Exploring Subnetwork Interactions in Heterogeneous Brain Network via Prior-Informed Graph Learning

2026-03-13

AI Summary

Existing Transformer-based approaches struggle to effectively model the complex interactions among functional brain subnetworks under limited sample sizes, hindering accurate diagnosis and pathway elucidation of psychiatric disorders. To address this limitation, this work proposes KD-Brain, a novel framework that explicitly models heterogeneous brain network interactions by integrating functional semantic priors with clinical pathological knowledge. Specifically, a semantic-conditioned attention mechanism is introduced to inject prior knowledge into the query process, while a pathology consistency constraint aligns representations with established clinical insights. Evaluated across multiple psychiatric disorder diagnosis tasks, KD-Brain achieves state-of-the-art performance and identifies neurobiologically plausible and interpretable biomarkers, demonstrating its potential for both clinical translation and mechanistic understanding.

Technology Category

• Humans and AI: Brain-Sensing and Analysis
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Data Mining & Knowledge Management: Semantic Web

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

Modeling the complex interactions among functional subnetworks is crucial for the diagnosis of mental disorders and the identification of functional pathways. However, learning the interactions of the underlying subnetworks remains a significant challenge for existing Transformer-based methods due to the limited number of training samples. To address these challenges, we propose KD-Brain, a Prior-Informed Graph Learning framework for explicitly encoding prior knowledge to guide the learning process. Specifically, we design a Semantic-Conditioned Interaction mechanism that injects semantic priors into the attention query, explicitly navigating the subnetwork interactions based on their functional identities. Furthermore, we introduce a Pathology-Consistent Constraint, which regularizes the model optimization by aligning the learned interaction distributions with clinical priors. Additionally, KD-Brain leads to state-of-the-art performance on a wide range of disorder diagnosis tasks and identifies interpretable biomarkers consistent with psychiatric pathophysiology. Our code is available at https://anonymous.4open.science/r/KDBrain.

Problem

• subnetwork interactions
• heterogeneous brain network
• mental disorders
• functional pathways
• limited training samples

Innovation

• Prior-Informed Graph Learning
• Semantic-Conditioned Interaction
• Pathology-Consistent Constraint
• Subnetwork Interactions
• Interpretable Biomarkers