1
Anti-causal domain generalization: Leveraging unlabeled data
反因果视角突破域泛化瓶颈，巧用未标注数据提升模型泛化能力，ICML 2026前沿研究
arXiv:2602.17187v2 Announce Type: replace-cross Abstract: The problem of domain generalization concerns learning predictive models that are robust to …