Physiological Prior-Driven Label Enhancement for Cross-Subject EEG Emotion Recognition

2026-07-16

AI Summary

Cross-subject EEG-based emotion recognition is hindered by substantial inter-individual variability and label noise, limiting its clinical applicability. To address this challenge, this work proposes PhyDA, a novel framework that, for the first time, leverages interpretable neurophysiological priors—such as spectral slope—to quantify subject-specific physiological noise and drive a training-free, parameter-free adaptive label refinement (DALR) mechanism for efficient label denoising. Notably, PhyDA requires no additional training and is readily compatible with diverse backbone networks. Extensive experiments demonstrate consistent performance gains across benchmark datasets: average classification accuracy improves by 2.76%, 2.66%, and 3.32% on DEAP, SEED, and SEED-IV, respectively, significantly outperforming existing label denoising approaches.

Abstract

Electroencephalography (EEG)-based emotion recognition captures affective neural signals with high temporal precision, but cross-subject variability and label noise remain critical challenges to its practical healthcare deployment. Existing label-denoising methods lack physiological grounding, while physiology-informed approaches rely on hand-crafted hyperparameters. To bridge these two paradigms, we propose PhyDA, a plug-and-play, tuning-free framework that unifies neurophysiological priors with data-driven label refinement. PhyDA comprises two modules. Since cross-subject variability renders global thresholds suboptimal, the Physiological Noise Quantifier (PhyNQ) exploits a spectral slope} to produce a subject-specific noise score, providing a neurophysiologically interpretable quality assessment {that naturally adapts to each individual. The Data-Adaptive Label Refiner (DALR) directly adopts this noise score as the contamination ratio to drive a label refinement pipeline that requires no additional neural network training, thereby directly mitigating the impact of inter-subject label noise. Extensive experiments on three public datasets (DEAP, SEED, SEED-IV) across seven backbone architectures under strict leave-one-subject-out cross-validation demonstrate that PhyDA consistently and significantly outperforms both general and EEG-tailored label-denoising baselines, achieving average accuracy gains of 2.76%, 2.66%, and 3.32%, respectively. Visualization further confirms its neurophysiological interpretability and practical robustness. The source code is available at: https://github.com/HongyuZhu-s/PhyDA.

Problem

• cross-subject variability
• label noise
• EEG emotion recognition
• physiological priors
• label denoising

Innovation

• Physiological Prior
• Label Enhancement
• Cross-Subject EEG
• Noise Quantification
• Plug-and-Play Framework