将回归任务转为排序问题，用分类方法提升回归性能。
RankUp: Boosting Semi-Supervised Regression with an Auxiliary Ranking Classifier
- 把回归转成排序任务，用辅助分类器结合半监督学习
- 在多个视觉、音频和语言任务上达到当前最佳效果
- 适合需要高精度回归的场景，如医疗或工业预测
当前最先进的半监督学习方法（如 FixMatch 及其变体）在分类任务中表现优异，但无法直接用于回归任务。本文提出 RankUp，一种简单而有效的方法，将现有半监督分类技术应用于回归任务。RankUp 通过将原始回归任务转化为排序问题，并同时训练回归目标与辅助排序分类器，使伪标签可被现有分类方法利用。此外，我们引入回归分布对齐（RDA），通过分布对齐优化伪标签，进一步提升性能。尽管方法简单，RankUp 在多个回归基准测试中（涵盖计算机视觉、音频和自然语言处理）均达到当前最优水平。代码与日志已开源：https://github.com/pm25/semi-supervised-regression。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。