Neural-DISCO: Source-Conditioned Counterfactual Editing of Neural Population Activity

Computer Science > Machine Learning arXiv:2610.33145 (cs) [Submitted on 23 Oct 2026] Title: Neural-DISCO: Source-Conditioned Counterfactual Editing of Neural Population Activity Authors: Nico Policzer, James Ho, Joseph Soo, Xin Tang.

计算机科学 > 机器学习 arXiv:2610.33145 (cs) [提交于 2026 年 10 月 23 日] 标题：Neural-DISCO：神经群体活动的源条件反事实编辑 作者：Nico Policzer, James Ho, Joseph Soo, Xin Tang。

Abstract: Understanding how neural activity encodes behavioral and sensory variables is a key challenge in systems neuroscience. This requires models that go beyond predicting activity from labels and instead support source-conditioned counterfactual editing: given a recorded source response, we should be able to edit one measured behavioral or stimulus label and predict how neural activity would change while preserving other observed labels and source-specific variability not explained by the labels.

摘要：理解神经活动如何编码行为和感官变量是系统神经科学中的一个关键挑战。这需要模型超越单纯从标签预测活动的范畴，转而支持源条件反事实编辑：给定一个记录的源响应，我们应该能够编辑一个已测量的行为或刺激标签，并预测神经活动将如何变化，同时保留其他观察到的标签以及未被这些标签解释的源特定变异性。

Here, we introduce \textbf{Neural-DISCO}, a disentangled representation learning framework for counterfactual modeling of neural activity. Neural-DISCO partitions the latent space into label-specific components, each associated with an observed behavioral or stimulus label, together with a residual latent that captures variability not supplied through observed labels.

在此，我们引入了 \textbf{Neural-DISCO}，这是一个用于神经活动反事实建模的解耦表示学习框架。Neural-DISCO 将潜在空间划分为标签特定的组件，每个组件与一个观察到的行为或刺激标签相关联，并结合一个捕获未通过观察标签提供的变异性的残差潜在变量。

Across simulated and real neural recording datasets, we show that this structure enables selective editing of measured labels to generate counterfactual neural responses while preserving the remaining content of the original activity. Further, to gain insight into how behavioral and stimulus labels are encoded at single-neuron resolution, we pair this disentangled framework with feature attribution methods that identify which neurons are most important for each label.

通过模拟和真实的神经记录数据集，我们展示了这种结构能够对测量的标签进行选择性编辑，从而生成反事实的神经响应，同时保留原始活动中的其余内容。此外，为了深入了解行为和刺激标签如何在单神经元分辨率下进行编码，我们将此解耦框架与特征归因方法相结合，以识别哪些神经元对每个标签最为重要。