Online Multi-Source Domain Adaptation through Gaussian Mixtures and Dataset Dictionary Learning
Abstract
This paper addresses the challenge of online multi-source domain adaptation (MSDA) in transfer learning, a scenario where one needs to adapt multiple, heterogeneous source domains towards a target domain that comes in a stream. We introduce a novel approach for the online fit of a Gaussian Mixture Model (GMM), based on the Wasserstein geometry of Gaussian measures. We build upon this method and recent developments in dataset dictionary learning for proposing a novel strategy in online MSDA. Experiments on the challenging Tennessee Eastman Process benchmark demonstrate that our approach is able to adapt \emph{on the fly} to the stream of target domain data. Furthermore, our online GMM serves as a memory, representing the whole stream of data.
- Publication:
-
arXiv e-prints
- Pub Date:
- July 2024
- DOI:
- 10.48550/arXiv.2407.19853
- arXiv:
- arXiv:2407.19853
- Bibcode:
- 2024arXiv240719853F
- Keywords:
-
- Computer Science - Machine Learning;
- Statistics - Machine Learning
- E-Print:
- 6 pages, 3 figures, accepted at the IEEE International Workshop on Machine Learning for Signal Processing 2024