v1v2v3v4 (latest)

The Rich Get Richer: Disparate Impact of Semi-Supervised Learning

International Conference on Learning Representations (ICLR), 2021

12 October 2021

Zhaowei Zhu

Tianyi Luo

Yang Liu

ArXiv (abs)PDF HTML

Papers citing "The Rich Get Richer: Disparate Impact of Semi-Supervised Learning"

27 / 27 papers shown

Title
Adaptive Bounded Exploration and Intermediate Actions for Data DebiasingINFORMS journal on computing (IJOC), 2025 Yifan Yang Yang Liu Parinaz Naghizadeh 213 1 0 10 Apr 2025
Noise-Resilient Point-wise Anomaly Detection in Time Series Using Weak Segment LabelsKnowledge Discovery and Data Mining (KDD), 2025 Yaxuan Wang Hao Cheng Jing Xiong Qingsong Wen Han Jia Ruixuan Song Li Zhang Zhaowei Zhu Yang Liu AI4TS 196 3 0 21 Jan 2025
Fairness Without Harm: An Influence-Guided Active Sampling Approach Jinlong Pang Jialu Wang Zhaowei Zhu Yuanshun Yao Chen Qian Yang Liu TDI 171 8 0 20 Feb 2024
Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models Zhaowei Zhu Jialu Wang Hao Cheng Yang Liu 191 26 0 19 Nov 2023
Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and ToolsConference on Equity and Access in Algorithms, Mechanisms, and Optimization (EAAMO), 2023 Maximilian Schambach Rakshit Naidu Rayid Ghani Kit T. Rodolfa Daniel E. Ho Hoda Heidari FaML 201 21 0 29 Sep 2023
STRAPPER: Preference-based Reinforcement Learning via Self-training Augmentation and Peer Regularization Yachen Kang Li He Jinxin Liu Zifeng Zhuang Xuetao Zhang 252 1 0 19 Jul 2023
On the Cause of Unfairness: A Training Sample Perspective Yuanshun Yao Yang Liu TDI 194 0 0 30 Jun 2023
The Importance of Human-Labeled Data in the Era of LLMsInternational Joint Conference on Artificial Intelligence (IJCAI), 2023 Yang Liu ALM 152 11 0 18 Jun 2023
Enhancing CLIP with CLIP: Exploring Pseudolabeling for Limited-Label Prompt TuningNeural Information Processing Systems (NeurIPS), 2023 Cristina Menghini Andrew T. Delworth Stephen H. Bach VLM 342 32 0 02 Jun 2023
T2IAT: Measuring Valence and Stereotypical Biases in Text-to-Image GenerationAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 Jialu Wang Xinyue Liu Zonglin Di Yongxu Liu Xin Eric Wang 152 45 0 01 Jun 2023
Fairness Improves Learning from Noisily Labeled Long-Tailed Data Jiaheng Wei Zhaowei Zhu Gang Niu Tongliang Liu Sijia Liu Masashi Sugiyama Yang Liu 126 9 0 22 Mar 2023
On Comparing Fair Classifiers under Data Bias Mohit Sharma Amit Deshpande R. Shah 242 2 0 12 Feb 2023
Weak Proxies are Sufficient and Preferable for Fairness with Missing Sensitive AttributesInternational Conference on Machine Learning (ICML), 2022 Zhaowei Zhu Yuanshun Yao Jiankai Sun Hanguang Li Zehua Wang 219 27 0 06 Oct 2022
Data Feedback Loops: Model-driven Amplification of Dataset BiasesInternational Conference on Machine Learning (ICML), 2022 Rohan Taori Tatsunori B. Hashimoto 268 58 0 08 Sep 2022
Teacher Guided Training: An Efficient Framework for Knowledge TransferInternational Conference on Learning Representations (ICLR), 2022 Manzil Zaheer A. S. Rawat Seungyeon Kim Chong You Himanshu Jain Andreas Veit Rob Fergus Surinder Kumar VLM 127 1 0 14 Aug 2022
Understanding Instance-Level Impact of Fairness ConstraintsInternational Conference on Machine Learning (ICML), 2022 Jialu Wang Xinze Wang Yang Liu TDI FaML 186 40 0 30 Jun 2022
Transferring Fairness under Distribution Shifts via Fair Consistency RegularizationNeural Information Processing Systems (NeurIPS), 2022 Bang An Zora Che Mucong Ding Furong Huang 185 36 0 26 Jun 2022
Input-agnostic Certified Group Fairness via Gaussian Parameter SmoothingInternational Conference on Machine Learning (ICML), 2022 Jiayin Jin Zeru Zhang Yang Zhou Lingfei Wu 160 15 0 22 Jun 2022
To Aggregate or Not? Learning with Separate Noisy Labels Jiaheng Wei Zhaowei Zhu Tianyi Luo Ehsan Amid Abhishek Kumar Yang Liu NoLa 122 45 0 14 Jun 2022
Pruning has a disparate impact on model accuracyNeural Information Processing Systems (NeurIPS), 2022 Cuong Tran Ferdinando Fioretto Jung-Eun Kim Rakshit Naidu 197 45 0 26 May 2022
Don't Throw it Away! The Utility of Unlabeled Data in Fair Decision MakingConference on Fairness, Accountability and Transparency (FAccT), 2022 Miriam Rateike Ayan Majumdar Olga Mineeva Krishna P. Gummadi Isabel Valera OffRL 240 13 0 10 May 2022
Don't fear the unlabelled: safe semi-supervised learning via simple debiasingInternational Conference on Learning Representations (ICLR), 2022 Hugo Schmutz O. Humbert Pierre-Alexandre Mattei 221 11 0 14 Mar 2022
Beyond Images: Label Noise Transition Matrix Estimation for Tasks with Lower-Quality FeaturesInternational Conference on Machine Learning (ICML), 2022 Zhaowei Zhu Jialu Wang Yang Liu NoLa 188 40 0 02 Feb 2022
Adaptive Data Debiasing through Bounded ExplorationNeural Information Processing Systems (NeurIPS), 2021 Yifan Yang Yang Liu Parinaz Naghizadeh FaML 140 9 0 25 Oct 2021
Learning with Noisy Labels Revisited: A Study Using Real-World Human AnnotationsInternational Conference on Learning Representations (ICLR), 2021 Jiaheng Wei Zhaowei Zhu Weiran Wang Tongliang Liu Gang Niu Yang Liu NoLa 271 301 0 22 Oct 2021
Detecting Corrupted Labels Without Training a Model to PredictInternational Conference on Machine Learning (ICML), 2021 Zhaowei Zhu Zihao Dong Yang Liu NoLa 366 79 0 12 Oct 2021
Assessing Multilingual Fairness in Pre-trained Multimodal RepresentationsFindings (Findings), 2021 Jialu Wang Yang Liu Xinze Wang EGVM 177 41 0 12 Jun 2021