Explicitly Modeling Generality into Self-Supervised Learning

arXiv:2405.01053v1 Announce Type: new
Abstract: The goal of generality in machine learning is to achieve excellent performance on various unseen tasks and domains. Recently, self-supervised learning (SSL) has been regarded as an effective method to achieve this goal. It can learn high-quality representations from unlabeled data and achieve promising empirical performance on multiple downstream tasks. Existing SSL methods mainly constrain generality from two aspects: (i) large-scale training data, and (ii) learning task-level shared knowledge. However, these methods lack explicit modeling …

abstract arxiv cs.ai cs.lg data domains learn machine machine learning modeling multiple performance quality self-supervised learning ssl supervised learning tasks type