MEDNet: Multi-level Expert Disentangled Network For EEG Classification

doi:10.1007/978-981-95-4381-6_3

MEDNet: Multi-level Expert Disentangled Network For EEG Classification

2026-01-01

0

PRE

AI

DOI：10.1007/978-981-95-4381-6_3

Original

Original request for help

Save

Abstract

En 中文

Electroencephalogram (EEG) offers insights into brain function for conditions like Attention Deficit Hyperactivity Disorder (ADHD). Accurate diagnosis is critical, yet existing EEG methods struggle with capturing multi-faceted frequency-band characteristics, complex long-range spatio-temporal dynamics, and avoiding redundant feature learning. We propose Multi-level Expert Disentangled Network (MEDNet), a novel architecture addressing these challenges. MEDNet integrates dedicated multi-expert layers: one for adaptive frequency-band feature extraction, and another utilizing Mamba for efficient temporal modeling and a learnable graph for spatial relationships. An expert disentanglement loss is introduced to ensure learned features are diverse and complementary. Extensive experiments on the DEEG-ADHD dataset demonstrate MEDNet achieves state-of-the-art performance, outperforming existing methods. Ablation studies confirm the contribution of each proposed component.

Keywords:

Electroencephalogram (EEG)

Selective State Space Models

Mixture of Experts

MEDNet: Multi-level Expert Disentangled Network For EEG Classification

Abstract

Journal

Organization