Supercharging Imbalanced Data Learning With Energy-based Contrastive Representation Transfer.

ABSTRACT: Dealing with severe class imbalance poses a major challenge for many real-world applications, especially when the accurate classification and generalization of minority classes are of primary interest. In computer vision and NLP, learning from datasets with long-tail behavior is a recurring theme, especially for naturally occurring labels. Existing solutions mostly appeal to sampling or weighting adjustments to alleviate the extreme imbalance, or impose inductive bias to prioritize generalizable associations. Here we take a novel perspective to promote sample efficiency and model generalization based on the invariance principles of causality. Our contribution posits a meta-distributional scenario, where the causal generating mechanism for label-conditional features is invariant across diff

SUBMITTER: Chen J 

PROVIDER: S-EPMC9555007 | biostudies-literature | 2021 Dec

REPOSITORIES: biostudies-literature