A Unified Causal View of Domain Invariant Representation Learning. (arXiv:2208.06987v2 [stat.ML] UPDATED)

Machine learning methods can be unreliable when deployed in domains that
differ from the domains on which they were trained. To address this, we may
wish to learn representations of data that are domain-invariant in the sense
that we preserve data structure that is stable across domains, but throw out
spuriously-varying parts. There are many representation-learning approaches of
this type, including methods based on data augmentation, distributional
invariances, and risk invariance. Unfortunately, when faced with any particular
real-world domain shift, …

arxiv learning ml representation representation learning