RankUp: Boosting Semi-Supervised Regression with an Auxiliary Ranking Classifier
This addresses the limitation of current semi-supervised techniques being inapplicable to regression, offering a solution for domains requiring regression with limited labeled data.
The paper tackles the problem of adapting semi-supervised learning to regression tasks by proposing RankUp, which converts regression into a ranking problem and integrates with existing classification methods, achieving state-of-the-art results across computer vision, audio, and NLP benchmarks.
State-of-the-art (SOTA) semi-supervised learning techniques, such as FixMatch and it's variants, have demonstrated impressive performance in classification tasks. However, these methods are not directly applicable to regression tasks. In this paper, we present RankUp, a simple yet effective approach that adapts existing semi-supervised classification techniques to enhance the performance of regression tasks. RankUp achieves this by converting the original regression task into a ranking problem and training it concurrently with the original regression objective. This auxiliary ranking classifier outputs a classification result, thus enabling integration with existing semi-supervised classification methods. Moreover, we introduce regression distribution alignment (RDA), a complementary technique that further enhances RankUp's performance by refining pseudo-labels through distribution alignment. Despite its simplicity, RankUp, with or without RDA, achieves SOTA results in across a range of regression benchmarks, including computer vision, audio, and natural language processing tasks. Our code and log data are open-sourced at https://github.com/pm25/semi-supervised-regression.