Transferable Time-Series Forecasting under Causal Conditional Shift. (arXiv:2111.03422v2 [cs.LG] UPDATED)

This paper focuses on the problem of semi-supervised domain adaptation for
time-series forecasting, which is underexplored in literatures, despite being
often encountered in practice. Existing methods on time-series domain
adaptation mainly follow the paradigm designed for the static data, which
cannot handle domain-specific complex conditional dependencies raised by data
offset, time lags, and variant data distributions. In order to address these
challenges, we analyze variational conditional dependencies in time-series data
and find that the causal structures are usually stable among …

arxiv forecasting time