FreqDGT: Frequency-Adaptive Dynamic Graph Networks with Transformer for Cross-subject EEG Emotion Recognition

TL;DR

FreqDGT introduces a novel frequency-adaptive dynamic graph transformer that enhances cross-subject EEG emotion recognition by integrating frequency weighting, adaptive connectivity, and hierarchical temporal modeling, achieving significant accuracy improvements.

Contribution

It presents a new framework combining frequency-adaptive processing, dynamic graph learning, and multi-scale temporal disentanglement for robust cross-subject EEG emotion recognition.

Findings

Significantly improves cross-subject emotion recognition accuracy.

Effectively models temporal dynamics and individual variability.

Demonstrates robustness through comprehensive experiments.

Abstract

Electroencephalography (EEG) serves as a reliable and objective signal for emotion recognition in affective brain-computer interfaces, offering unique advantages through its high temporal resolution and ability to capture authentic emotional states that cannot be consciously controlled. However, cross-subject generalization remains a fundamental challenge due to individual variability, cognitive traits, and emotional responses. We propose FreqDGT, a frequency-adaptive dynamic graph transformer that systematically addresses these limitations through an integrated framework. FreqDGT introduces frequency-adaptive processing (FAP) to dynamically weight emotion-relevant frequency bands based on neuroscientific evidence, employs adaptive dynamic graph learning (ADGL) to learn input-specific brain connectivity patterns, and implements multi-scale temporal disentanglement network (MTDN) that combines hierarchical temporal transformers with adversarial feature disentanglement to capture both temporal dynamics and ensure cross-subject robustness. Comprehensive experiments demonstrate that FreqDGT significantly improves cross-subject emotion recognition accuracy, confirming the effectiveness of integrating frequency-adaptive, spatial-dynamic, and temporal-hierarchical modeling while ensuring robustness to individual differences. The code is available at https://github.com/NZWANG/FreqDGT.