Analysis of the generalization ability of graph neural networks in cross-subject EEG emotion recognition
Neurological Sciences · 2026
DOI: 10.1007/s10072-026-08835-6 ↗Kurz gefasst
Fachartikel in der Zeitschrift Neurological Sciences, 2026. Verfasst von Lingyue Wang und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Health Sciences and Biomedical Engineering, Hebei University of Technology, Tianjin, 300401, China. Hauptthemen laut MEDLINE: Graph Neural Networks, Emotions, Electroencephalography, Signal Processing, Computer-Assisted. Die Arbeit nennt 34 Literaturangaben.
Abstract (Originalsprache)
BACKGROUND: Emotion decoding from Electroencephalography (EEG) remains limited by cross-subject variability and low structural generalisation. This study aimed to develop a calibration-free (inference without per-subject retraining), entropy-guided graph neural network (EGGN) to enhance accuracy, Architectural interpretability, and fairness in EEG-based emotion recognition. METHODS: We used the Shanghai Jiao Tong University Emotion EEG Dataset (SEED) (n = 15, 3 sessions, 62 channels) and the Database for Emotion Analysis using Physiological Signals (DEAP) (n = 32, 40 trials, 32 channels) datasets, segmented into 3-s epochs with a sampling rate of 128 Hz. Models included Graph Convolutional Network (GCN), Transformer, and Entropy-Guided Graph Neural Network (EGGN), trained using 10-fold cross-validation. Graph edges were derived via entropy gradients; dual-attention pooling and fairness metrics were applied. Saliency and graph fingerprint analyses were performed on SEED; calibration-free and meta-learning evaluations were conducted on DEAP. RESULTS: EGGN achieved the highest accuracy: 84.2% (valence) and 83.1% (arousal) on SEED, outperforming Transformer (80.5%, 79.8%) and GCN (78.1%, 76.4%). Entropy-based edge modelling improved accuracy by 2.8–3.9%; dual-attention pooling further increased accuracy (+ 3.6–4.1%) and Neuropsychological Alignment Score (NAS) defined by cosine similarity between predicted saliency maps and established emotion-related brain regions (+ 0.14–0.17). Fairness metrics showed minimal gender bias (Disparate Impact Ratio (DIR) = 0.97; Equal Opportunity Difference (EOD) = –1.1%). Graph similarity peaked at 0.74 for high arousal (SEED–DEAP); Uniform Manifold Approximation and Projection (UMAP) silhouette score was 0.64. Calibration-free inference yielded a minor performance drop (EGGN Δ = –1.4% to –0.8%). CONCLUSION: EGGN enables robust, interpretable, and fair emotion decoding from electroencephalography across subjects and datasets.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Health Sciences and Biomedical Engineering, Hebei University of Technology, Tianjin, 300401, China.
- School of Electrical Engineering, Hebei University of Technology, Tianjin, 300401, China.
- School of Health Sciences and Biomedical Engineering, Hebei University of Technology, Tianjin, 300401, China. liying_hebut_tj@163.com.
Zitieren
APA
Wang, L., Guo, L., Yang, X., & Li, Y. (2026). Analysis of the generalization ability of graph neural networks in cross-subject EEG emotion recognition. Neurological Sciences. https://doi.org/10.1007/s10072-026-08835-6
Vancouver
Wang L, Guo L, Yang X, Li Y. Analysis of the generalization ability of graph neural networks in cross-subject EEG emotion recognition. Neurological Sciences. 2026. doi:10.1007/s10072-026-08835-6
BibTeX
@article{Wang2026,
author = {Wang, Lingyue and Guo, Lei and Yang, Xinsheng and Li, Ying},
title = {Analysis of the generalization ability of graph neural networks in cross-subject EEG emotion recognition},
journal = {Neurological Sciences},
year = {2026},
doi = {10.1007/s10072-026-08835-6}
}
EUVIMED