Graph Learning for Cross-Subject, Cross-Population EEG Emotion Decoding and Model-Derived Spatial-Spectral Neural Signatures

2026-08-13

AI Summary

This study addresses the challenges of substantial inter-subject variability and the loss of spatial-spectral structures in cross-subject and cross-population EEG emotion decoding by proposing EmoDiPyraTrans. This model introduces a novel graph learning framework integrating differential attention with pyramid fusion, leveraging adaptive graph recursion, relative power spectral density sequence modeling, and distribution regularization to achieve efficient and interpretable emotion recognition. Evaluated on benchmark datasets including SEED, it attains a state-of-the-art accuracy of 0.928 and significantly enhances transfer performance from healthy to depressed populations. Furthermore, the approach successfully identifies Alpha-band-dominant spatial-spectral neural signatures, effectively bridging generalization assessment with model interpretability.

Abstract

Cross subject emotion decoding from electroencephalography EEG requires representations that accommodate individual variability while preserving spatial spectral structure for interpretation. This study introduces EmoDiPyraTrans, a differential graph Transformer that integrates adaptive graph recurrence, differential attention, pyramid fusion and distribution regularization over sequential relative power spectral density graphs. Across SEED, FACED, MAHNOB HCI, DEAP and DREAMER, the model achieved the highest participant mean accuracy and positive class F1 among the evaluated methods, with accuracy and F1 both reaching 0.928 on SEED. On DEP EEG, positive versus neutral accuracy reached 0.802 within healthy controls and 0.704 within participants with depression, compared with 0.591 under healthy to depression transfer and 0.581 with mixed population development. Complementary SEED analyses identified distributed spatial weighting and an alpha centred spectral preference, while configurations averaging six channels retained near full performance. These findings link generalization assessment with model derived candidate signatures to support interpretable EEG emotion decoding, with code available at https://github.com/hdy6438/EmoDiPyraTrans.

Problem

• Cross-subject emotion decoding
• EEG
• Spatial-spectral structure
• Interpretability
• Cross-population generalization

Innovation

• Graph Transformer
• Cross-Subject EEG Decoding
• Differential Attention
• Pyramid Fusion
• Spatial-Spectral Signatures