• Home
  • Search
  • Graph Neural Network Learning on the Pediatric Structural Connectome.
  • https://doi.org/10.3390/tomography11020014Copy DOI Icon

Graph Neural Network Learning on the Pediatric Structural Connectome.

Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

Sex classification is a major benchmark of previous work in learning on the structural connectome, a naturally occurring brain graph that has proven useful for studying cognitive function and impairment. While graph neural networks (GNNs), specifically graph convolutional networks (GCNs), have gained popularity lately for their effectiveness in learning on graph data, achieving strong performance in adult sex classification tasks, their application to pediatric populations remains unexplored. We seek to characterize the capacity for GNN models to learn connectomic patterns on pediatric data through an exploration of training techniques and architectural design choices. Two datasets comprising an adult BRIGHT dataset (N = 147 Hodgkin's lymphoma survivors and N = 162 age similar controls) and a pediatric Human Connectome Project in Development (HCP-D) dataset (N = 135 healthy subjects) were utilized. Two GNN models (GCN simple and GCN residual), a deep neural network (multi-layer perceptron), and two standard machine learning models (random forest and support vector machine) were trained. Architecture exploration experiments were conducted to evaluate the impact of network depth, pooling techniques, and skip connections on the ability of GNN models to capture connectomic patterns. Models were assessed across a range of metrics including accuracy, AUC score, and adversarial robustness. GNNs outperformed other models across both populations. Notably, adult GNN models achieved 85.1% accuracy in sex classification on unseen adult participants, consistent with prior studies. The extension of the adult models to the pediatric dataset and training on the smaller pediatric dataset were sub-optimal in their performance. Using adult data to augment pediatric models, the best GNN achieved comparable accuracy across unseen pediatric (83.0%) and adult (81.3%) participants. Adversarial sensitivity experiments showed that the simple GCN remained the most robust to perturbations, followed by the multi-layer perceptron and the residual GCN. These findings underscore the potential of GNNs in advancing our understanding of sex-specific neurological development and disorders and highlight the importance of data augmentation in overcoming challenges associated with small pediatric datasets. Further, they highlight relevant tradeoffs in the design landscape of connectomic GNNs. For example, while the simpler GNN model tested exhibits marginally worse accuracy and AUC scores in comparison to the more complex residual GNN, it demonstrates a higher degree of adversarial robustness.

Similar Papers
  • Research Article

Towards Drug Repurposing for Leukemia: An Ensemble Graph Neural Network Model for Drug Response Prediction

  • Sep 01, 2025
  • International Journal of Artificial Intelligence Tools
  • I T Anjusha +2
  • Research Article
  • Citations27

Improved GNNs for Log D7.4 Prediction by Transferring Knowledge from Low-Fidelity Data

  • Mar 31, 2023
  • Journal of Chemical Information and Modeling
  • Yan-Jing Duan +10
  • Conference Article
  • Citations321

Exploiting Edge Features for Graph Neural Networks

  • Jun 01, 2019
  • Liyu Gong +1
  • Conference Article
  • Citations7

Knowledge Enhanced Graph Neural Networks

  • Oct 09, 2023
  • Luisa Werner +3
  • Research Article
  • Citations3

Improving drug-induced liver injury prediction using graph neural networks with augmented graph features from molecular optimisation

  • Aug 18, 2025
  • Journal of Cheminformatics
  • Taeyeub Lee +1
  • Conference Article
  • Citations2

Robust Denoising in Graph Neural Networks

  • Dec 04, 2022
  • Siying Zhang +2
  • PDF
  • Research Article
  • Citations8

Leveraging graph neural networks and neural operator techniques for high-fidelity mesh-based physics simulations

  • Nov 22, 2023
  • APL Machine Learning
  • Zeqing Jin +3
  • Conference Article
  • Citations26

Graph Neural Networks for COVID-19 Drug Discovery

  • Dec 10, 2020
  • Mark Cheung +1
  • PDF
  • Research Article
  • Citations2

Rapid and automated alloy design with graph neural network-powered large language model-driven multi-agent AI

  • Nov 01, 2025
  • MRS Bulletin
  • Alireza Ghafarollahi +1
  • PDF
  • Research Article
  • Citations63

Geometric deep learning for online prediction of cascading failures in power grids

  • Sep 01, 2023
  • Reliability Engineering & System Safety
  • Anna Varbella +2
  • Research Article

GNNBleed: Inference Attacks to Unveil Private Edges in Graphs with Realistic Access to GNN Models

  • Jul 01, 2025
  • Proceedings on Privacy Enhancing Technologies
  • Zeyu Song +2
  • Research Article
  • Citations2

Consumer phase identification in distribution grids using Graph Neural Networks based on synthetic and measured power profiles

  • Dec 01, 2025
  • Energy and AI
  • Chandra Sekhar Charan Dande +4
  • PDF
  • Research Article
  • Citations60

A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability

  • Sep 27, 2024
  • Machine Intelligence Research
  • Enyan Dai +7
  • Conference Article

Graph Representation Learning with Adaptive Mixtures

  • Dec 01, 2021
  • Da Sun Handason Tam +2
  • Research Article
  • Citations1

Research on GNNs with stable learning

  • Aug 08, 2025
  • Scientific Reports
  • Wenbin Li +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.