상세 보기
Improving Worst-Group Accuracy with a Filtering-Based Method
- Kim, Mingi;
- Ryu, Jongwon;
- Kim, Junyeong
WEB OF SCIENCE
0SCOPUS
0초록
Spurious correlations in training data often cause models to underperform on minority groups. Existing methods that improve worst-group accuracy (WGA) typically rely on group annotations, complex optimization objectives or multi-stage pipelines, limiting their practical application.We make a key observation: robust classifiers utilize a sparse set of features, suggesting they selectively focus on core, task-essential features. Based on this insight, we propose a single-stage, annotation-free method that co-trains a learnable binary mask to structurally filter input features. End-to-end training is enabled via a Straight-Through Estimator (STE) and a Gradient Adjustment technique, with the mask learned solely from the main task loss. While many de-biasing methods improve WGA, they often overlook the critical trade-off with overall accuracy. We therefore propose a novel Trade-off Ratio (ToR) metric, which quantifies the efficiency of WGA gains relative to any loss in overall accuracy. On four benchmarks (Waterbirds, CelebA, CivilComments, MultiNLI), our method achieves state-of-the-art WGA on CivilComments of 81.9% on CivilComments and the highest ToR score of 12.8 on Waterbirds.
키워드
- 제목
- Improving Worst-Group Accuracy with a Filtering-Based Method
- 저자
- Kim, Mingi; Ryu, Jongwon; Kim, Junyeong
- 발행일
- 2025
- 유형
- Article
- 저널명
- IEEE Access
- 권
- 13
- 페이지
- 214201 ~ 214210
- 언어
- ENG
- 출판사
- Institute of Electrical and Electronics Engineers Inc.
- 발행국가
- 미국
- 분량
- 10 페이지
- ISSN
- E 2169-3536
P 2169-3536