Learning from Similarity/Dissimilarity and Pairwise Comparison

• URL: http://arxiv.org/abs/2603.19713v1
• Date: Fri, 20 Mar 2026 07:35:03 GMT
• Title: Learning from Similarity/Dissimilarity and Pairwise Comparison
• Abstract summary: We propose a binary judgment based weakly supervised learning framework that relies on relative judgments, namely class agreement between two instances and pairwise preference toward the positive class.<n>We show that the proposed approach improves classification performance over methods using a single weak label, and is robust to label noise and uncertainty in class prior estimation.
• Score: 0.07646713951724009
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper addresses binary classification in scenarios where obtaining explicit instance level labels is impractical, by exploiting multiple weak labels defined on instance pairs. The existing SconfConfDiff classification framework relies on continuous valued probabilistic supervision, including similarity-confidence, the probability of class agreement, and confidence-difference, the difference in positive class probabilities. However, probabilistic labeling requires subjective uncertainty quantification, often leading to unstable supervision. We propose SD-Pcomp classification, a binary judgment based weakly supervised learning framework that relies only on relative judgments, namely class agreement between two instances and pairwise preference toward the positive class. The method employs Similarity/Dissimilarity (SD) labels and Pairwise Comparison (Pcomp) labels, and develops two unbiased risk estimators, (i) a convex combination of SD and Pcomp and (ii) a unified estimator that integrates both labels by modeling their relationship. Theoretical analysis and experimental results show that the proposed approach improves classification performance over methods using a single weak label, and is robust to label noise and uncertainty in class prior estimation.

Related papers

• Rethinking Consistent Multi-Label Classification under Inexact Supervision [60.79309683889278]
  In partial multi-label learning, each instance is annotated with a candidate label set, among which only some labels are relevant.<n>In complementary multi-label learning, each instance is annotated with complementary labels indicating the classes to which the instance does not belong.
  arXiv  Detail & Related papers  (2025-10-05T08:30:32Z)
• Learning from Uncertain Similarity and Unlabeled Data [6.553242735096595]
  We propose Uncertain Similarity and Unlabeled Learning (USimUL), a novel framework where each similarity pair is embedded with an uncertainty component to reduce label leakage.<n>We show that our method achieves superior classification performance compared to conventional similarity-based approaches.
  arXiv  Detail & Related papers  (2025-09-15T14:29:36Z)
• Learning from Similarity-Confidence and Confidence-Difference [0.07646713951724009]
  We propose a novel Weakly Supervised Learning (WSL) framework that leverages complementary weak supervision signals from multiple perspectives.<n>Specifically, we introduce SconfConfDiff Classification, a method that integrates two distinct forms of weaklabels.<n>We prove that both estimators achieve optimal convergence rates with respect to estimation error bounds.
  arXiv  Detail & Related papers  (2025-08-07T07:42:59Z)
• Weakly-Supervised Contrastive Learning for Imprecise Class Labels [50.57424331797865]
  We introduce the concept of continuous semantic similarity'' to define positive and negative pairs.<n>We propose a graph-theoretic framework for weakly-supervised contrastive learning.<n>Our framework is highly versatile and can be applied to many weakly-supervised learning scenarios.
  arXiv  Detail & Related papers  (2025-05-28T06:50:40Z)
• Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical [66.57396042747706]
  Complementary-label learning is a weakly supervised learning problem. We propose a consistent approach that does not rely on the uniform distribution assumption. We find that complementary-label learning can be expressed as a set of negative-unlabeled binary classification problems.
  arXiv  Detail & Related papers  (2023-11-27T02:59:17Z)
• Binary Classification with Confidence Difference [100.08818204756093]
  This paper delves into a novel weakly supervised binary classification problem called confidence-difference (ConfDiff) classification. We propose a risk-consistent approach to tackle this problem and show that the estimation error bound the optimal convergence rate. We also introduce a risk correction approach to mitigate overfitting problems, whose consistency and convergence rate are also proven.
  arXiv  Detail & Related papers  (2023-10-09T11:44:50Z)
• Class-Distribution-Aware Pseudo Labeling for Semi-Supervised Multi-Label Learning [97.88458953075205]
  Pseudo-labeling has emerged as a popular and effective approach for utilizing unlabeled data. This paper proposes a novel solution called Class-Aware Pseudo-Labeling (CAP) that performs pseudo-labeling in a class-aware manner.
  arXiv  Detail & Related papers  (2023-05-04T12:52:18Z)
• Pointwise Binary Classification with Pairwise Confidence Comparisons [97.79518780631457]
  We propose pairwise comparison (Pcomp) classification, where we have only pairs of unlabeled data that we know one is more likely to be positive than the other. We link Pcomp classification to noisy-label learning to develop a progressive URE and improve it by imposing consistency regularization.
  arXiv  Detail & Related papers  (2020-10-05T09:23:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.