task-aware-brain-connectivity

Learn task-aware brain connectivity from fMRI time-series using DAG-based graph learning.

2|Updated Feb 12, 2026
One-click install
npx skills add https://github.com/hiyenwong/ai_collection --skill task-aware-brain-connectivity
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: task-aware-brain-connectivity
Source: https://github.com/hiyenwong/ai_collection/tree/main/collection/skills/task-aware-brain-connectivity
Command: npx skills add https://github.com/hiyenwong/ai_collection --skill task-aware-brain-connectivity

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Researchers need robust methods to learn task-aware brain connectivity from fMRI time-series for downstream predictive tasks such as cognitive state classification or neurological disorder diagnosis.

Core Features & Use Cases

  • DAG learning: Convert time-series into directed acyclic graph structures to capture causal brain interactions.
  • Task-aware optimization: Jointly optimize connectivity learning with downstream prediction tasks using contrastive regularization.
  • Graph neural encoder: Use a GNN to encode brain graphs and derive task-relevant embeddings for classification or regression.
  • Use Case: Useful for fMRI analysis, brain network modeling, and diagnosis prediction in neuroscience research.

Quick Start

Provide your fMRI time-series data to TBDS and run a basic training pipeline to obtain task-aware connectivity embeddings.

Frequently Asked Questions about task-aware-brain-connectivity

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I learn task-aware brain connectivity from fMRI time-series data?

Task-aware brain connectivity models directed acyclic graph structures from fMRI data to capture causal brain interactions, which static correlation-based brain networks fail to represent for cognitive state classification.

How do I convert fMRI time-series into directed acyclic graph structures for brain network modeling?

DAG learning converts fMRI time-series into directed acyclic graph structures by processing inputs shaped as (batch, n_rois, time_steps) to capture directed causal brain interactions across regions of interest.

Do I need PyTorch Geometric to run task-aware brain network modeling?

Yes, task-aware brain network modeling requires a PyTorch-based environment with PyTorch Geometric installed to support the GNN encoder and the underlying DAG-based graph learning pipeline.

What is the best way to optimize brain connectivity learning with downstream prediction tasks?

The best way is task-aware optimization, which jointly optimizes directed acyclic graph connectivity learning with downstream prediction tasks using contrastive regularization to ensure task-relevant embeddings.

What format should fMRI inputs be for task-aware brain network extraction?

fMRI inputs for task-aware brain network extraction must be shaped as (batch, n_rois, time_steps) to properly feed into the DAG learning pipeline and generate adjacency matrices alongside multiple loss terms.

What outputs do I get from task-aware brain connectivity modeling?

Task-aware brain connectivity modeling outputs classification logits, task-relevant embeddings, the learned adjacency matrix representing brain connectivity, and multiple loss terms for monitoring the joint optimization process.