Saved in:
Bibliographic Details
Main Authors: Dai, Zilin, Wang, Lehong, Lin, Fangzhou, Wang, Yidong, Li, Zhigang, Yamada, Kazunori D, Zhang, Ziming, Lu, Wang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.17211
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908328047673344
author Dai, Zilin
Wang, Lehong
Lin, Fangzhou
Wang, Yidong
Li, Zhigang
Yamada, Kazunori D
Zhang, Ziming
Lu, Wang
author_facet Dai, Zilin
Wang, Lehong
Lin, Fangzhou
Wang, Yidong
Li, Zhigang
Yamada, Kazunori D
Zhang, Ziming
Lu, Wang
contents Real-world machine learning applications often struggle with two major challenges: distribution shift and label noise. Models tend to overfit by focusing on redundant and uninformative features in the training data, which makes it hard for them to generalize to the target domain. Noisy data worsens this problem by causing further overfitting to the noise, meaning that existing methods often fail to tell the difference between true, invariant features and misleading, spurious ones. To tackle these issues, we introduce Anchor Alignment and Adaptive Weighting (A3W). This new algorithm uses sample reweighting guided by natural language processing (NLP) anchors to extract more representative features. In simple terms, A3W leverages semantic representations from natural language models as a source of domain-invariant prior knowledge. Additionally, it employs a weighted loss function that adjusts each sample's contribution based on its similarity to the corresponding NLP anchor. This adjustment makes the model more robust to noisy labels. Extensive experiments on standard benchmark datasets show that A3W consistently outperforms state-of-the-art domain generalization methods, offering significant improvements in both accuracy and robustness across different datasets and noise levels.
format Preprint
id arxiv_https___arxiv_org_abs_2503_17211
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Language Anchor-Guided Method for Robust Noisy Domain Generalization
Dai, Zilin
Wang, Lehong
Lin, Fangzhou
Wang, Yidong
Li, Zhigang
Yamada, Kazunori D
Zhang, Ziming
Lu, Wang
Computation and Language
Computer Vision and Pattern Recognition
Machine Learning
Real-world machine learning applications often struggle with two major challenges: distribution shift and label noise. Models tend to overfit by focusing on redundant and uninformative features in the training data, which makes it hard for them to generalize to the target domain. Noisy data worsens this problem by causing further overfitting to the noise, meaning that existing methods often fail to tell the difference between true, invariant features and misleading, spurious ones. To tackle these issues, we introduce Anchor Alignment and Adaptive Weighting (A3W). This new algorithm uses sample reweighting guided by natural language processing (NLP) anchors to extract more representative features. In simple terms, A3W leverages semantic representations from natural language models as a source of domain-invariant prior knowledge. Additionally, it employs a weighted loss function that adjusts each sample's contribution based on its similarity to the corresponding NLP anchor. This adjustment makes the model more robust to noisy labels. Extensive experiments on standard benchmark datasets show that A3W consistently outperforms state-of-the-art domain generalization methods, offering significant improvements in both accuracy and robustness across different datasets and noise levels.
title A Language Anchor-Guided Method for Robust Noisy Domain Generalization
topic Computation and Language
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2503.17211