Abstract
AbstractIn this work, we study the problem of generalizing a prediction (classification or regression) model trained on a set of source domains to an unseen target domain, where the source and target domains are different but related, i.e, the domain generalization problem. The challenge in this problem lies in the domain difference, which could degrade the generalization ability of the prediction model. To tackle this challenge, we propose to learn a neural network representation function to align a joint distribution and a product distribution in the representation space, and show that such joint-product distribution alignment conveniently leads to the alignment of multiple domains. In particular, we align the joint distribution and the product distribution under the $$L^{2}$$
L
2
-distance, and show that this distance can be analytically estimated by exploiting its variational characterization and a linear variational function. This allows us to comfortably align the two distributions by minimizing the estimated distance with respect to the network representation function. Our experiments on synthetic and real-world datasets for classification and regression demonstrate the effectiveness of the proposed solution. For example, it achieves the best average classification accuracy of 82.26% on the text dataset Amazon Reviews, and the best average regression error of 0.114 on the WiFi dataset UJIIndoorLoc.
Funder
National Natural Science Foundation of China
Publisher
Springer Science and Business Media LLC
Subject
Artificial Intelligence,Software
Reference56 articles.
1. Akuzawa K, Iwasawa Y, Matsuo Y (2019) Adversarial invariant feature learning with accuracy constraint for domain generalization. In: Joint European conference on machine learning and knowledge discovery in databases, pp 315–331
2. Baktashmotlagh M, Harandi M, Salzmann M (2016) Distribution-matching embedding for visual domain adaptation. J Mach Learn Res 17(108):1–30
3. Balaji Y, Sankaranarayanan S, Chellappa R (2018) Metareg: towards domain generalization using meta-regularization. Adv Neural Inf Process Syst 31:998–1008
4. Bickel S, Bogojeska J, Lengauer T, et al (2008) Multi-task learning for HIV therapy screening. In: International conference on machine learning, pp 56–63
5. Blanchard G, Lee G, Scott C (2011) Generalizing from several related classification tasks to a new unlabeled sample. Adv Neural Inform Process Syst, pp 2178–2186
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献