PRISM Prioritized Channel Importance with Semi-supervised Domain Adaptation for Cross-Subject EEG Emotion Recognition

Jul 16, 2026

Upload by Finn

Electroencephalogram (EEG) enables high-temporal-fidelity emotion decoding, yet scalable cross-subject generalization is hindered by channel redundancy and strong inter-subject variability. PRISM proposes a label-efficient framework that simultaneously prioritizes informative electrodes and aligns domains. On the channel side, PRISM produces differentiable, data-dependent channel weights via a lightweight expert ensemble to amplify reliable channels and suppress distractors. On the domain side, it uses confidence-filtered pseudo-labels to drive consistency regularization and domain alignment, reducing subject heterogeneity. Experiments on DEAP, DREAMER, and SEED outperform prior methods with limited annotations.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages11

Reading Time28 min

Abstract

Introduction

Motivation: channel redundancy and inter-subject heterogeneity

Problem statement and challenges

Overview of PRISM framework

PRISM: Prioritized Channel Importance with Semi-supervised Domain Adaptation for Cross-Subject EEG Emotion Recognition Xin Zhou, Xiang Zhang, Hao Deng, and Lijun Yin∗ , Fellow, IEEE arXiv :2607 .00358v 1 [ cs .LG] 1 Jul 2026 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 methodson DEAP, DREAMER, and SEED datasets, achieving robust cross-subject generalization given limited annotations. Index Terms—Electroencephalogram (EEG), emotion recognition, channel importance, semi-supervised domain adaptation. I. INTRODUCTION EEG is noninvasive and has high temporal resolution, which enables the capture of affect related neural dynamics and is therefore regarded as an ideal signal for emotion decoding [1], [2] . Neuropsychological studies indicate that emotion processing exhibits regional selectivity across the cortex, with frontal systems showing particular sensitivity [3] . In practice, some electrodes contribute little to emotional representations and are more susceptible to ocular and myogenic artifacts [4], [5], which leads to pronounced spatial nonuniformity in full channel EEG. Using all channels without discrimination dilutes discriminative information and reduces recognition accuracy, and it also increases dimensional redundancy and computational cost. Identifying and emphasizing electrodes that are more informative for emotion decoding, while suppressing redundant and noisy sources, is therefore a key path to improving the quality and deployability of EEGbased emotional representations. Prior work has explored emotion recognition with a small set of channels and found that using only a limited number of emotion-relevant electrodes as input does not markedly reduce Xin Zhou, Xiang Zhang and Lijun Yin are with the School of Computing, T. J Watson College of Engineering and Applied Science, Binghamton University - State University of New York, Binghamton, NY 13902 USA (e-mail: [xzhou11@binghamton.edu](xzhou11@binghamton.edu); [zxiang4@binghamton.edu](zxiang4@binghamton.edu); [lyin@binghamton.edu](lyin@binghamton.edu)). Hao Deng is with the Massachusetts General Hospital, Harvard University, Boston, MA 02114 USA (e-mail: [hdeng1@mgh.harvard.edu](hdeng1@mgh.harvard.edu)). ∗Corresponding author. accuracy [6], [7] . Other studies employ attention mechanisms [6], [8] or graph convolutions [9], [10] to assign dynamic weights across channels. However, many existing approaches either do not adequately account for differences in cortical responses across distinct emotion elicitation paradigms, or they rely on a single weighting configuration, which limits adaptability across tasks, paradigms, and settings. Given heterogeneous elicitation conditions and application constraints, supporting multiple weighting configurations that update ina data adaptive manner is both practically meaningful and methodologically valuable. Beyond channel redundancy, EEG exhibits pronounced cross-subject heterogeneity, that is, substantial innate differences among individuals in anatomy, physiological state, and psychological responses. As a result, the EEG distributions produced by

FAQs

What core problem does PRISM address in cross-subject EEG emotion recognition?

PRISM targets two bottlenecks: redundant EEG channels and pronounced variability across subjects, which together reduce generalization when training and testing involve different individuals.

How does PRISM handle channel redundancy?

PRISM assigns differentiable, data-dependent channel weights using a lightweight expert ensemble, amplifying informative electrodes and suppressing distractors/noisy sources.

How does PRISM mitigate cross-subject heterogeneity when labels are scarce?

PRISM leverages unlabeled target data through confidence-filtered pseudo-labels, using consistency regularization and domain alignment to reduce subject-specific distribution shifts.

Jul 16, 2026

Upload by Finn