用少量排名信息提升小数据下的回归预测精度
Post Hoc Regression Refinement via Pairwise Rankings
- 通过逆方差加权融合模型输出与排名估计
- 仅用20次比较即可降低10%的平均绝对误差
- 无需重训练，适合低数据场景的快速优化
准确预测连续属性对众多科学与工程任务至关重要。尽管深度学习回归器在标签充足时表现优异，但在数据稀缺情况下性能下降。我们提出 RankRefine，一种模型无关、即插即用的后处理方法，利用来自成对排名的专家知识来优化回归结果。给定查询项和少量已知属性的参考集，RankRefine 通过逆方差加权将基础回归器输出与基于排名的估计结合，无需重新训练。在分子性质预测任务中，仅需通过通用大语言模型（无微调）获取20次成对比较，即可实现最高10%的平均绝对误差相对降低。由于人类专家或通用大语言模型提供的排名即可在多个领域提升回归性能，RankRefine 具有实际应用价值与广泛适用性，尤其适用于低数据环境。
原文摘要 · Abstract (English)
Accurate prediction of continuous properties is essential to many scientific and engineering tasks. Although deep-learning regressors excel with abundant labels, their accuracy deteriorates in data-scarce regimes. We introduce RankRefine, a model-agnostic, plug-and-play post hoc method that refines regression with expert knowledge coming from pairwise rankings. Given a query item and a small reference set with known properties, RankRefine combines the base regressor's output with a rank-based estimate via inverse variance weighting, requiring no retraining. In molecular property prediction task, RankRefine achieves up to 10% relative reduction in mean absolute error using only 20 pairwise comparisons obtained through a general-purpose large language model (LLM) with no finetuning. As rankings provided by human experts or general-purpose LLMs are sufficient for improving regression across diverse domains, RankRefine offers practicality and broad applicability, especially in low-data settings.
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。