Generalized Contrastive Partial Label Learning for Cross-Subject EEG-Based Emotion Recognition

Electroencephalogram (EEG)-based emotion recognition has become a hot topic in affective computing. However, due to the challenges of intersubject variability and label ambiguity of EEG data, existing research often suffers from poor performance. This limitation significantly hampers the practical application of cross-subject EEG-based emotion recognition. To overcome these challenges, we propose a novel and effective partial label learning (PLL) method, named generalized contrastive PLL (GCPL). By performing label disambiguation, GCPL can uncover the authentic emotion label from the multiple ambiguous emotions reported in the self-assessment of each subject. By integrating contrastive learning with domain generalization seamlessly, GCPL can extract the class-discriminative and domain-invariant features in spite of intersubject variability. Besides, by employing self-distillation, GCPL can mitigate the overfitting problem caused by the limited data size. Experimental results on the SEED, SEED-IV, MPED, and FACED datasets demonstrate the effectiveness of GCPL in cross-subject EEG-based emotion recognition.