提出角度补偿对比正则化，提升回归模型在小样本和不均衡数据下的表现。
ACCon: Angle-Compensated Contrastive Regularizer for Deep Regression
- 基于标签距离与表征相似性的线性负相关假设，调整对比学习中的余弦距离。
- 在小样本和不均衡数据上显著提升回归性能，优于主流对比学习方法。
- 可直接插入现有框架，适合需要高数据效率的回归任务研究者使用。
在深度回归中，捕捉特征空间中连续标签间的关系是一个基础挑战，日益受到关注。解决该问题可避免模型在多种回归任务中收敛至次优解，从而提升性能，尤其在数据不均衡和样本有限的情况下。现有方法多依赖顺序感知表示学习或基于距离的加权策略。本文假设回归任务中标签距离与表征相似性存在线性负相关关系。为此，我们提出一种角度补偿对比正则化（ACCon），在对比学习框架内调整锚点与负样本间的余弦距离。该方法具备即插即用特性，可扩展多数现有对比学习回归方法。大量实验与理论分析表明，所提方法不仅在回归性能上具有竞争力，且在数据效率及不均衡数据处理方面表现优异。
原文摘要 · Abstract (English)
In deep regression, capturing the relationship among continuous labels in feature space is a fundamental challenge that has attracted increasing interest. Addressing this issue can prevent models from converging to suboptimal solutions across various regression tasks, leading to improved performance, especially for imbalanced regression and under limited sample sizes. However, existing approaches often rely on order-aware representation learning or distance-based weighting. In this paper, we hypothesize a linear negative correlation between label distances and representation similarities in regression tasks. To implement this, we propose an angle-compensated contrastive regularizer for deep regression, which adjusts the cosine distance between anchor and negative samples within the contrastive learning framework. Our method offers a plug-and-play compatible solution that extends most existing contrastive learning methods for regression tasks. Extensive experiments and theoretical analysis demonstrate that our proposed angle-compensated contrastive regularizer not only achieves competitive regression performance but also excels in data efficiency and effectiveness on imbalanced datasets.
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。