1. A Review of Domain Adaptation without Target Labels
- Author
-
Marco Loog and Wouter M. Kouw
- Subjects
FOS: Computer and information sciences ,Computer Science - Machine Learning ,Domain adaptation ,domain adaptation ,Machine Learning (stat.ML) ,02 engineering and technology ,transfer learning ,Machine learning ,computer.software_genre ,Machine Learning (cs.LG) ,Statistics - Machine Learning ,Artificial Intelligence ,Covariate shift ,0202 electrical engineering, electronic engineering, information engineering ,Estimation theory ,business.industry ,Applied Mathematics ,pattern recognition ,Generalization error ,Weighting ,covariate shift ,Computational Theory and Mathematics ,Categorization ,sample selection bias ,020201 artificial intelligence & image processing ,Computer Vision and Pattern Recognition ,Artificial intelligence ,business ,Transfer of learning ,computer ,Classifier (UML) ,Software - Abstract
Domain adaptation has become a prominent problem setting in machine learning and related fields. This review asks the question: how can a classifier learn from a source domain and generalize to a target domain? We present a categorization of approaches, divided into, what we refer to as, sample-based, feature-based and inference-based methods. Sample-based methods focus on weighting individual observations during training based on their importance to the target domain. Feature-based methods revolve around on mapping, projecting and representing features such that a source classifier performs well on the target domain and inference-based methods incorporate adaptation into the parameter estimation procedure, for instance through constraints on the optimization procedure. Additionally, we review a number of conditions that allow for formulating bounds on the cross-domain generalization error. Our categorization highlights recurring ideas and raises questions important to further research., Comment: 20 pages, 5 figures
- Published
- 2021