Pairwise Supervision Can Provably Elicit A Decision Boundary

Abstract

Similarity learning is a general problem to elicit useful representations by predicting the relationship between a pair of patterns. This problem is related to various important preprocessing tasks such as metric learning, kernel learning, and contrastive learning. A classifier built upon the representations is expected to perform well in downstream classification; however, little theory has been given in literature so far and thereby the relationship between similarity and classification has remained elusive. Therefore, we tackle a fundamental question: can similarity information provably leads a model to perform well in downstream classification? In this paper, we reveal that a product-type formulation of similarity learning is strongly related to an objective of binary classification. We further show that these two different problems are explicitly connected by an excess risk bound. Consequently, our results elucidate that similarity learning is capable of solving binary classificat

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keybao2020pairwise

Related papers

• A Probabilistic Theory Of Supervised Similarity Learning For Pointwise ROC Curve Optimization (2018)0.00
• Learning Similarity Conditions Without Explicit Supervision (2019)13.93
• Discriminative Learning Of Similarity And Group Equivariant Representations (2018)0.00
• Pairwise Similarity Learning Is Simple (2023)7.50
• Similarity Learning Via Kernel Preserving Embedding (2019)10.35
• Unsupervised Feature Learning Via Non-parametric Instance-level Discrimination (2018)25.66
• Similarity Function Tracking Using Pairwise Comparisons (2017)2.26
• Beyond Supervised Vs. Unsupervised: Representative Benchmarking And Analysis Of Image Representation Learning (2022)8.35