Skip to yearly menu bar Skip to main content


Domain Adaptation with Asymmetrically-Relaxed Distribution Alignment

Yifan Wu · Ezra Winston · Divyansh Kaushik · Zachary Lipton

Pacific Ballroom #177

Keywords: [ Unsupervised and Semi-supervised Learning ] [ Transfer and Multitask Learning ]


Domain adaptation addresses the common situation in which the target distribution generating our test data differs from the source distribution generating our training data. While absent assumptions, domain adaptation is impossible, strict conditions, e.g. covariate or label shift, enable principled algorithms. Recently-proposed domain-adversarial approaches consist of aligning source and target encodings, an approach often motivated as minimizing two (of three) terms in a theoretical bound on target error. Unfortunately, this minimization can cause arbitrary increases in the third term, a problem guaranteed to arise under shifting label distributions. We propose asymmetrically-relaxed distribution alignment, a new approach that overcomes some limitations of standard domain-adversarial algorithms. Moreover, we characterize precise assumptions under which our algorithm is theoretically principled and demonstrate empirical benefits on both synthetic and real datasets.

Live content is unavailable. Log in and register to view live content