Problem
Research questions and friction points this paper is trying to address.
EEG emotion recognition
channel redundancy
inter-subject variability
cross-subject generalization
scalable decoding
PRISM: Prioritized Channel Importance with Semi-supervised Domain Adaptation for Cross-Subject EEG Emotion Recognition
🤖 AI Summary
This work addresses the limited generalization in EEG-based emotion recognition caused by channel redundancy and inter-subject variability by proposing a semi-supervised domain adaptation framework that integrates differentiable channel weighting with a lightweight mixture-of-experts architecture. The approach employs data-driven channel prioritization to emphasize reliable electrodes and leverages unlabeled target-domain data through confidence-based pseudo-labeling, consistency regularization, and domain alignment. Experimental results on the DEAP, DREAMER, and SEED datasets demonstrate that the method achieves state-of-the-art performance with only a small number of labeled samples, enabling efficient and robust cross-subject emotion decoding.
📝 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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
channel importance weighting
semi-supervised domain adaptation
cross-subject EEG emotion recognition
pseudo-labeling
consistency regularization
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
