Importance Tempering: Group Robustness for Overparameterized Models
원문 초록
Although overparameterized models have shown their success on many machine learning tasks, the accuracy could drop on the testing distribution that is different from the training one. This accuracy drop still limits applying machine learning in the wild. At the same time, importance weighting, a traditional technique to handle distribution shifts, has been demonstrated to have less or even no effect on overparameterized models both empirically and theoretically. In this paper, we propose importance tempering to improve the decision boundary and achieve consistently better results for overparameterized models. Theoretically, we justify that the selection of group temperature can be different under label shift and spurious correlation setting. At the same time, we also prove that properly selected temperatures can extricate the minority collapse for imbalanced classification. Empirically, we achieve state-of-the-art results on worst group classification tasks using importance tempering.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
LSH-DynED: A Dynamic Ensemble Framework with LSH-Based Undersampling for Evolving Multi-Class Imbalanced Classification
A statistical theory of overfitting for imbalanced classification
A Mathematics Framework of Artificial Shifted Population Risk and Its Further Understanding Related to Consistency Regularization
Synthetic Tabular Data Generation for Imbalanced Classification: The Surprising Effectiveness of an Overlap Class
GAT-RWOS: Graph Attention-Guided Random Walk Oversampling for Imbalanced Data Classification
Dist Loss: Enhancing Regression in Few-Shot Region through Distribution Distance Constraint
토론
이 논문과 연결된 포럼 글이 아직 없습니다.