the classifier by using noisy data. Empirical results on benchmark-simulated and real-world label-noise datasets demonstrate that without using exact anchor points, the proposed method is superior to state-of-the-art label-noise learning methods.
Author Information
Xiaobo Xia (The University of Sydney / Xidian University)
Tongliang Liu (The University of Sydney)
Nannan Wang (Xidian University)
Bo Han (RIKEN)
Chen Gong (Nanjing University of Science and Technology)
Gang Niu (RIKEN)
Masashi Sugiyama (RIKEN / University of Tokyo)
More from the Same Authors
-
2021 Spotlight: TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation »
Haoang Chi · Feng Liu · Wenjing Yang · Long Lan · Tongliang Liu · Bo Han · William Cheung · James Kwok -
2021 : On the Role of Pre-training for Meta Few-Shot Learning »
Chia-You Chen · Hsuan-Tien Lin · Masashi Sugiyama · Gang Niu -
2021 Workshop: Second Workshop on Quantum Tensor Networks in Machine Learning »
Xiao-Yang Liu · Qibin Zhao · Ivan Oseledets · Yufei Ding · Guillaume Rabusseau · Jean Kossaifi · Khadijeh Najafi · Anwar Walid · Andrzej Cichocki · Masashi Sugiyama -
2021 : Discussion: Chelsea Finn, Masashi Sugiyama »
Chelsea Finn · Masashi Sugiyama -
2021 : Importance Weighting for Transfer Learning »
Masashi Sugiyama -
2021 Poster: Understanding and Improving Early Stopping for Learning with Noisy Labels »
Yingbin Bai · Erkun Yang · Bo Han · Yanhua Yang · Jiatong Li · Yinian Mao · Gang Niu · Tongliang Liu -
2021 Poster: Loss function based second-order Jensen inequality and its application to particle variational inference »
Futoshi Futami · Tomoharu Iwata · naonori ueda · Issei Sato · Masashi Sugiyama -
2021 Poster: Contrastive Graph Poisson Networks: Semi-Supervised Learning with Extremely Limited Labels »
Sheng Wan · Yibing Zhan · Liu Liu · Baosheng Yu · Shirui Pan · Chen Gong -
2021 Poster: Universal Semi-Supervised Learning »
Zhuo Huang · Chao Xue · Bo Han · Jian Yang · Chen Gong -
2021 Poster: Probabilistic Margins for Instance Reweighting in Adversarial Training »
qizhou wang · Feng Liu · Bo Han · Tongliang Liu · Chen Gong · Gang Niu · Mingyuan Zhou · Masashi Sugiyama -
2021 Poster: Instance-dependent Label-noise Learning under a Structural Causal Model »
Yu Yao · Tongliang Liu · Mingming Gong · Bo Han · Gang Niu · Kun Zhang -
2021 Poster: TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation »
Haoang Chi · Feng Liu · Wenjing Yang · Long Lan · Tongliang Liu · Bo Han · William Cheung · James Kwok -
2021 Poster: Confident Anchor-Induced Multi-Source Free Domain Adaptation »
Jiahua Dong · Zhen Fang · Anjin Liu · Gan Sun · Tongliang Liu -
2020 Poster: Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learning »
Yu Yao · Tongliang Liu · Bo Han · Mingming Gong · Jiankang Deng · Gang Niu · Masashi Sugiyama -
2020 Poster: Part-dependent Label Noise: Towards Instance-dependent Label Noise »
Xiaobo Xia · Tongliang Liu · Bo Han · Nannan Wang · Mingming Gong · Haifeng Liu · Gang Niu · Dacheng Tao · Masashi Sugiyama -
2020 Spotlight: Part-dependent Label Noise: Towards Instance-dependent Label Noise »
Xiaobo Xia · Tongliang Liu · Bo Han · Nannan Wang · Mingming Gong · Haifeng Liu · Gang Niu · Dacheng Tao · Masashi Sugiyama -
2020 Poster: Rethinking Importance Weighting for Deep Learning under Distribution Shift »
Tongtong Fang · Nan Lu · Gang Niu · Masashi Sugiyama -
2020 Poster: Learning from Aggregate Observations »
Yivan Zhang · Nontawat Charoenphakdee · Zhenguo Wu · Masashi Sugiyama -
2020 Poster: Analysis and Design of Thompson Sampling for Stochastic Partial Monitoring »
Taira Tsuchiya · Junya Honda · Masashi Sugiyama -
2020 Spotlight: Rethinking Importance Weighting for Deep Learning under Distribution Shift »
Tongtong Fang · Nan Lu · Gang Niu · Masashi Sugiyama -
2020 Poster: Provably Consistent Partial-Label Learning »
Lei Feng · Jiaqi Lv · Bo Han · Miao Xu · Gang Niu · Xin Geng · Bo An · Masashi Sugiyama -
2020 Poster: Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximators »
Takeshi Teshima · Isao Ishikawa · Koichi Tojo · Kenta Oono · Masahiro Ikeda · Masashi Sugiyama -
2020 Oral: Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximators »
Takeshi Teshima · Isao Ishikawa · Koichi Tojo · Kenta Oono · Masahiro Ikeda · Masashi Sugiyama -
2020 Poster: Domain Generalization via Entropy Regularization »
Shanshan Zhao · Mingming Gong · Tongliang Liu · Huan Fu · Dacheng Tao -
2019 : Poster Presentations »
Rahul Mehta · Andrew Lampinen · Binghong Chen · Sergio Pascual-Diaz · Jordi Grau-Moya · Aldo Faisal · Jonathan Tompson · Yiren Lu · Khimya Khetarpal · Martin Klissarov · Pierre-Luc Bacon · Doina Precup · Thanard Kurutach · Aviv Tamar · Pieter Abbeel · Jinke He · Maximilian Igl · Shimon Whiteson · Wendelin Boehmer · RaphaĆ«l Marinier · Olivier Pietquin · Karol Hausman · Sergey Levine · Chelsea Finn · Tianhe Yu · Lisa Lee · Benjamin Eysenbach · Emilio Parisotto · Eric Xing · Ruslan Salakhutdinov · Hongyu Ren · Anima Anandkumar · Deepak Pathak · Christopher Lu · Trevor Darrell · Alexei Efros · Phillip Isola · Feng Liu · Bo Han · Gang Niu · Masashi Sugiyama · Saurabh Kumar · Janith Petangoda · Johan Ferret · James McClelland · Kara Liu · Animesh Garg · Robert Lange -
2019 Poster: Curvilinear Distance Metric Learning »
Shuo Chen · Lei Luo · Jian Yang · Chen Gong · Jun Li · Heng Huang -
2019 Poster: Uncoupled Regression from Pairwise Comparison Data »
Liyuan Xu · Junya Honda · Gang Niu · Masashi Sugiyama -
2019 Poster: Control Batch Size and Learning Rate to Generalize Well: Theoretical and Empirical Evidence »
Fengxiang He · Tongliang Liu · Dacheng Tao -
2019 Poster: On the Calibration of Multiclass Classification with Rejection »
Chenri Ni · Nontawat Charoenphakdee · Junya Honda · Masashi Sugiyama -
2018 Poster: Binary Classification from Positive-Confidence Data »
Takashi Ishida · Gang Niu · Masashi Sugiyama -
2018 Spotlight: Binary Classification from Positive-Confidence Data »
Takashi Ishida · Gang Niu · Masashi Sugiyama -
2018 Poster: Uplift Modeling from Separate Labels »
Ikko Yamane · Florian Yger · Jamal Atif · Masashi Sugiyama -
2018 Poster: Continuous-time Value Function Approximation in Reproducing Kernel Hilbert Spaces »
Motoya Ohnishi · Masahiro Yukawa · Mikael Johansson · Masashi Sugiyama -
2018 Poster: Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networks »
Yusuke Tsuzuku · Issei Sato · Masashi Sugiyama -
2018 Poster: Masking: A New Perspective of Noisy Supervision »
Bo Han · Jiangchao Yao · Gang Niu · Mingyuan Zhou · Ivor Tsang · Ya Zhang · Masashi Sugiyama -
2018 Poster: Co-teaching: Robust training of deep neural networks with extremely noisy labels »
Bo Han · Quanming Yao · Xingrui Yu · Gang Niu · Miao Xu · Weihua Hu · Ivor Tsang · Masashi Sugiyama -
2017 : Poster Session (encompasses coffee break) »
Beidi Chen · Borja Balle · Daniel Lee · iuri frosio · Jitendra Malik · Jan Kautz · Ke Li · Masashi Sugiyama · Miguel A. Carreira-Perpinan · Ramin Raziperchikolaei · Theja Tulabandhula · Yung-Kyun Noh · Adams Wei Yu -
2017 Poster: Positive-Unlabeled Learning with Non-Negative Risk Estimator »
Ryuichi Kiryo · Gang Niu · Marthinus C du Plessis · Masashi Sugiyama -
2017 Poster: Learning from Complementary Labels »
Takashi Ishida · Gang Niu · Weihua Hu · Masashi Sugiyama -
2017 Oral: Positive-Unlabeled Learning with Non-Negative Risk Estimator »
Ryuichi Kiryo · Gang Niu · Marthinus C du Plessis · Masashi Sugiyama -
2017 Poster: Expectation Propagation for t-Exponential Family Using q-Algebra »
Futoshi Futami · Issei Sato · Masashi Sugiyama -
2017 Poster: Generative Local Metric Learning for Kernel Regression »
Yung-Kyun Noh · Masashi Sugiyama · Kee-Eung Kim · Frank Park · Daniel Lee -
2016 Poster: Theoretical Comparisons of Positive-Unlabeled Learning against Positive-Negative Learning »
Gang Niu · Marthinus Christoffel du Plessis · Tomoya Sakai · Yao Ma · Masashi Sugiyama -
2014 Poster: Analysis of Variational Bayesian Latent Dirichlet Allocation: Weaker Sparsity Than MAP »
Shinichi Nakajima · Issei Sato · Masashi Sugiyama · Kazuho Watanabe · Hiroko Kobayashi -
2014 Poster: Multitask learning meets tensor factorization: task imputation via convex optimization »
Kishan Wimalawarne · Masashi Sugiyama · Ryota Tomioka -
2014 Poster: Analysis of Learning from Positive and Unlabeled Data »
Marthinus C du Plessis · Gang Niu · Masashi Sugiyama -
2013 Poster: Parametric Task Learning »
Ichiro Takeuchi · Tatsuya Hongo · Masashi Sugiyama · Shinichi Nakajima -
2013 Poster: Global Solver and Its Efficient Approximation for Variational Bayesian Low-rank Subspace Clustering »
Shinichi Nakajima · Akiko Takeda · S. Derin Babacan · Masashi Sugiyama · Ichiro Takeuchi -
2012 Poster: Perfect Dimensionality Recovery by Variational Bayesian PCA »
Shinichi Nakajima · Ryota Tomioka · Masashi Sugiyama · S. Derin Babacan -
2012 Poster: Density-Difference Estimation »
Masashi Sugiyama · Takafumi Kanamori · Taiji Suzuki · Marthinus C du Plessis · Song Liu · Ichiro Takeuchi -
2011 Poster: Relative Density-Ratio Estimation for Robust Distribution Comparison »
Makoto Yamada · Taiji Suzuki · Takafumi Kanamori · Hirotaka Hachiya · Masashi Sugiyama -
2011 Poster: Target Neighbor Consistent Feature Weighting for Nearest Neighbor Classification »
Ichiro Takeuchi · Masashi Sugiyama -
2011 Poster: Analysis and Improvement of Policy Gradient Estimation »
Tingting Zhao · Hirotaka Hachiya · Gang Niu · Masashi Sugiyama -
2011 Poster: Global Solution of Fully-Observed Variational Bayesian Matrix Factorization is Column-Wise Independent »
Shinichi Nakajima · Masashi Sugiyama · S. Derin Babacan -
2010 Spotlight: Global Analytic Solution for Variational Bayesian Matrix Factorization »
Shinichi Nakajima · Masashi Sugiyama · Ryota Tomioka -
2010 Poster: Global Analytic Solution for Variational Bayesian Matrix Factorization »
Shinichi Nakajima · Masashi Sugiyama · Ryota Tomioka -
2008 Poster: Efficient Direct Density Ratio Estimation for Non-stationarity Adaptation and Outlier Detection »
Takafumi Kanamori · Shohei Hido · Masashi Sugiyama -
2007 Poster: Direct Importance Estimation with Model Selection and Its Application to Covariate Shift Adaptation »
Masashi Sugiyama · Shinichi Nakajima · Hisashi Kashima · Paul von Buenau · Motoaki Kawanabe -
2007 Poster: Multi-Task Learning via Conic Programming »
Tsuyoshi Kato · Hisashi Kashima · Masashi Sugiyama · Kiyoshi Asai -
2006 Workshop: Learning when test and training inputs have different distributions »
Joaquin QuiƱonero Candela · Masashi Sugiyama · Anton Schwaighofer · Neil D Lawrence -
2006 Poster: Mixture Regression for Covariate Shift »
Amos Storkey · Masashi Sugiyama