Similarity-Aware Mixture-of-Experts for Data-Efficient Continual Learning

ArXi:2603.23436v1 Announce Type: new Machine learning models often need to adapt to new data after deployment due to structured or unstructured real-world dynamics. The Continual Learning (CL) framework enables continuous model adaptation, but most existing approaches either assume each task contains sufficiently many data samples or that the learning tasks are non-overlapping. In this paper, we address the general setting where each task may have a limited dataset, and tasks may overlap in an arbitrary manner without a priori knowledge.