← Search

Cun-Yuan Xing

1 accepted papers

2025

One-Pass Feature Evolvable Learning with Theoretical Guarantees

ICML 2025poster

Feature evolvable learning studies the scenario where old features will vanish and new features will emerge when learning with data streams, and various methods have been developed by utilizing some useful relationships from old features to new features, rather than re-training from scratch. In this…

Cited by 0SourcePDFScholar