paper-with-me

홈 › Papers

Cross-Domain Empirical Risk Minimization for Unbiased Long-tailed Classification

2021-12-29 · Beier Zhu, Yulei Niu, Xian-Sheng Hua, Hanwang Zhang

We address the overlooked unbiasedness in existing long-tailed classification methods: we find that their overall improvement is mostly attributed to the biased preference of tail over head, as the test distribution is assumed to be balanced; however, when the test is as imbalanced as the long-tailed training data -- let the test respect Zipf's law of nature -- the tail bias is no longer beneficial overall because it hurts the head majorities. In this paper, we propose Cross-Domain Empirical Risk Minimization (xERM) for training an unbiased model to achieve strong performances on both test distributions, which empirically demonstrates that xERM fundamentally improves the classification by learning better feature representation rather than the head vs. tail game. Based on causality, we further theoretically explain why xERM achieves unbiasedness: the bias caused by the domain selection is removed by adjusting the empirical risks on the imbalanced domain and the balanced but unseen domain. Codes are available at https://github.com/BeierZhu/xERM.

📄 PDF Abstract BibTeX arXiv:2112.14380

Code (1)

beierzhu/xerm 공식 구현 pytorch

Tasks

Classification

Similar Papers 제목 키워드 기반

Classification from Pairwise Similarities/Dissimilarities and Unlabeled Data via Empirical Risk Minimization

2019-04-26 · Takuya Shimada, Han Bao, Issei Sato, Masashi Sugiyama

Pairwise similarities and dissimilarities between data points might be easier to obtain than fully labeled data in real-world classification problems, e.g., in privacy-aware situations. To handle such pairwise informatio…

ClusteringGeneral Classification

Unbiased Risk Estimators Can Mislead: A Case Study of Learning with Complementary Labels

2020-07-05 · ICML 2020 1 · Yu-Ting Chou, Gang Niu, Hsuan-Tien Lin, Masashi Sugiyama

In weakly supervised learning, unbiased risk estimator(URE) is a powerful tool for training classifiers when training and test data are drawn from different distributions. Nevertheless, UREs lead to overfitting in many p…

Weakly-supervised Learning

Empirical Risk Minimization and Stochastic Gradient Descent for Relational Data

2018-06-27 · Victor Veitch, Morgane Austern, Wenda Zhou, David M. Blei 외

Empirical risk minimization is the main tool for prediction problems, but its extension to relational data remains unsolved. We solve this problem using recent ideas from graph sampling theory to (i) define an empirical …

Graph SamplingNode Classification

Cost-Sensitive Unbiased Risk Estimation for Multi-Class Positive-Unlabeled Learning

2025-10-29 · Miao Zhang, Junpeng Li, Changchun Hua, Yana Yang arxiv

Positive--Unlabeled (PU) learning considers settings in which only positive and unlabeled data are available, while negatives are missing or left unlabeled. This situation is common in real applications where annotating …

Cross-Audit Projection for Model Risk Prediction

2026-07-02 · Yijian Huang arxiv

For training-data-based model risk prediction, $K$-fold cross-validation~(CV) is widely used to mitigate the well-known over-optimism of the empirical risk and is often regarded as reliable. However, for binary classific…

Breast Cancer DetectionBinary Classification