Zhenbo Li

CIGR: Causal Invariant Representation Learning Framework With Global Redundancy Information for Open-Set Multi-Target Domain Adaptation.

A Causal-Invariant representation learning framework with Global Redundancy information (CIGR) for OSMTDA, and a graph-based multi-domain causal invariance learning (MCIL) module that generates virtual unknown features from redundant factors, enabling causally invariant representations for known and unknown classes.