面向解耦表示的对比学习统一框架
Towards a Unified Framework of Contrastive Learning for Disentangled Representations
AI总结：
该研究将对比学习解耦的理论保证拓展至更广泛的对比方法家族，放宽数据分布假设，证明四种对比损失下真实隐变量的可辨识性，经基准数据集验证并探究了方法的实际局限。
摘要：
对比学习近年来已成为一种颇具前景的学习数据表示的方法，能够发现并解耦数据的解释性因子。此前对这类方法的分析大多聚焦于单个对比损失，例如噪声对比估计（NCE）和InfoNCE，且依赖于关于数据生成过程的特定假设。本文将解耦的理论保证拓展到更广泛的对比方法家族，同时放宽了对数据分布的假设。具体而言，我们证明了本文研究的四种对比损失下真实隐变量的可辨识性，且无需施加常见的独立性假设。理论发现在多个基准数据集上得到了验证。最后，本文还探究了这些方法的实际局限性。
英文摘要：
Contrastive learning has recently emerged as a promising approach for learning data representations that discover and disentangle the explanatory factors of the data. Previous analyses of such approaches have largely focused on individual contrastive losses, such as noise-contrastive estimation (NCE) and InfoNCE, and rely on specific assumptions about the data generating process. This paper extends the theoretical guarantees for disentanglement to a broader family of contrastive methods, while also relaxing the assumptions about the data distribution. Specifically, we prove identifiability of the true latents for four contrastive losses studied in this paper, without imposing common independence assumptions. The theoretical findings are validated on several benchmark datasets. Finally, practical limitations of these methods are also investigated.
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。
