EMOD: A Unified EEG Emotion Representation Framework Leveraging V-A Guided Contrastive Learning

TL;DR

EMOD introduces a unified framework for EEG emotion recognition that leverages valence-arousal guided contrastive learning to improve cross-dataset generalization and semantic alignment.

Contribution

It proposes a novel V-A guided contrastive learning approach and a flexible backbone to unify heterogeneous EEG emotion datasets for better transferability.

Findings

Achieves state-of-the-art performance on benchmark datasets.

Demonstrates strong cross-dataset generalization.

Effectively aligns semantic and structural features across datasets.

Abstract

Emotion recognition from EEG signals is essential for affective computing and has been widely explored using deep learning. While recent deep learning approaches have achieved strong performance on single EEG emotion datasets, their generalization across datasets remains limited due to the heterogeneity in annotation schemes and data formats. Existing models typically require dataset-specific architectures tailored to input structure and lack semantic alignment across diverse emotion labels. To address these challenges, we propose EMOD: A Unified EEG Emotion Representation Framework Leveraging Valence-Arousal (V-A) Guided Contrastive Learning. EMOD learns transferable and emotion-aware representations from heterogeneous datasets by bridging both semantic and structural gaps. Specifically, we project discrete and continuous emotion labels into a unified V-A space and formulate a soft-weighted supervised contrastive loss that encourages emotionally similar samples to cluster in the latent space. To accommodate variable EEG formats, EMOD employs a flexible backbone comprising a Triple-Domain Encoder followed by a Spatial-Temporal Transformer, enabling robust extraction and integration of temporal, spectral, and spatial features. We pretrain EMOD on 8 public EEG datasets and evaluate its performance on three benchmark datasets. Experimental results show that EMOD achieves the state-of-the-art performance, demonstrating strong adaptability and generalization across diverse EEG-based emotion recognition scenarios.