Cross-Subject EEG Emotion Recognition Based on Temporal Asynchronous Alignment Contrastive Learning

TL;DR

This paper introduces a novel EEG emotion recognition framework that aligns temporally asynchronous signals across subjects using contrastive learning, improving accuracy and robustness.

Contribution

It proposes a Temporal Asynchronous Alignment Contrastive Learning (TA2CL) method inspired by NLP, addressing temporal misalignment in EEG-based emotion recognition.

Findings

Achieves 64.5% accuracy on FACED nine-class task

Attains 86.4% accuracy on SEED dataset

Effectively mitigates inter-subject temporal delays

Abstract

With the advancement of science and technology, the importance of emotion research has become increasingly evident. Electroencephalography (EEG)-based emotion recognition has emerged as an active research area in recent years, owing to its objectivity and high temporal resolution. However, most existing methods focus on optimizing encoder structures to enhance feature extraction capabilities, while paying relatively little attention to similarity calculation strategies, particularly overlooking the potential temporal misalignment of responses among different subjects. To address these shortcomings, this paper draws inspiration from the late interaction mechanism of ColBERT in natural language processing (NLP) and proposes a Temporal Asynchronous Alignment-based Contrastive Learning (TA2CL) framework. This method transforms the traditional global "hard alignment" similarity calculation approach into a fine-grained local matching mechanism, enabling the model to adaptively search for and align "locally highly correlated" segments between two EEG signals, thereby effectively mitigating the effects of inter-subject differences and temporal delays. Experimental results demonstrate that the proposed method achieves strong performance across multiple public datasets. Specifically, on the FACED dataset, it achieves an accuracy of 64.5% for the nine-class classification task and 79.5% for the binary classification task, while on the SEED and SEED-V datasets, it achieves accuracies of 86.4% and 70.1%, respectively, validating the method's effectiveness and generalization capability.