• Home
  • Search
  • Optimized Gradient Clipping for Noisy Label Learning
  • Cite Icon4
  • https://doi.org/10.1609/aaai.v39i9.33025Copy DOI Icon

Optimized Gradient Clipping for Noisy Label Learning

  • Abstract
  • Literature Map
  • Citations
  • Similar Papers
Abstract

Previous research has shown that constraining the gradient of loss function w.r.t. model-predicted probabilities can enhance the model robustness against noisy labels. These methods typically specify a fixed optimal threshold for gradient clipping through validation data to obtain the desired robustness against noise. However, this common practice overlooks the dynamic distribution of gradients from both clean and noisy-labeled samples at different stages of training, significantly limiting the model capability to adapt to the variable nature of gradients throughout the training process. To address this issue, we propose a simple yet effective approach called Optimized Gradient Clipping (OGC), which dynamically adjusts the clipping threshold based on the ratio of noise gradients to clean gradients after clipping, estimated by modeling the distributions of clean and noisy samples. This approach allows us to modify the clipping threshold at each training step, effectively controlling the influence of noise gradients. Additionally, we provide statistical analysis to certify the noise-tolerance ability of OGC. Our extensive experiments across various types of label noise, including symmetric, asymmetric, instance-dependent, and real-world noise, demonstrate the effectiveness of our approach.

Similar Papers
  • Research Article

Мотивация достижения успеха у каратистов на разных этапах подготовки

  • Jan 29, 2026
  • Scientific notes of P. F. Lesgaft University
  • Tatiana Stebliy +3
  • Research Article
  • Citations70

Robust Medical Image Classification From Noisy Labeled Data With Global and Local Representation Guided Co-Training.

  • Jun 01, 2022
  • IEEE Transactions on Medical Imaging
  • Cheng Xue +4
  • Research Article
  • Citations1

ПCИХОЛОГИЧЕСКИЕ ОСОБЕННОСТИ СИНДРОМА ЭМОЦИОНАЛЬНОГО ВЫГОРАНИЯ У СТУДЕНТОВ МЕДИЦИНСКИХ ВУЗОВ

  • Dec 31, 2021
  • PERSONALITY IN A CHANGING WORLD: HEALTH, ADAPTATION, DEVELOPMENT
  • I.L Gureeva +3
  • Research Article

FedEBM: Robust graph federated learning via energy-based model.

  • May 28, 2026
  • Neural networks : the official journal of the International Neural Network Society
  • Jiayu Wang +4
  • Research Article
  • Citations10

TBC-MI : Suppressing noise labels by maximizing cleaning samples for robust image classification

  • Jun 12, 2024
  • Information Processing and Management
  • Yanhong Li +3
  • PDF
  • Research Article
  • Citations9

Deep Learning Network Intensification for Preventing Noisy-Labeled Samples for Remote Sensing Classification

  • Apr 27, 2021
  • Remote Sensing
  • Chuang Lin +6
  • Research Article

Feature Space-Preserving Machine Unlearning for Robust Image Classification with Noisy Labels

  • Jan 01, 2026
  • IEEE Access
  • Shohei Yamamoto +2
  • Conference Article
  • Citations1

Distribution Mining and Noise Correction for Facial Expression Recognition

  • Apr 19, 2024
  • Hailan Huang +1
  • PDF
  • Research Article
  • Citations1

An Improved Heteroscedastic Modeling Method for Chest X-ray Image Classification with Noisy Labels

  • May 04, 2023
  • Algorithms
  • Qingji Guan +2
  • Research Article
  • Citations65

Problems and Strategies in Consecutive Interpreting: A Pilot Study at Two Different Stages of Interpreter Training

  • Jul 08, 2013
  • Meta
  • Marta Arumí Ribas
  • Research Article
  • Citations4

Meta-probability Weighting for Improving Reliability of DNNs to Label Noise.

  • Apr 01, 2023
  • IEEE journal of biomedical and health informatics
  • Zhen Wang +4
  • Conference Article

Screening, Rectifying, and Re-Screening: A Unified Framework for Tuning Vision-Language Models with Noisy Labels

  • Sep 01, 2025
  • Chaowei Fang +5
  • Conference Article
  • Citations33

ProMix: Combating Label Noise via Maximizing Clean Sample Utility

  • Aug 01, 2023
  • Ruixuan Xiao +6
  • Research Article
  • Citations4

Agree to Disagree: Robust Anomaly Detection with Noisy Labels

  • Feb 10, 2025
  • Proceedings of the ACM on Management of Data
  • Dennis M Hofmann +6
  • PDF
  • Research Article
  • Citations3

Separating hard clean samples from noisy samples with samples’ learning risk for DNN when learning with noisy labels

  • Mar 01, 2024
  • Complex & Intelligent Systems
  • Lihui Deng +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.