让回归模型学会连续排序，提升预测准确性和鲁棒性
Evaluating Rank-N-Contrast: Continuous and Robust Representations for Regression
- 通过对比样本排名学习连续表示，避免离散化导致的性能损失
- 在新增数据集上实现顶尖性能，排除部分数据仍保持稳定表现
- 适合需要高精度和强泛化能力的回归任务研究者
深度回归模型常无法捕捉样本顺序的连续特性，导致表示碎片化，性能不佳。本文复现了2023年发表的Rank-N-Contrast（RNC）框架，该方法通过在目标空间中对比样本的排名来学习连续表示。本研究验证了RNC在理论与实证上的优势，包括性能提升和鲁棒性增强。我们将其评估扩展至一个额外的回归数据集，并采用保留测试法进行鲁棒性测试——从训练集中排除特定范围的连续数据。该方法评估了模型对未见数据的泛化能力，并达到当前最优水平。此次复现研究验证了原始结论，并拓展了对RNC适用性与鲁棒性的理解。
原文摘要 · Abstract (English)
This document is an evaluation of the original "Rank-N-Contrast" (arXiv:2210.01189v2) paper published in 2023. This evaluation is done for academic purposes. Deep regression models often fail to capture the continuous nature of sample orders, creating fragmented representations and suboptimal performance. To address this, we reproduced the Rank-N-Contrast (RNC) framework, which learns continuous representations by contrasting samples by their rankings in the target space. Our study validates RNC's theoretical and empirical benefits, including improved performance and robustness. We extended the evaluation to an additional regression dataset and conducted robustness tests using a holdout method, where a specific range of continuous data was excluded from the training set. This approach assessed the model's ability to generalize to unseen data and achieve state-of-the-art performance. This replication study validates the original findings and broadens the understanding of RNC's applicability and robustness.
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。