Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere
This work provides foundational insights for researchers in representation learning, though it is incremental in building on existing contrastive methods.
The paper tackles the problem of understanding contrastive representation learning by identifying alignment and uniformity as key properties, proving their optimization by contrastive loss and showing that directly optimizing these metrics leads to comparable or better performance on downstream tasks.
Contrastive representation learning has been outstandingly successful in practice. In this work, we identify two key properties related to the contrastive loss: (1) alignment (closeness) of features from positive pairs, and (2) uniformity of the induced distribution of the (normalized) features on the hypersphere. We prove that, asymptotically, the contrastive loss optimizes these properties, and analyze their positive effects on downstream tasks. Empirically, we introduce an optimizable metric to quantify each property. Extensive experiments on standard vision and language datasets confirm the strong agreement between both metrics and downstream task performance. Remarkably, directly optimizing for these two metrics leads to representations with comparable or better performance at downstream tasks than contrastive learning. Project Page: https://tongzhouwang.info/hypersphere Code: https://github.com/SsnL/align_uniform , https://github.com/SsnL/moco_align_uniform