Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Exploring General Intelligence via Gated Graph Transformer in Functional Connectivity Studies

Gang Qu, Anton Orlichenko, Junqi Wang, Gemeng Zhang, Li Xiao, Aiying Zhang, Zhengming Ding, Yu-Ping Wang

TL;DR

This work addresses the limitation of requiring predefined graphs in FC-based brain analysis by proposing GGT, a gated graph transformer that uses FC-derived graphs with learnable position encodings to predict cognitive metrics. It combines attention-based message passing with edge-aware gating and random-walk inspired position encoding, evaluated on the PNC to predict WRAT scores, outperforming several baselines. The attention maps offer interpretable biomarkers linking WRAT-related cognitive processes to networks such as AUD, VIS, MEM, DFN, and SUB across multiple tasks. The approach integrates spatial brain knowledge with advanced neural architectures to advance general intelligence modeling from functional connectivity data.

Abstract

Functional connectivity (FC) as derived from fMRI has emerged as a pivotal tool in elucidating the intricacies of various psychiatric disorders and delineating the neural pathways that underpin cognitive and behavioral dynamics inherent to the human brain. While Graph Neural Networks (GNNs) offer a structured approach to represent neuroimaging data, they are limited by their need for a predefined graph structure to depict associations between brain regions, a detail not solely provided by FCs. To bridge this gap, we introduce the Gated Graph Transformer (GGT) framework, designed to predict cognitive metrics based on FCs. Empirical validation on the Philadelphia Neurodevelopmental Cohort (PNC) underscores the superior predictive prowess of our model, further accentuating its potential in identifying pivotal neural connectivities that correlate with human cognitive processes.

Exploring General Intelligence via Gated Graph Transformer in Functional Connectivity Studies

TL;DR

This work addresses the limitation of requiring predefined graphs in FC-based brain analysis by proposing GGT, a gated graph transformer that uses FC-derived graphs with learnable position encodings to predict cognitive metrics. It combines attention-based message passing with edge-aware gating and random-walk inspired position encoding, evaluated on the PNC to predict WRAT scores, outperforming several baselines. The attention maps offer interpretable biomarkers linking WRAT-related cognitive processes to networks such as AUD, VIS, MEM, DFN, and SUB across multiple tasks. The approach integrates spatial brain knowledge with advanced neural architectures to advance general intelligence modeling from functional connectivity data.

Abstract

Functional connectivity (FC) as derived from fMRI has emerged as a pivotal tool in elucidating the intricacies of various psychiatric disorders and delineating the neural pathways that underpin cognitive and behavioral dynamics inherent to the human brain. While Graph Neural Networks (GNNs) offer a structured approach to represent neuroimaging data, they are limited by their need for a predefined graph structure to depict associations between brain regions, a detail not solely provided by FCs. To bridge this gap, we introduce the Gated Graph Transformer (GGT) framework, designed to predict cognitive metrics based on FCs. Empirical validation on the Philadelphia Neurodevelopmental Cohort (PNC) underscores the superior predictive prowess of our model, further accentuating its potential in identifying pivotal neural connectivities that correlate with human cognitive processes.
Paper Structure (6 sections, 2 equations, 1 figure, 1 table)

This paper contains 6 sections, 2 equations, 1 figure, 1 table.

Table of Contents

  1. Introduction
  2. Methods
  3. Experiments
  4. Conclusion
  5. Potential Negative Societal Impact
  6. Acknowledgements

Figures (1)

  • Figure 1: Average heatmap generated using the attention scores (left) and brain functional networks with high attention scores (right). SUB: Subcortical, VIS: Visual, MEM: Memory Retrieval, DFN: Default Mode, AUD: Auditory, SM: Sensory/somatomotor.