DAMSDAN: Distribution-Aware Multi-Source Domain Adaptation Network for Cross-Domain EEG-based Emotion Recognition

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hu, Fo, Wang, Can, Zheng, Qinxu, Yang, Xusheng, Zhou, Bin, Li, Gang, Sun, Yu, Zhang, Wen-an
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915563639406592
author Hu, Fo
Wang, Can
Zheng, Qinxu
Yang, Xusheng
Zhou, Bin
Li, Gang
Sun, Yu
Zhang, Wen-an
author_facet Hu, Fo
Wang, Can
Zheng, Qinxu
Yang, Xusheng
Zhou, Bin
Li, Gang
Sun, Yu
Zhang, Wen-an
contents Significant inter-individual variability limits the generalization of EEG-based emotion recognition under cross-domain settings. We address two core challenges in multi-source adaptation: (1) dynamically modeling distributional heterogeneity across sources and quantifying their relevance to a target to reduce negative transfer; and (2) achieving fine-grained semantic consistency to strengthen class discrimination. We propose a distribution-aware multi-source domain adaptation network (DAMSDAN). DAMSDAN integrates prototype-based constraints with adversarial learning to drive the encoder toward discriminative, domain-invariant emotion representations. A domain-aware source weighting strategy based on maximum mean discrepancy (MMD) dynamically estimates inter-domain shifts and reweights source contributions. In addition, a prototype-guided conditional alignment module with dual pseudo-label interaction enhances pseudo-label reliability and enables category-level, fine-grained alignment, mitigating noise propagation and semantic drift. Experiments on SEED and SEED-IV show average accuracies of 94.86\% and 79.78\% for cross-subject, and 95.12\% and 83.15\% for cross-session protocols. On the large-scale FACED dataset, DAMSDAN achieves 82.88\% (cross-subject). Extensive ablations and interpretability analyses corroborate the effectiveness of the proposed framework for cross-domain EEG-based emotion recognition.
format Preprint
id arxiv_https___arxiv_org_abs_2510_17475
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DAMSDAN: Distribution-Aware Multi-Source Domain Adaptation Network for Cross-Domain EEG-based Emotion Recognition
Hu, Fo
Wang, Can
Zheng, Qinxu
Yang, Xusheng
Zhou, Bin
Li, Gang
Sun, Yu
Zhang, Wen-an
Machine Learning
Artificial Intelligence
Significant inter-individual variability limits the generalization of EEG-based emotion recognition under cross-domain settings. We address two core challenges in multi-source adaptation: (1) dynamically modeling distributional heterogeneity across sources and quantifying their relevance to a target to reduce negative transfer; and (2) achieving fine-grained semantic consistency to strengthen class discrimination. We propose a distribution-aware multi-source domain adaptation network (DAMSDAN). DAMSDAN integrates prototype-based constraints with adversarial learning to drive the encoder toward discriminative, domain-invariant emotion representations. A domain-aware source weighting strategy based on maximum mean discrepancy (MMD) dynamically estimates inter-domain shifts and reweights source contributions. In addition, a prototype-guided conditional alignment module with dual pseudo-label interaction enhances pseudo-label reliability and enables category-level, fine-grained alignment, mitigating noise propagation and semantic drift. Experiments on SEED and SEED-IV show average accuracies of 94.86\% and 79.78\% for cross-subject, and 95.12\% and 83.15\% for cross-session protocols. On the large-scale FACED dataset, DAMSDAN achieves 82.88\% (cross-subject). Extensive ablations and interpretability analyses corroborate the effectiveness of the proposed framework for cross-domain EEG-based emotion recognition.
title DAMSDAN: Distribution-Aware Multi-Source Domain Adaptation Network for Cross-Domain EEG-based Emotion Recognition
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2510.17475