Information Bottleneck-Guided Heterogeneous Graph Learning for Interpretable Neurodevelopmental Disorder Diagnosis

2025-02-28

AI Summary

To address the challenge of interpretable modeling for multimodal data—specifically fMRI and non-imaging clinical/behavioral data—in neurodevelopmental disorder (NDD) diagnosis, this paper proposes an information-bottleneck-guided heterogeneous graph neural network framework. Under connectomic constraints, it jointly models local functional connectivity patterns and global cross-modal interactions via heterogeneous graph attention and graph Transformers, enabling fine-grained biomarker extraction and quantitative feature attribution. Key contributions include: (i) the first integration of information bottleneck theory into heterogeneous graph learning to jointly enforce representation compression and interpretability; (ii) explicit disentanglement of fMRI functional connectivity subnetworks with clinically meaningful semantic annotations; and (iii) simultaneous provision of verifiable explanations for both imaging and non-imaging features. The method achieves state-of-the-art performance on NDD diagnosis tasks, delivering both high accuracy and strong model interpretability.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Developing interpretable models for diagnosing neurodevelopmental disorders (NDDs) is highly valuable yet challenging, primarily due to the complexity of encoding, decoding and integrating imaging and non-imaging data. Many existing machine learning models struggle to provide comprehensive interpretability, often failing to extract meaningful biomarkers from imaging data, such as functional magnetic resonance imaging (fMRI), or lacking mechanisms to explain the significance of non-imaging data. In this paper, we propose the Interpretable Information Bottleneck Heterogeneous Graph Neural Network (I2B-HGNN), a novel framework designed to learn from fine-grained local patterns to comprehensive global multi-modal interactions. This framework comprises two key modules. The first module, the Information Bottleneck Graph Transformer (IBGraphFormer) for local patterns, integrates global modeling with brain connectomic-constrained graph neural networks to identify biomarkers through information bottleneck-guided pooling. The second module, the Information Bottleneck Heterogeneous Graph Attention Network (IB-HGAN) for global multi-modal interactions, facilitates interpretable multi-modal fusion of imaging and non-imaging data using heterogeneous graph neural networks. The results of the experiments demonstrate that I2B-HGNN excels in diagnosing NDDs with high accuracy, providing interpretable biomarker identification and effective analysis of non-imaging data.

Problem

• Develop interpretable models for neurodevelopmental disorder diagnosis
• Integrate imaging and non-imaging data effectively
• Identify meaningful biomarkers using advanced graph neural networks

Innovation

• Information Bottleneck-guided pooling for biomarker identification
• Heterogeneous Graph Neural Networks for multi-modal data fusion
• Interpretable framework combining local and global data patterns