Domain Generalization via Selective Consistency Regularization for Time Series Classification. (arXiv:2206.07876v1 [cs.LG])

Web: http://arxiv.org/abs/2206.07876

Domain generalization methods aim to learn models robust to domain shift with
data from a limited number of source domains and without access to target
domain samples during training. Popular domain alignment methods for domain
generalization seek to extract domain-invariant features by minimizing the
discrepancy between feature distributions across all domains, disregarding
inter-domain relationships. In this paper, we instead propose a novel
representation learning methodology that selectively enforces prediction
consistency between source domains estimated to be closely-related.
Specifically, we hypothesize …

arxiv classification lg regularization time time series