HoMM: Higher-Order Moment Matching for Unsupervised Domain Adaptation

Authors

  • Chao Chen Zhejiang University
  • Zhihang Fu Alibaba Group
  • Zhihong Chen Zhejiang University
  • Sheng Jin Harbin Institute of Technology
  • Zhaowei Cheng Zhejiang University
  • Xinyu Jin Zhejiang University
  • Xian-sheng Hua Alibaba Group

DOI:

https://doi.org/10.1609/aaai.v34i04.5745

Abstract

Minimizing the discrepancy of feature distributions between different domains is one of the most promising directions in unsupervised domain adaptation. From the perspective of moment matching, most existing discrepancy-based methods are designed to match the second-order or lower moments, which however, have limited expression of statistical characteristic for non-Gaussian distributions. In this work, we propose a Higher-order Moment Matching (HoMM) method, and further extend the HoMM into reproducing kernel Hilbert spaces (RKHS). In particular, our proposed HoMM can perform arbitrary-order moment matching, we show that the first-order HoMM is equivalent to Maximum Mean Discrepancy (MMD) and the second-order HoMM is equivalent to Correlation Alignment (CORAL). Moreover, HoMM (order≥ 3) is expected to perform fine-grained domain alignment as higher-order statistics can approximate more complex, non-Gaussian distributions. Besides, we also exploit the pseudo-labeled target samples to learn discriminative representations in the target domain, which further improves the transfer performance. Extensive experiments are conducted, showing that our proposed HoMM consistently outperforms the existing moment matching methods by a large margin. Codes are available at https://github.com/chenchao666/HoMM-Master

Downloads

Published

2020-04-03

How to Cite

Chen, C., Fu, Z., Chen, Z., Jin, S., Cheng, Z., Jin, X., & Hua, X.- sheng. (2020). HoMM: Higher-Order Moment Matching for Unsupervised Domain Adaptation. Proceedings of the AAAI Conference on Artificial Intelligence, 34(04), 3422-3429. https://doi.org/10.1609/aaai.v34i04.5745

Issue

Section

AAAI Technical Track: Machine Learning