arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.26261cs.LGstat.ML
收藏

对比性符合集

Contrastive Conformal Sets

School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore(南洋理工大学电气与电子工程学院)

Yahya Alkhatib, Wee Peng Tay

AI总结:

本文提出一种基于对比学习的符合集方法,通过最小体积覆盖集和可学习多范数约束,实现对正样本的覆盖和负样本的排除,提升了在图像数据集上的包含-排除平衡。

摘要:

对比学习通过鼓励正样本聚类紧密而分离负样本生成一致的语义特征嵌入。然而,现有对比学习方法缺乏对语义特征空间内覆盖的原理性保证。我们通过引入最小体积覆盖集并配备可学习的广义多范数约束,将符合预测扩展到此设定。我们提出了一种方法,构造符合集以保证用户指定的正样本覆盖同时最大化负样本排除。我们理论证明体积最小化作为负样本排除的代理,使我们的方法即使在负样本不可用时也能有效运作。正样本包含保证继承了符合预测的分布无关覆盖性质,而负样本排除则通过在预留训练集上优化学习的集合几何来最大化。在模拟和真实世界图像数据集上的实验表明,与标准距离基线相比,改进了包含-排除权衡。

英文摘要:

Contrastive learning produces coherent semantic feature embeddings by encouraging positive samples to cluster closely while separating negative samples. However, existing contrastive learning methods lack a principled construction of geometric sets in the semantic feature space with distribution-free guarantees at any user-specified coverage level. We extend conformal prediction to this setting by introducing covering sets equipped with learnable generalized hyper-ball constraints. We propose a method that constructs conformal sets guaranteeing user-specified coverage of positive samples while maximizing negative sample exclusion. We theoretically motivate volume minimization as a proxy for negative exclusion, enabling our approach to operate effectively even when negative pairs are unavailable. The positive inclusion guarantee inherits the distribution-free coverage property of conformal prediction, while negative exclusion is maximized through learned set geometry optimized on a held-out training split. Experiments on simulated and real-world image datasets demonstrate improved inclusion-exclusion trade-offs compared to standard distance-based conformal baselines.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑