2021/12/09 by Lukas Balles, Balles, Lukas, Giovanni Zappella +3
Computer Science · #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multimodal Machine Learning Applications
paper · pdf · doi:10.48550/arxiv.2112.05025
openalex publication_date 2021/12/09 · openalex created_date 2022/05/05 · openalex updated_date 2026/07/28
We devise a coreset selection method based on the idea of gradient matching: The gradients induced by the coreset should match, as closely as possible, those induced by the original training dataset. We evaluate the method in the context of continual learning, where it can be used to curate a rehearsal memory. Our method performs strong competitors such as reservoir sampling across a range of memory sizes.