DualMatch: Robust Semi-Supervised Learning with Dual-Level Interaction
This addresses robustness issues in semi-supervised learning for machine learning practitioners, but it is incremental as it builds on existing SSL frameworks.
The paper tackles the problem of semi-supervised learning being non-robust due to reliance on pseudo-label quality by proposing DualMatch, a method that uses dual-level interaction for consistent regularization, resulting in a 9% error reduction in standard settings and 6% in class-imbalanced settings compared to SOTA methods.
Semi-supervised learning provides an expressive framework for exploiting unlabeled data when labels are insufficient. Previous semi-supervised learning methods typically match model predictions of different data-augmented views in a single-level interaction manner, which highly relies on the quality of pseudo-labels and results in semi-supervised learning not robust. In this paper, we propose a novel SSL method called DualMatch, in which the class prediction jointly invokes feature embedding in a dual-level interaction manner. DualMatch requires consistent regularizations for data augmentation, specifically, 1) ensuring that different augmented views are regulated with consistent class predictions, and 2) ensuring that different data of one class are regulated with similar feature embeddings. Extensive experiments demonstrate the effectiveness of DualMatch. In the standard SSL setting, the proposal achieves 9% error reduction compared with SOTA methods, even in a more challenging class-imbalanced setting, the proposal can still achieve 6% error reduction. Code is available at https://github.com/CWangAI/DualMatch