用流模型特性提取数据中隐藏的结构信息，实现无模拟的表征学习。
Zero-Flow Encoders
- 基于修正流的零流准则，判断分布是否相同
- 可无模拟地学习图模型的马尔可夫毯与自监督表征
- 适用于需要精确结构推理的任务，如因果发现
基于流的方法在生成建模中取得显著成功，能捕捉复杂数据分布中的细微结构。然而，现有工作较少利用这一能力解决生成之外的精细结构问题。本文提出一种受流启发的表征学习框架：首先证明，若源分布与目标分布相同，则独立耦合训练的修正流在 t=0.5 处为零，我们称此性质为“零流准则”；其次，该准则可验证条件独立性，从而提取数据中的充分信息；最后，将该准则转化为可计算、无需模拟的损失函数，实现图模型中马尔可夫毯与自监督学习中潜在表征的推断。在模拟和真实数据集上的实验验证了方法的有效性。代码见：https://github.com/probabilityFLOW/zfe。
原文摘要 · Abstract (English)
Flow-based methods have achieved significant success in various generative modeling tasks, capturing nuanced details within complex data distributions. However, few existing works have exploited this unique capability to resolve fine-grained structural details beyond generation tasks. This paper presents a flow-inspired framework for representation learning. First, we demonstrate that a rectified flow trained using independent coupling is zero everywhere at $t=0.5$ if and only if the source and target distributions are identical. We term this property the \emph{zero-flow criterion}. Second, we show that this criterion can certify conditional independence, thereby extracting \emph{sufficient information} from the data. Third, we translate this criterion into a tractable, simulation-free loss function that enables learning amortized Markov blankets in graphical models and latent representations in self-supervised learning tasks. Experiments on both simulated and real-world datasets demonstrate the effectiveness of our approach. The code reproducing our experiments can be found at: https://github.com/probabilityFLOW/zfe.
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。