SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised Learning

Autor:	Chen, Hao, Tao, Ran, Fan, Yue, Wang, Yidong, Wang, Jindong, Schiele, Bernt, Xie, Xing, Raj, Bhiksha, Savvides, Marios
Rok vydání:	2023
Předmět:	Computer Science - Machine Learning Computer Science - Artificial Intelligence Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	The critical challenge of Semi-Supervised Learning (SSL) is how to effectively leverage the limited labeled data and massive unlabeled data to improve the model's generalization performance. In this paper, we first revisit the popular pseudo-labeling methods via a unified sample weighting formulation and demonstrate the inherent quantity-quality trade-off problem of pseudo-labeling with thresholding, which may prohibit learning. To this end, we propose SoftMatch to overcome the trade-off by maintaining both high quantity and high quality of pseudo-labels during training, effectively exploiting the unlabeled data. We derive a truncated Gaussian function to weight samples based on their confidence, which can be viewed as a soft version of the confidence threshold. We further enhance the utilization of weakly-learned classes by proposing a uniform alignment approach. In experiments, SoftMatch shows substantial improvements across a wide variety of benchmarks, including image, text, and imbalanced classification. Comment: Accepted by ICLR 2023
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2301.10921 Zobrazit plný text záznamu View this record from Arxiv