논문 링크: Representation Learning via Invariant Causal MechanismsSelf-supervised learning has emerged as a strategy to reduce the reliance on costly supervised signal by pretraining representations only using unlabeled data. These methods combine heuristic proxy classification tasks with data augmentations and have achiarxiv.org 출처: J. Mitrovic, B. McWilliams, J. Walker, L. Buesing, and C. Blundel..
