Multi-Scale Hyperbolic Contrastive Learning for Cross-Subject EEG Emotion Recognition

• Published in: IEEE transactions on affective computing Vol. 16; no. 3; pp. 1 - 16
• Main Authors: Chang, Jiang, Zhang, Zhixin, Qian, Yuhua, Lin, Pan
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2025; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accuracy; Affective computing; Brain modeling; Computational modeling; Contrastive learning; cross-subject; Data models; EEG; Electroencephalography; Emotion recognition; Emotions; Feature extraction; Hyperbolic coordinates; hyperbolic embedding; Invariants; Learning; Representations; Vectors
• ISSN: 1949-3045; 1949-3045
• DOI: 10.1109/TAFFC.2025.3535542

Electroencephalography (EEG) serves as a reliable and objective signal for affective computing applications. However, individual differences in EEG signals pose a significant challenge for emotion recognition tasks across subjects. To address this, we proposed a novel method called Multi-Scale Hyperbolic Contrastive Learning (MSHCL), which leverages event-relatedness to learn subject-invariant representations. MSHCL employs contrastive losses at two different scales-emotion and stimulus-to effectively capture complex EEG patterns within a hyperbolic space hierarchy. Our method is evaluated on three datasets: SEED, MPED, and FACED. It achieves 89.3% accuracy on the three-class task for SEED, 38.8% on the seven-class task for MPED, and 77.0% and 45.7% on the binary and nine-class tasks for FACED in cross-subject emotion recognition. These results demonstrate that the proposed MSHCL method superior performance over other baselines and its effectiveness in learning subject-invariant representations. The source code is available at https://github.com/JiangChang-BRAIN/MSHCL .