Invariant Feature Learning Based on Causal Inference from Heterogeneous Environments

Causality has become a powerful tool for addressing the out-of-distribution (OOD) generalization problem, with the idea of invariant causal features across domains of interest. Most existing methods for learning invariant features are based on optimization, which typically fails to converge to the o...

Popoln opis

Bibliografske podrobnosti

Principais autores:	Hang Su, Wei Wang
Format:	Artigo
Jezik:	Inglês
Izdano:	MDPI AG 2024-02-01
Serija:	Mathematics
Teme:	invariant feature learning causal representation learning out-of-distribution generalization causal inference
Online dostop:	https://www.mdpi.com/2227-7390/12/5/696
Oznake:	Označite Brez oznak, prvi označite!