USimUL: Closing the Privacy Gap in Similarity-Based Weakly Supervised Learning

Meng Wei, Zhongnian Li, Peng Ying, Xinzheng Xu

Keywords: Weak Supervision, Uncertain Similarity, Pairwise Similarity Learning, Unbiased Risk Estimator

TL;DR: We propose USimUL, a privacy-preserving framework that learns from uncertain similarity and unlabeled data using an unbiased risk estimator with optimal convergence guarantees.

Abstract: Existing similarity-based weakly supervised learning approaches often rely on precise similarity annotations between data pairs, which may inadvertently expose sensitive label information and raise privacy risks. To mitigate this issue, 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. In this paper, we propose an unbiased risk estimator that learns from uncertain similarity and unlabeled data. Additionally, we theoretically prove that the estimator achieves statistically optimal parametric convergence rates. Extensive experiments on both benchmark and real-world datasets show that our method achieves superior classification performance compared to conventional similarity-based approaches.

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Submission Number: 7613