arXiv 2603.267132026-03-18cs.LGeess.SPstat.ML

面向边界的原型驱动对抗对齐用于跨语料EEG情绪识别

Boundary-aware Prototype-driven Adversarial Alignment for Cross-Corpus EEG Emotion Recognition

School of Biological Science and Medical Engineering, Hunan University of Technology（湖南工业大学生物科学与医学工程学院）；School of Biomedical Engineering, Health Science Center, Shenzhen University（深圳大学医学部生物医学工程学院）；Guangdong Provincial Key Laboratory of Biomedical Measurements and Ultrasound Imaging（广东省生物医学测量与超声成像重点实验室）；Shenzhen Pengrui Brain Science Technology（深圳鹏瑞脑科学技术有限公司）

Guangli Li, Canbiao Wu, Na Tian, Li Zhang, Zhen Liang

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出原型驱动对抗对齐框架，通过局部类条件对齐、对比语义正则化和边界感知聚合提升EEG情绪识别的跨语料泛化能力，实验显示在多个数据集上取得显著提升。

摘要：

基于EEG的情绪识别在跨异质数据集转移时因生理差异、实验范式差异和设备不一致而性能下降。现有领域对抗方法主要强制全局边缘对齐，常忽视类条件不匹配和决策边界扭曲，限制了跨语料泛化。本文提出统一的原型驱动对抗对齐（PAA）框架，通过三种配置：PAA-L进行原型引导的局部类条件对齐；PAA-C引入对比语义正则化增强类内紧凑性和类间分离性；PAA-M整合双关系感知分类器，在三阶段对抗优化方案中显式细化决策边界附近争议样本。通过结合原型引导的子域对齐、对比判别增强和边界感知聚合，将情绪识别重新公式化为关系驱动的表示学习问题，减少对标签噪声的敏感性并提高跨域稳定性。在SEED、SEED-IV和SEED-V上的广泛实验显示，在四种跨语料评估协议下取得最佳性能，平均提升分别为6.72%、5.59%、6.69%和4.83%。此外，该框架在临床抑郁症识别场景中表现出良好的泛化能力，验证了其在现实异质环境中的鲁棒性。源代码可在https://github.com/WuCB-BCI/PAA获取。

英文摘要：

Electroencephalography (EEG)-based emotion recognition suffers from severe performance degradation when models are transferred across heterogeneous datasets due to physiological variability, experimental paradigm differences, and device inconsistencies. Existing domain adversarial methods primarily enforce global marginal alignment and often overlook class-conditional mismatch and decision boundary distortion, limiting cross-corpus generalization. In this work, we propose a unified Prototype-driven Adversarial Alignment (PAA) framework for cross-corpus EEG emotion recognition. The framework is progressively instantiated in three configurations: PAA-L, which performs prototype-guided local class-conditional alignment; PAA-C, which further incorporates contrastive semantic regularization to enhance intra-class compactness and inter-class separability; and PAA-M, the full boundary-aware configuration that integrates dual relation-aware classifiers within a three-stage adversarial optimization scheme to explicitly refine controversial samples near decision boundaries. By combining prototype-guided subdomain alignment, contrastive discriminative enhancement, and boundary-aware aggregation within a coherent adversarial architecture, the proposed framework reformulates emotion recognition as a relation-driven representation learning problem, reducing sensitivity to label noise and improving cross-domain stability. Extensive experiments on SEED, SEED-IV, and SEED-V demonstrate state-of-the-art performance under four cross-corpus evaluation protocols, with average improvements of 6.72\%, 5.59\%, 6.69\%, and 4.83\%, respectively. Furthermore, the proposed framework generalizes effectively to clinical depression identification scenarios, validating its robustness in real-world heterogeneous settings. The source code is available at \textit{https://github.com/WuCB-BCI/PAA}

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。