arXiv cs.AI· Robert Bain, Marjan Rashidi, Elizabeth Chrastil·· 12 小时前AI 评分36
成对学习提升深度神经网络的数据效率
Pairwise Learning Increases Data Efficiency in Deep Neural Networks
AI 导读
研究者提出成对比较框架，将回归任务重构为聚合相对排序，在多种模型架构和数据集规模上提升数据效率。在 UTKFace（23k 图像）上，该方法无需额外监督即生成超 10 亿条训练比较，使家用硬件从零训练的轻量 ResNet10 达到 3.64 年 MAE，超过包括大规模预训练在内的此前模型。
正文 · 原文
Abstract:Deep neural networks often fail at small-sample regression, collapsing to low-variance predictions that miss individual differences. Here, we introduce a pairwise comparison framework that reframes regression as aggregated relative rankings. This method improves data efficiency across model architectures and dataset sizes. On the UTKFace dataset (23k images), pairwise learning generates over one billion training comparisons without additional supervision. The paired ranking allows a lightweight ResNet10 trained from scratch on home hardware to achieve a 3.64-year MAE-surpassing previous models, including those with large-scale pretraining. For classification into categories, pairwise supervision consistently outperforms an otherwise identical 10-way crossentropy model on STL10 with 500-2000 labeled examples, improving accuracy by up to 5.2%. Overall, pairwise supervision enhances data efficiency and enables strong regression and classification performance when labeled data are limited, particularly in clinical settings.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2610.27669 [cs.LG] |
| (or arXiv:2610.27669v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.27669 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Robert Bain [view email]
[v1]
Tue, 20 Oct 2026 05:34:16 UTC (1,215 KB)
来源：arXiv cs.AI · arxiv.org