BrainNetMLP: An Efficient and Effective Baseline for Functional Brain Network Classification

TL;DR

BrainNetMLP introduces a simple yet effective MLP-based approach for classifying functional brain networks, achieving state-of-the-art results with fewer parameters and efficient computation by capturing spatial and spectral features.

Contribution

This paper presents BrainNetMLP, a novel pure MLP architecture with a dual-branch structure for brain network classification, challenging the notion that complex models are necessary for high accuracy.

Findings

Achieves state-of-the-art performance on HCP and ABIDE datasets.

Demonstrates MLP's potential as an efficient alternative to complex models.

Validates the effectiveness of dual-branch structure for feature fusion.

Abstract

Recent studies have made great progress in functional brain network classification by modeling the brain as a network of Regions of Interest (ROIs) and leveraging their connections to understand brain functionality and diagnose mental disorders. Various deep learning architectures, including Convolutional Neural Networks, Graph Neural Networks, and the recent Transformer, have been developed. However, despite the increasing complexity of these models, the performance gain has not been as salient. This raises a question: Does increasing model complexity necessarily lead to higher classification accuracy? In this paper, we revisit the simplest deep learning architecture, the Multi-Layer Perceptron (MLP), and propose a pure MLP-based method, named BrainNetMLP, for functional brain network classification, which capitalizes on the advantages of MLP, including efficient computation and fewer parameters. Moreover, BrainNetMLP incorporates a dual-branch structure to jointly capture both spatial connectivity and spectral information, enabling precise spatiotemporal feature fusion. We evaluate our proposed BrainNetMLP on two public and popular brain network classification datasets, the Human Connectome Project (HCP) and the Autism Brain Imaging Data Exchange (ABIDE). Experimental results demonstrate pure MLP-based methods can achieve state-of-the-art performance, revealing the potential of MLP-based models as more efficient yet effective alternatives in functional brain network classification. The code will be available at https://github.com/JayceonHo/BrainNetMLP.