Model-Aware Contrastive Learning: Towards Escaping the Dilemmas
This work addresses performance degradation problems in contrastive learning for researchers and practitioners in machine learning, though it is incremental as it builds on existing CL methods.
The paper tackled the uniformity-tolerance dilemma and gradient reduction issues in InfoNCE-based contrastive learning by introducing a Model-Aware Contrastive Learning (MACL) strategy with adaptive temperature and gradient reweighting, achieving general improvements in representation learning and downstream tasks across vision, sentence, and graph modalities.
Contrastive learning (CL) continuously achieves significant breakthroughs across multiple domains. However, the most common InfoNCE-based methods suffer from some dilemmas, such as \textit{uniformity-tolerance dilemma} (UTD) and \textit{gradient reduction}, both of which are related to a $\mathcal{P}_{ij}$ term. It has been identified that UTD can lead to unexpected performance degradation. We argue that the fixity of temperature is to blame for UTD. To tackle this challenge, we enrich the CL loss family by presenting a Model-Aware Contrastive Learning (MACL) strategy, whose temperature is adaptive to the magnitude of alignment that reflects the basic confidence of the instance discrimination task, then enables CL loss to adjust the penalty strength for hard negatives adaptively. Regarding another dilemma, the gradient reduction issue, we derive the limits of an involved gradient scaling factor, which allows us to explain from a unified perspective why some recent approaches are effective with fewer negative samples, and summarily present a gradient reweighting to escape this dilemma. Extensive remarkable empirical results in vision, sentence, and graph modality validate our approach's general improvement for representation learning and downstream tasks.