Home / cuhk-aim-group / neurodiscovery · GitHub

lggnn SKILL.md skillA

lggnn from cuhk-aim-group/neurodiscovery is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add cuhk-aim-group/neurodiscovery/lggnn@git:20260519.c62dcfb

Pins git:20260519.c62dcfb in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: cuhk-aim-group/neurodiscovery
Path: skills/lggnn/SKILL.md
Versions recorded: 1
Latest version: git:20260519.c62dcfb, committed May 19, 2026
Size: 5,467 bytes
Repository stars: 93
License: MIT

Use this model doc whenever the user wants to run LG-GNN (Local-to-Global GNN) for fMRI phenotype prediction. LG-GNN is a PyG-based GNN with SABP (Self-Attention Brain Pooling) and mutual-information regularization. NeuroClaw adapts the original population-graph version to single-subject brain graphs.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# LG-GNN Model Doc

## Overview
LG-GNN (Local-to-Global GNN) 是一种针对脑疾病诊断的两阶段图神经网络。原始论文使用 Local_GNN 提取每个被试的脑图嵌入，再通过基于人口学信息构建的 Global_GNN 进行人群图分类。NeuroClaw 改造为单被试任务：保留 Local_GNN（含 SABP + 互信息正则化的创新组件），用 MLP head 替代人口图。

- Paper: Zhang et al., 2022, "Local to Global Hierarchical Graph Neural Network for Brain Disorder Diagnosis"，MICCAI
- Official code: https://github.com/cnuzh/LG-GNN
- NeuroClaw reimplementation: `models/lggnn/`（去除人口图依赖，单被试 PyG 流程）
- Primary input: PyG Data graph（与 BrainGNN 共享数据格式）
- Primary output: phenotype prediction + ROI 重要性（SABP perm）+ MI loss 辅助监督

**Research use only.**

---

## NeuroClaw 实现要点

1. **单被试改造**：原版需要非影像表型数据构建人口图，NeuroClaw 仅保留 Local_GNN，用 MLP head 输出。
2. **SABP 池化**：Self-Attention Brain Pooling，topk 选择 ROI + tanh(score) 加权，并产生互信息估计 `mi` 作为辅助 loss（论文权重 0.1，loss 取 `loss - 0.1 * mi` 鼓励高互信息）。
3. **PyG 2.7 兼容**：原 `torch_geometric.nn.pool.topk_pool` 已重构，NeuroClaw 用 `pool.select.topk` + 内联 `filter_adj`。
4. **任务统一接口**：classification (`nclass=N`) 与 regression (`nclass=1, task='regression'`) 一套代码。
5. **数据复用**：直接复用 BrainGNN 的 `NeuroClawFCDataset`，无需额外预处理。

---

## Quick Start (NeuroClaw 内部)

### 前置条件
- conda env: `neuroclaw` (Python 3.11)
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add cuhk-aim-group/neurodiscovery/lggnn@sha256:83afaf08dc3b8a89

The line at the top of this page pins the label git:20260519.c62dcfb, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_snuwp3vjiigqrcui.svg)](https://markdownregistry.com/a/art_snuwp3vjiigqrcui)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on May 19, 2026.

version	committed	commit	size	audit
git:20260519.c62dcfb latest	2026-05-19	c62dcfb	5,467 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (5467 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

cuhk-aim-group/neurodiscovery · 93 stars · license MIT · pushed 2026-10-23 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_snuwp3vjiigqrcui
GET https://markdownregistry.com/api/v1/resolve?ref=cuhk-aim-group/neurodiscovery/lggnn
GET https://markdownregistry.com/api/v1/blob/83afaf08dc3b8a898d6355a3b1122c8ac387345e42bd35a63e1c17fa51a10102

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.