Salvato in:
Dettagli Bibliografici
Autori principali: Li, Yubin, Liu, Xingyu, Chen, Guozhang
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2505.13011
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916760142217216
author Li, Yubin
Liu, Xingyu
Chen, Guozhang
author_facet Li, Yubin
Liu, Xingyu
Chen, Guozhang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_13011
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Unveiling and Steering Connectome Organization with Interpretable Latent Variables
Li, Yubin
Liu, Xingyu
Chen, Guozhang
Artificial Intelligence
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.
title Unveiling and Steering Connectome Organization with Interpretable Latent Variables
topic Artificial Intelligence
url https://arxiv.org/abs/2505.13011