MvHo-IB: Multi-View Higher-Order Information Bottleneck for Brain Disorder Diagnosis

TL;DR

This paper introduces MvHo-IB, a multi-view learning framework that effectively models higher-order interactions in fMRI data, improving brain disorder diagnosis accuracy through innovative information bottleneck techniques.

Contribution

The paper presents a novel framework combining higher-order interaction modeling with an information bottleneck approach for improved diagnostic performance.

Findings

Achieves state-of-the-art results on three benchmark datasets.

Outperforms existing hypergraph-based methods.

Effectively extracts and utilizes higher-order interactions in fMRI data.

Abstract

Recent evidence suggests that modeling higher-order interactions (HOIs) in functional magnetic resonance imaging (fMRI) data can enhance the diagnostic accuracy of machine learning systems. However, effectively extracting and utilizing HOIs remains a significant challenge. In this work, we propose MvHo-IB, a novel multi-view learning framework that integrates both pairwise interactions and HOIs for diagnostic decision-making, while automatically compressing task-irrelevant redundant information. MvHo-IB introduces several key innovations: (1) a principled method that combines O-information from information theory with a matrix-based Renyi alpha-order entropy estimator to quantify and extract HOIs, (2) a purpose-built Brain3DCNN encoder to effectively utilize these interactions, and (3) a new multi-view learning information bottleneck objective to enhance representation learning. Experiments on three benchmark fMRI datasets demonstrate that MvHo-IB achieves state-of-the-art performance, significantly outperforming previous methods, including recent hypergraph-based techniques. The implementation of MvHo-IB is available at https://github.com/zky04/MvHo-IB.