PRISM: Prioritized Channel Importance with Semi-supervised Domain Adaptation for Cross-Subject EEG Emotion Recognition
2026-07-01 • Machine Learning
Machine Learning
AI summaryⓘ
The authors developed a method called PRISM to better read emotions from brain signals recorded by EEG. Their approach smartly picks out important sensors and uses some unlabeled data to adjust for differences between people. This helps the system work well even when there are only a few labeled examples from new individuals. Tests on several standard datasets showed PRISM did better than previous methods at understanding emotions across different subjects.
Electroencephalogram (EEG)Emotion decodingChannel selectionCross-subject variabilitySemi-supervised learningDomain adaptationPseudo-labelingConsistency regularizationDEAP datasetSEED dataset
Authors
Xin Zhou, Xiang Zhang, Hao Deng, Lijun Yin
Abstract
Electroencephalogram (EEG) captures endogenous brain activity with high temporal fidelity and holds substantial promise for precise emotion decoding. However, channel redundancy and pronounced inter-subject variability remain key obstacles to scalable generalization. To address these limitations, we propose a novel framework termed PRioritized channel Importance with Semi-supervised doMain adaptation (PRISM), enabling label-efficient cross-subject emotion decoding. On the channel side, PRISM assigns differentiable, data-dependent channel weights via a lightweight expert ensemble, amplifying reliable electrodes while suppressing distractors. On the domain side, PRISM leverages unlabeled data through confidence-filtered pseudo-labels to drive consistency regularization and domain alignment, mitigating subject-specific heterogeneity. Extensive experiments show that PRISM surpasses state-of-the-art methods on DEAP, DREAMER, and SEED datasets, achieving robust cross-subject generalization given limited annotations.