Abstract
Coping with distributional shifts is an important part of transfer learning methods in order to perform well in real-life tasks. However, most of the existing approaches in this area either focus on an ideal scenario in which the data does not contain noises or employ a complicated training paradigm or model design to deal with distributional shifts. In this paper, we revisit the robustness of the minimum error entropy (MEE) criterion, a widely used objective in statistical signal processing to deal with non-Gaussian noises, and investigate its feasibility and usefulness in real-life transfer learning regression tasks, where distributional shifts are common. Specifically, we put forward a new theoretical result showing the robustness of MEE against covariate shift. We also show that by simply replacing the mean squared error (MSE) loss with the MEE on basic transfer learning algorithms such as fine-tuning and linear probing, we can achieve competitive performance with respect to state-of-the-art transfer learning algorithms. We justify our arguments on both synthetic data and 5 real-world time-series data.
Original language | English |
---|---|
Title of host publication | ECAI 2023 |
Subtitle of host publication | 26th European Conference on Artificial Intelligence, including 12th Conference on Prestigious Applications of Intelligent Systems, PAIS 2023 - Proceedings |
Editors | Kobi Gal, Kobi Gal, Ann Nowe, Grzegorz J. Nalepa, Roy Fairstein, Roxana Radulescu |
Publisher | IOS Press BV |
Pages | 2146-2153 |
Number of pages | 8 |
ISBN (Electronic) | 9781643684369 |
DOIs | |
Publication status | Published - 2023 |
Event | 26th European Conference on Artificial Intelligence, ECAI 2023 - Krakow, Poland Duration: 30 Sept 2023 → 4 Oct 2023 |
Publication series
Name | Frontiers in Artificial Intelligence and Applications |
---|---|
Publisher | IOS Press |
Volume | 372 |
ISSN (Print) | 0922-6389 |
Conference
Conference | 26th European Conference on Artificial Intelligence, ECAI 2023 |
---|---|
Country/Territory | Poland |
City | Krakow |
Period | 30/09/23 → 4/10/23 |
Bibliographical note
Funding Information:This work has been conducted as part of the Just in Time Maintenance project funded by the European Fund for Regional Development.
Publisher Copyright:
© 2023 The Authors.