OTMatch: Improving Semi-Supervised Learning with Optimal Transport
This work addresses semi-supervised learning for vision and language tasks, but it appears incremental as it builds on existing self-training methods with a new loss function.
The paper tackled the problem of semi-supervised learning algorithms neglecting class relationships by introducing OTMatch, which uses an optimal transport loss to match distributions based on semantic relationships, resulting in improvements over baselines on standard vision and language datasets.
Semi-supervised learning has made remarkable strides by effectively utilizing a limited amount of labeled data while capitalizing on the abundant information present in unlabeled data. However, current algorithms often prioritize aligning image predictions with specific classes generated through self-training techniques, thereby neglecting the inherent relationships that exist within these classes. In this paper, we present a new approach called OTMatch, which leverages semantic relationships among classes by employing an optimal transport loss function to match distributions. We conduct experiments on many standard vision and language datasets. The empirical results show improvements in our method above baseline, this demonstrates the effectiveness and superiority of our approach in harnessing semantic relationships to enhance learning performance in a semi-supervised setting.