用可解释的潜在变量揭示果蝇脑图谱的组织规律并可控生成子图。
Unveiling and Steering Connectome Organization with Interpretable Latent Variables
- 从果蝇脑图谱中提取子图，用生成模型学习其低维可解释表示。
- 通过潜变量控制，能按需生成具有特定结构特征的神经回路子图。
- 方法可揭示结构与功能关联，适合脑科学和类脑智能研究者。
大脑复杂的连接组（connectome）是其功能的蓝图，尽管结构极其复杂，却源于简短的遗传编码，暗示其背后存在低维组织原则。本文将连接组学与表征学习结合，提出一种框架：从果蝇连接组数据集 FlyWire 中提取子图，并利用生成模型获得神经回路的可解释低维表示。关键创新在于引入可解释模块，将这些潜在维度与具体结构特征关联，揭示其功能意义。我们验证了该方法在图重建上的有效性，并进一步展示了通过操控潜变量，可可控生成具备预设属性的连接组子图。这项研究为理解脑架构提供了新工具，也为设计生物启发的人工神经网络开辟了可能路径。
原文摘要 · Abstract (English)
The brain's intricate connectome, a blueprint for its function, presents immense complexity, yet it arises from a compact genetic code, hinting at underlying low-dimensional organizational principles. This work bridges connectomics and representation learning to uncover these principles. We propose a framework that combines subgraph extraction from the Drosophila connectome, FlyWire, with a generative model to derive interpretable low-dimensional representations of neural circuitry. Crucially, an explainability module links these latent dimensions to specific structural features, offering insights into their functional relevance. We validate our approach by demonstrating effective graph reconstruction and, significantly, the ability to manipulate these latent codes to controllably generate connectome subgraphs with predefined properties. This research offers a novel tool for understanding brain architecture and a potential avenue for designing bio-inspired artificial neural networks.
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。