 |
Free and accessible knowledge |
Conference papers
Unsupervised Multi-Source Domain Adaptation for Regression
Abstract : We consider the problem of unsupervised domain adaptation from multiple sources in a regression setting. We propose in this work an original method to take benefit of different sources using a weighted combination of the sources. For this purpose, we define a new measure of similarity between probabilities for domain adaptation which we call hypothesis-discrepancy. We then prove a new bound for unsupervised domain adaptation combining multiple sources. We derive from this bound a novel adversarial domain adaptation algorithm adjusting weights given to each source, ensuring that sources related to the target receive higher weights. We finally evaluate our method on different public datasets and compare it to other domain adaptation baselines to demonstrate the improvement for regression tasks.
Cited literature [23 references]
https://hal.archives-ouvertes.fr/hal-02543790
Contributor : Guillaume Richard Connect in order to contact the contributor
Submitted on : Wednesday, April 15, 2020 - 4:18:06 PM
Last modification on : Thursday, April 7, 2022 - 1:58:34 PM
Contributor : Guillaume Richard Connect in order to contact the contributor
Submitted on : Wednesday, April 15, 2020 - 4:18:06 PM
Last modification on : Thursday, April 7, 2022 - 1:58:34 PM
File
paper_hal.pdf
Files produced by the author(s)