MetaMask: Revisiting Dimensional Confounder for Self-Supervised Learning
This addresses sample inefficiency and interference issues in self-supervised learning, offering a novel method for improving representation learning, but it is incremental as it builds on existing contrastive learning frameworks.
The paper tackles the problems of task-irrelevant information interference and sample inefficiency in contrastive self-supervised learning by identifying dimensional redundancy and confounder as intrinsic issues, and proposes MetaMask, which achieves state-of-the-art performance on various benchmarks.
As a successful approach to self-supervised learning, contrastive learning aims to learn invariant information shared among distortions of the input sample. While contrastive learning has yielded continuous advancements in sampling strategy and architecture design, it still remains two persistent defects: the interference of task-irrelevant information and sample inefficiency, which are related to the recurring existence of trivial constant solutions. From the perspective of dimensional analysis, we find out that the dimensional redundancy and dimensional confounder are the intrinsic issues behind the phenomena, and provide experimental evidence to support our viewpoint. We further propose a simple yet effective approach MetaMask, short for the dimensional Mask learned by Meta-learning, to learn representations against dimensional redundancy and confounder. MetaMask adopts the redundancy-reduction technique to tackle the dimensional redundancy issue and innovatively introduces a dimensional mask to reduce the gradient effects of specific dimensions containing the confounder, which is trained by employing a meta-learning paradigm with the objective of improving the performance of masked representations on a typical self-supervised task. We provide solid theoretical analyses to prove MetaMask can obtain tighter risk bounds for downstream classification compared to typical contrastive methods. Empirically, our method achieves state-of-the-art performance on various benchmarks.