Research Area:  Machine Learning

Abstract:

Having a lot of labeled data is always a problem in machine learning issues. Even by collecting lots of data hardly, shift in data distribution might emerge because of differences in source and target domains. The shift would make the model to face with problems in test step. Therefore, the necessity of using domain adaptation emerges. There are three techniques in the field of domain adaptation namely discrepancy based, adversarial based and reconstruction based methods. For domain adaptation, adversarial learning approaches showed state-of-the-art performance. Although there are some comprehensive surveys about domain adaptation, we technically focus on adversarial based domain adaptation methods. We examine each proposed method in detail with respect to their structures and objective functions. The common aspect of proposed methods besides domain adaptation is considering the target labels are predicted as accurately as possible. It can be represented by some methods such as metric learning and multi-adversarial discriminators as are used in some of the papers. Also, we address the negative transfer issue for dissimilar distributions and propose the addition of clustering heuristics to the underlying structures for future research.

Keywords:  
adversarial domain adaptation

Author(s) Name:  Mahta HassanPour Zonoozi,Vahid Seydi

Publisher name:  Springer

DOI:  10.1007/s11063-022-10977-5

Volume Information:  Volume 55, pages 2429–2469, (2023)

Paper Link:   https://link.springer.com/article/10.1007/s11063-022-10977-5