RankUp: Boosting Semi-Supervised Regression with an Auxiliary Ranking Classifier

TL;DR

RankUp introduces a novel semi-supervised regression method that converts regression into a ranking problem and leverages classification techniques, achieving state-of-the-art results across various domains.

Contribution

It adapts semi-supervised classification techniques to regression by using a ranking classifier and introduces regression distribution alignment for improved pseudo-label refinement.

Findings

Achieves SOTA results on multiple regression benchmarks

Effective across computer vision, audio, and NLP tasks

Enhances pseudo-label quality through distribution alignment

Abstract

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.