ABFR-KAN: Kolmogorov-Arnold Networks for Functional Brain Analysis

2026-01-01

arXiv.org

AI Summary

This study addresses the limitations of conventional graph-based brain functional connectivity analyses, which are often biased by template selection and fail to capture individual-specific characteristics, thereby compromising diagnostic reliability. To overcome these issues, the authors propose ABFR-KAN, a novel method that, for the first time, integrates Kolmogorov–Arnold Networks (KANs) into functional brain analysis. By combining a new individualized functional representation with a Transformer architecture, ABFR-KAN enables unbiased and anatomically consistent modeling of functional connectivity. Evaluated on the ABIDE I dataset for autism spectrum disorder classification, the method significantly outperforms existing approaches. Ablation studies and cross-site validation further demonstrate its robustness and generalizability.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Humans and AI: Brain-Sensing and Analysis
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Social Networks and Social Media: Fairness and bias in social network and social media analysis
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

Functional connectivity (FC) analysis, a valuable tool for computer-aided brain disorder diagnosis, traditionally relies on atlas-based parcellation. However, issues relating to selection bias and a lack of regard for subject specificity can arise as a result of such parcellations. Addressing this, we propose ABFR-KAN, a transformer-based classification network that incorporates novel advanced brain function representation components with the power of Kolmogorov-Arnold Networks (KANs) to mitigate structural bias, improve anatomical conformity, and enhance the reliability of FC estimation. Extensive experiments on the ABIDE I dataset, including cross-site evaluation and ablation studies across varying model backbones and KAN configurations, demonstrate that ABFR-KAN consistently outperforms state-of-the-art baselines for autism spectrum distorder (ASD) classification. Our code is available at https://github.com/tbwa233/ABFR-KAN.

Problem

• functional connectivity
• atlas-based parcellation
• selection bias
• subject specificity
• brain disorder diagnosis

Innovation

• Kolmogorov-Arnold Networks
• functional connectivity
• atlas-free representation
• Transformer-based classification
• brain disorder diagnosis