Adversarial Multiple Source Domain Adaptation

Authors:
Han Zhao Carnegie Mellon University
Shanghang Zhang Carnegie Mellon University
Guanhang Wu Carnegie Mellon University
José M. F. Moura Carnegie Mellon University
Joao P Costeira Instituto Superior Tecnico VAT- 501507930
Geoffrey Gordon MSR Montréal & CMU

Introduction:

The authors propose new generalization bounds and algorithms under both classification and regression settings for unsupervised multiple source domain adaptation.

Abstract:

While domain adaptation has been actively researched, most algorithms focus on the single-source-single-target adaptation setting. In this paper we propose new generalization bounds and algorithms under both classification and regression settings for unsupervised multiple source domain adaptation. Our theoretical analysis naturally leads to an efficient learning strategy using adversarial neural networks: we show how to interpret it as learning feature representations that are invariant to the multiple domain shifts while still being discriminative for the learning task. To this end, we propose multisource domain adversarial networks (MDAN) that approach domain adaptation by optimizing task-adaptive generalization bounds. To demonstrate the effectiveness of MDAN, we conduct extensive experiments showing superior adaptation performance on both classification and regression problems: sentiment analysis, digit classification, and vehicle counting.

You may want to know: