Rethinking Positive Pairs in Contrastive Learning

2024-10-23

arXiv.org

AI Summary

Existing contrastive learning methods define similarity exclusively over semantically consistent sample pairs, overlooking latent structural similarities inherent in semantically dissimilar pairs. To address this limitation, we propose SimLAP—a novel framework that redefines positive pairs not as semantically identical samples but as learnable, discriminative subspace-aligned pairs. SimLAP jointly optimizes pairwise similarity estimation and subspace projection within an end-to-end training paradigm, incorporating both contrastive loss and explicit subspace alignment constraints. By uncovering and leveraging structural similarities among inter-class samples residing in shared latent subspaces, SimLAP breaks from conventional similarity modeling paradigms. Extensive experiments across multiple benchmarks demonstrate its effectiveness: SimLAP significantly improves few-shot transfer performance and model robustness under distribution shifts. Moreover, it offers a new perspective on unsupervised similarity learning—shifting focus from semantic identity to geometric consistency in learned representation subspaces.

Technology Category

• Machine Learning: Semi-Supervised Learning
• Search and Optimization: Sampling/Simulation-based Search
• Computer Vision: Representation Learning for Vision

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

The training methods in AI do involve semantically distinct pairs of samples. However, their role typically is to enhance the between class separability. The actual notion of similarity is normally learned from semantically identical pairs. This paper presents SimLAP: a simple framework for learning visual representation from arbitrary pairs. SimLAP explores the possibility of learning similarity from semantically distinct sample pairs. The approach is motivated by the observation that for any pair of classes there exists a subspace in which semantically distinct samples exhibit similarity. This phenomenon can be exploited for a novel method of learning, which optimises the similarity of an arbitrary pair of samples, while simultaneously learning the enabling subspace. The feasibility of the approach will be demonstrated experimentally and its merits discussed.

Problem

• Learning similarity from semantically distinct sample pairs
• Exploring subspaces where distinct samples exhibit similarity
• Optimizing similarity for arbitrary pairs while learning subspaces

Innovation

• Learning similarity from distinct sample pairs
• Optimizing similarity via enabling subspace learning
• Exploiting inter-class similarity for representation learning