Saved in:
Bibliographic Details
Main Authors: Zhu, Hongyu, Chen, Lin, Shang, Mingsheng
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.29205
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910088202027008
author Zhu, Hongyu
Chen, Lin
Shang, Mingsheng
author_facet Zhu, Hongyu
Chen, Lin
Shang, Mingsheng
contents Multimodal Sentiment Analysis (MSA) that integrates Electroencephalogram (EEG) with peripheral physiological signals (PPS) is crucial for the development of brain-computer interface (BCI) systems. However, existing methods encounter three major challenges: (1) overlooking the region-specific characteristics of affective processing by treating EEG signals as homogeneous; (2) treating EEG as a black-box input, which lacks interpretability into neural representations;(3) ineffective fusion of EEG features with complementary PPS features. To overcome these issues, we propose BiMoE, a novel brain-inspired mixture of experts framework. BiMoE partitions EEG signals in a brain-topology-aware manner, with each expert utilizing a dual-stream encoder to extract local and global spatiotemporal features. A dedicated expert handles PPS using multi-scale large-kernel convolutions. All experts are dynamically fused through adaptive routing and a joint loss function. Evaluated under strict subject-independent settings, BiMoE consistently surpasses state-of-the-art baselines across various affective dimensions. On the DEAP and DREAMER datasets, it yields average accuracy improvements of 0.87% to 5.19% in multimodal sentiment classification. The code is available at: https://github.com/HongyuZhu-s/BiMo.
format Preprint
id arxiv_https___arxiv_org_abs_2603_29205
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle BiMoE: Brain-Inspired Experts for EEG-Dominant Affective State Recognition
Zhu, Hongyu
Chen, Lin
Shang, Mingsheng
Human-Computer Interaction
Multimodal Sentiment Analysis (MSA) that integrates Electroencephalogram (EEG) with peripheral physiological signals (PPS) is crucial for the development of brain-computer interface (BCI) systems. However, existing methods encounter three major challenges: (1) overlooking the region-specific characteristics of affective processing by treating EEG signals as homogeneous; (2) treating EEG as a black-box input, which lacks interpretability into neural representations;(3) ineffective fusion of EEG features with complementary PPS features. To overcome these issues, we propose BiMoE, a novel brain-inspired mixture of experts framework. BiMoE partitions EEG signals in a brain-topology-aware manner, with each expert utilizing a dual-stream encoder to extract local and global spatiotemporal features. A dedicated expert handles PPS using multi-scale large-kernel convolutions. All experts are dynamically fused through adaptive routing and a joint loss function. Evaluated under strict subject-independent settings, BiMoE consistently surpasses state-of-the-art baselines across various affective dimensions. On the DEAP and DREAMER datasets, it yields average accuracy improvements of 0.87% to 5.19% in multimodal sentiment classification. The code is available at: https://github.com/HongyuZhu-s/BiMo.
title BiMoE: Brain-Inspired Experts for EEG-Dominant Affective State Recognition
topic Human-Computer Interaction
url https://arxiv.org/abs/2603.29205