Domain-Invariant Adaptive Graph Regularized Label Propagation for EEG-Based Emotion Recognition

Abstract

Emotion recognition holds significant potential for various real-world applications due to its reliability and precision. Nevertheless, variations in EEG patterns among individuals restrict the ability of emotion classifiers to generalize across different people. Furthermore, the non-stationary nature of EEG signals implies that a subject’s data can vary over time, posing a challenge in developing models effective across multiple sessions. This paper introduces a novel domain adaptation (DA) method designed to generalize emotion recognition models across both individuals and sessions. Current mainstream DA methods primarily focus on learning discriminative domain-invariant feature (DIF) representations by integrating the “pseudo labels” of the target domain to enhance knowledge transfer. However, most approaches treat the optimization of domain-invariant features and the updating of target “pseudo labels” as two separate stages, making it challenging to achieve optimal learning performance. To address this, we propose a joint Domain-Invariant feature learning and Adaptive Graph regularized Label Propagation (DIAGLP) method for EEG-based emotion recognition. DIAGLP integrates semi-supervised knowledge adaptation and label propagation on EEG data, optimizing DIF representation and the EEG emotion recognition task within a single framework, thereby allowing mutual enhancement. Specifically, by incorporating the concept of soft labels, a domain joint distribution measurement model is established to simultaneously mitigate both marginal and conditional distribution disparities between different subjects/sessions. Additionally, an adaptive probability graph model is constructed to improve the robustness of EEG label propagation. Furthermore, a robust $\sigma $ -norm is applied to the domain joint distribution measurement and inductive learning models, creating a unified objective optimization form. Compared to several representative domain adaptation methods, the proposed method demonstrated superior or comparable performance in cross-subject and cross-session EEG emotion recognition tasks.

Keywords

• EEG emotion recognition
• domain adaptation
• maximum mean discrepancy
• adaptive graph Laplacian
• label propagation