paper-with-me

홈 › Papers

Learning with Noisy Labels over Imbalanced Subpopulations

2022-11-16 · Mingcai Chen, Yu Zhao, Bing He, Zongbo Han, Bingzhe Wu, Jianhua Yao

Learning with Noisy Labels (LNL) has attracted significant attention from the research community. Many recent LNL methods rely on the assumption that clean samples tend to have "small loss". However, this assumption always fails to generalize to some real-world cases with imbalanced subpopulations, i.e., training subpopulations varying in sample size or recognition difficulty. Therefore, recent LNL methods face the risk of misclassifying those "informative" samples (e.g., hard samples or samples in the tail subpopulations) into noisy samples, leading to poor generalization performance. To address the above issue, we propose a novel LNL method to simultaneously deal with noisy labels and imbalanced subpopulations. It first leverages sample correlation to estimate samples' clean probabilities for label correction and then utilizes corrected labels for Distributionally Robust Optimization (DRO) to further improve the robustness. Specifically, in contrast to previous works using classification loss as the selection criterion, we introduce a feature-based metric that takes the sample correlation into account for estimating samples' clean probabilities. Then, we refurbish the noisy labels using the estimated clean probabilities and the pseudo-labels from the model's predictions. With refurbished labels, we use DRO to train the model to be robust to subpopulation imbalance. Extensive experiments on a wide range of benchmarks demonstrate that our technique can consistently improve current state-of-the-art robust learning paradigms against noisy labels, especially when encountering imbalanced subpopulations.

📄 PDF Abstract BibTeX arXiv:2211.08722

Code (0)

등록된 구현이 없습니다.

Tasks

Learning with noisy labels

Similar Papers 제목 키워드 기반

Learning with Imbalanced Noisy Data by Preventing Bias in Sample Selection

2024-02-17 · Huafeng Liu, Mengmeng Sheng, Zeren Sun, Yazhou Yao 외

Learning with noisy labels has gained increasing attention because the inevitable imperfect labels in real-world scenarios can substantially hurt the deep model performance. Recent studies tend to regard low-loss samples…

Learning with noisy labels

When Noisy Labels Meet Class Imbalance on Graphs: A Graph Augmentation Method with LLM and Pseudo Label

2025-07-24 · Riting Xia, Rucong Wang, Yulin Liu, Anchen Li 외 arxiv

Class-imbalanced graph node classification is a practical yet underexplored research problem. Although recent studies have attempted to address this issue, they typically assume clean and reliable labels when processing …

Node Classification

Active Label Refinement for Robust Training of Imbalanced Medical Image Classification Tasks in the Presence of High Label Noise

2024-07-08 · Bidur Khanal, Tianhong Dai, Binod Bhattarai, Cristian Linte

The robustness of supervised deep learning-based medical image classification is significantly undermined by label noise. Although several methods have been proposed to enhance classification performance in the presence …

Active LearningClassificationimage-classificationImage Classification+2

Correcting Performance Estimation Bias in Imbalanced Classification with Minority Subconcepts

2026-04-28 · Taylor Maxson, Roberto Corizzo, Yaning Wu, Nathalie Japkowicz 외 arxiv

Class-level evaluation can conceal substantial performance disparities across subconcepts within the same class, causing models that perform well on average to fail on specific subpopulations. Prior work has shown that c…

Incomplete Multi-View Weak-Label Learning with Noisy Features and Imbalanced Labels

2022-01-04 · Zhiwei Li, Zijian Yang, Lu Sun, Mineichi Kudo 외

A variety of modern applications exhibit multi-view multi-label learning, where each sample has multi-view features, and multiple labels are correlated via common views. Current methods usually fail to directly deal with…

Multi-Label Learning