Early Stopping Against Label Noise Without Validation Data

International Conference on Learning Representations (ICLR), 2025

11 February 2025

Papers citing "Early Stopping Against Label Noise Without Validation Data"

50 / 74 papers shown

Title
Gradient-Weight Alignment as a Train-Time Proxy for Generalization in Classification Tasks Florian A. Hölzl Daniel Rueckert Georgios Kaissis 121 0 0 29 Oct 2025
Early-stopping for Transformer model training Jing He Hua Jiang Cheng Li Siqian Xin Shuzhen Yang 100 0 0 17 Oct 2025
Knowledge Integration for Physics-informed Symbolic Regression Using Pre-trained Large Language Models Bilge Taskin Wenxiong Xie Teddy Lazebnik AI4CE 152 1 0 03 Sep 2025
GradES: Significantly Faster Training in Transformers with Gradient-Based Early Stopping Qifu Wen Xi Zeng Zihan Zhou Shuaijun Liu M. Hosseinzadeh Ningxin Su Reza Rawassizadeh 255 0 0 01 Sep 2025
GRADSTOP: Early Stopping of Gradient Descent via Posterior Sampling Arash Jamshidi Lauri Seppäläinen Katsiaryna Haitsiukevich Hoang Phuc Hau Luu Anton Björklund Kai Puolamäki BDL 141 0 0 26 Aug 2025
LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild DataInternational Joint Conference on Artificial Intelligence (IJCAI), 2025 Chuanxing Geng Qifei Li Xinrui Wang Dong Liang Songcan Chen Pong C. Yuen 313 1 0 19 May 2025
Is Supervised Learning Really That Different from Unsupervised? Oskar Allerbo Thomas B. Schön OOD SSL 534 0 0 16 May 2025
Handling Label Noise via Instance-Level Difficulty Modeling and Dynamic Optimization Kuan Zhang Chengliang Chai Jingzhe Xu Fangqiu Yi Ye Yuan Guoren Wang Lei Cao Lei Cao NoLa 687 1 0 01 May 2025
crowd-hpo: Realistic Hyperparameter Optimization and Benchmarking for Learning from Crowds with Noisy Labels M. Herde Lukas Lührs Denis Huseljic Bernhard Sick 360 0 0 12 Apr 2025
Robust Classification with Noisy Labels Based on Posterior Maximization Nicola Novello Andrea M. Tonello NoLa 257 2 0 09 Apr 2025
Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair SelectionIEEE Transactions on Image Processing (TIP), 2024 Zhipeng Yu Qianqian Xu Yangbangyan Jiang Yingfei Sun Qingming Huang NoLa 306 2 0 19 Jan 2025
NoisyEQA: Benchmarking Embodied Question Answering Against Noisy Queries Tao Wu Chuhao Zhou Yen Heng Wong Lin Gu Jianfei Yang 274 6 0 14 Dec 2024
Noisy Ostracods: A Fine-Grained, Imbalanced Real-World Dataset for Benchmarking Robust Machine Learning and Label Correction MethodsNeural Information Processing Systems (NeurIPS), 2024 Jiamian Hu Yuanyuan Hong Yihua Chen He Wang Moriaki Yasuhara 317 2 0 03 Dec 2024
dopanim: A Dataset of Doppelganger Animals with Noisy Annotations from Multiple Humans M. Herde Denis Huseljic Lukas Rauch Bernhard Sick 294 3 0 30 Jul 2024
Annot-Mix: Learning with Noisy Class Labels from Multiple Annotators via a Mixup ExtensionEuropean Conference on Artificial Intelligence (ECAI), 2024 M. Herde Lukas Lührs Denis Huseljic Bernhard Sick 332 3 0 06 May 2024
A Layer Selection Approach to Test Time AdaptationAAAI Conference on Artificial Intelligence (AAAI), 2024 Sabyasachi Sahoo Mostafa ElAraby Jonas Ngnawé Y. Pequignot Frédéric Precioso Christian Gagné 230 0 0 04 Apr 2024
Mitigating Label Noise on Graph via Topological Sample Selection Yuhao Wu Jiangchao Yao Xiaobo Xia Jun-chen Yu Ruxing Wang Bo Han Tongliang Liu NoLa 276 6 0 04 Mar 2024
Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context Learning Zhuo Huang Chang Liu Yinpeng Dong Hang Su Shibao Zheng Tongliang Liu VLM MLLM 207 18 0 05 Dec 2023
Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models Zhaowei Zhu Jialu Wang Hao Cheng Yang Liu 259 26 0 19 Nov 2023
On the Over-Memorization During Natural, Robust and Catastrophic OverfittingInternational Conference on Learning Representations (ICLR), 2023 Runqi Lin Chaojian Yu Bo Han Tongliang Liu 227 16 0 13 Oct 2023
Regularly Truncated M-estimators for Learning with Noisy LabelsIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023 Xiaobo Xia Pengqian Lu Chen Gong Bo Han Jun-chen Yu Jun Yu Tongliang Liu NoLa 188 14 0 02 Sep 2023
Late Stopping: Avoiding Confidently Learning from Mislabeled ExamplesIEEE International Conference on Computer Vision (ICCV), 2023 Suqin Yuan Lei Feng Tongliang Liu NoLa 223 16 0 26 Aug 2023
Improve Noise Tolerance of Robust Loss via Noise-AwarenessIEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2023 Kehui Ding Jun Shu Deyu Meng Zongben Xu NoLa 255 7 0 18 Jan 2023
Progress measures for grokking via mechanistic interpretabilityInternational Conference on Learning Representations (ICLR), 2023 Neel Nanda Lawrence Chan Tom Lieberum Jess Smith Jacob Steinhardt 458 621 0 12 Jan 2023
Leveraging Unlabeled Data to Track MemorizationInternational Conference on Learning Representations (ICLR), 2022 Mahsa Forouzesh Hanie Sedghi Patrick Thiran NoLa TDI 203 4 0 08 Dec 2022
Characterizing Datapoints via Second-Split ForgettingNeural Information Processing Systems (NeurIPS), 2022 Pratyush Maini Saurabh Garg Zachary Chase Lipton J. Zico Kolter 204 38 0 26 Oct 2022
Self-Filtering: A Noise-Aware Sample Selection for Label Noise with Confidence PenalizationEuropean Conference on Computer Vision (ECCV), 2022 Qinglai Wei Haoliang Sun Xiankai Lu Yilong Yin NoLa 179 55 0 24 Aug 2022
Towards Understanding Grokking: An Effective Theory of Representation LearningNeural Information Processing Systems (NeurIPS), 2022 Ziming Liu O. Kitouni Niklas Nolte Eric J. Michaud Max Tegmark Mike Williams AI4CE 278 205 0 20 May 2022
SELC: Self-Ensemble Label Correction Improves Learning with Noisy LabelsInternational Joint Conference on Artificial Intelligence (IJCAI), 2022 Yangdi Lu Wenbo He NoLa 209 46 0 02 May 2022
Robust Training under Label Noise by Over-parameterizationInternational Conference on Machine Learning (ICML), 2022 Sheng Liu Zhihui Zhu Qing Qu Chong You NoLa OOD 249 133 0 28 Feb 2022
Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets Alethea Power Yuri Burda Harrison Edwards Igor Babuschkin Vedant Misra 332 480 0 06 Jan 2022
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 339 308 0 22 Oct 2021
Understanding and Improving Early Stopping for Learning with Noisy LabelsNeural Information Processing Systems (NeurIPS), 2021 Ying-Long Bai Erkun Yang Bo Han Yanhua Yang Jiatong Li Yinian Mao Gang Niu Tongliang Liu NoLa 204 265 0 30 Jun 2021
To Smooth or Not? When Label Smoothing Meets Noisy LabelsInternational Conference on Machine Learning (ICML), 2021 Jiaheng Wei Hangyu Liu Tongliang Liu Gang Niu Masashi Sugiyama Yang Liu NoLa 612 99 0 08 Jun 2021
RATT: Leveraging Unlabeled Data to Guarantee GeneralizationInternational Conference on Machine Learning (ICML), 2021 Saurabh Garg Sivaraman Balakrishnan J. Zico Kolter Zachary Chase Lipton 232 30 0 01 May 2021
Robust Learning by Self-Transition for Handling Noisy Labels Hwanjun Song Minseok Kim Dongmin Park Yooju Shin Jae-Gil Lee NoLa 271 44 0 08 Dec 2020
Robustness of Accuracy Metric and its Inspirations in Learning with Noisy Labels Pengfei Chen Junjie Ye Guangyong Chen Jingwei Zhao Pheng-Ann Heng NoLa 280 37 0 08 Dec 2020
A Survey of Label-noise Representation Learning: Past, Present and Future Bo Han Quanming Yao Tongliang Liu Gang Niu Ivor W. Tsang James T. Kwok Masashi Sugiyama NoLa 329 180 0 09 Nov 2020
A Bayesian Perspective on Training Speed and Model SelectionNeural Information Processing Systems (NeurIPS), 2020 Clare Lyle Lisa Schut Binxin Ru Y. Gal Mark van der Wilk 184 25 0 27 Oct 2020
Learning with Instance-Dependent Label Noise: A Sample Sieve ApproachInternational Conference on Learning Representations (ICLR), 2020 Hao Cheng Zhaowei Zhu Xingyu Li Yifei Gong Xing Sun Yang Liu NoLa 253 236 0 05 Oct 2020
What Neural Networks Memorize and Why: Discovering the Long Tail via Influence EstimationNeural Information Processing Systems (NeurIPS), 2020 Vitaly Feldman Chiyuan Zhang TDI 518 561 0 09 Aug 2020
Learning from Noisy Labels with Deep Neural Networks: A SurveyIEEE Transactions on Neural Networks and Learning Systems (IEEE TNNLS), 2020 Hwanjun Song Minseok Kim Dongmin Park Yooju Shin Jae-Gil Lee NoLa 1.1K 1,196 0 16 Jul 2020
Are Labels Always Necessary for Classifier Accuracy Evaluation? Weijian Deng Liang Zheng 294 131 0 06 Jul 2020
Early-Learning Regularization Prevents Memorization of Noisy Labels Sheng Liu Jonathan Niles-Weed N. Razavian C. Fernandez‐Granda NoLa 441 668 0 30 Jun 2020
Speedy Performance Estimation for Neural Architecture Search Binxin Ru Clare Lyle Lisa Schut M. Fil Mark van der Wilk Y. Gal 324 41 0 08 Jun 2020
Computing the Testing Error without a Testing SetComputer Vision and Pattern Recognition (CVPR), 2020 C. Corneanu Meysam Madadi Sergio Escalera Aleix M. Martinez AAML 202 76 0 01 May 2020
Deep Double Descent: Where Bigger Models and More Data HurtInternational Conference on Learning Representations (ICLR), 2019 Preetum Nakkiran Gal Kaplun Yamini Bansal Tristan Yang Boaz Barak Ilya Sutskever 362 1,051 0 04 Dec 2019
Fantastic Generalization Measures and Where to Find ThemInternational Conference on Learning Representations (ICLR), 2019 Yiding Jiang Behnam Neyshabur H. Mobahi Dilip Krishnan Samy Bengio AI4CE 407 667 0 04 Dec 2019
How does Early Stopping Help Generalization against Label Noise? Hwanjun Song Minseok Kim Dongmin Park Jae-Gil Lee NoLa 404 82 0 19 Nov 2019
Benign Overfitting in Linear RegressionProceedings of the National Academy of Sciences of the United States of America (PNAS), 2019 Peter L. Bartlett Philip M. Long Gábor Lugosi Alexander Tsigler MLT 397 853 0 26 Jun 2019