统一预训练框架提升脑电情绪识别跨数据集泛化能力
One Model for All: Universal Pre-training for EEG based Emotion Recognition across Heterogeneous Datasets and Paradigms
- 分两阶段预训练：单通道自监督学习+多通道自适应注意力建模
- 在三个数据集上达到新SOTA，跨数据集迁移准确率达94.08%
- 适用于不同设备、实验范式下的脑电信号分析，尤其适合噪声环境
基于脑电的情绪识别受数据异质性（通道数/被试差异）严重制约，现有方法难以有效迁移知识。本文提出「One Model for All」通用预训练框架，实现跨异构数据集的脑电分析。该范式分为两个阶段：(1) 通过统一通道架构（UCS）利用通道并集（如SEED-62ch、DEAP-32ch），在单通道上进行自监督对比学习；(2) 采用新型‘ART’（自适应重采样变换器）与‘GAT’（图注意力网络）进行多变量微调，捕捉复杂时空依赖。实验表明，通用预训练是稳定性的关键，在SEED上防止模型坍塌，于DEAP上提升7.65%，在DREAMER上提升3.55%。该框架在所有被试内基准测试中均达新SOTA：SEED（99.27%）、DEAP（93.69%）、DREAMER（93.93%）。跨数据集迁移也表现优异，未见的DREAMER数据集上达到94.08%（交集）和93.05%（UCS），前者超越域内预训练基线。消融实验验证：GAT模块至关重要，在高噪声的DEAP上较GCN提升22.19%，移除后性能骤降16.44%。本工作为多样化脑电分析任务提供了更通用、可扩展、高效的预训练模型路径。
原文摘要 · Abstract (English)
EEG-based emotion recognition is hampered by profound dataset heterogeneity (channel/subject variability), hindering generalizable models. Existing approaches struggle to transfer knowledge effectively. We propose 'One Model for All', a universal pre-training framework for EEG analysis across disparate datasets. Our paradigm decouples learning into two stages: (1) Univariate pre-training via self-supervised contrastive learning on individual channels, enabled by a Unified Channel Schema (UCS) that leverages the channel union (e.g., SEED-62ch, DEAP-32ch); (2) Multivariate fine-tuning with a novel 'ART' (Adaptive Resampling Transformer) and 'GAT' (Graph Attention Network) architecture to capture complex spatio-temporal dependencies. Experiments show universal pre-training is an essential stabilizer, preventing collapse on SEED (vs. scratch) and yielding substantial gains on DEAP (+7.65%) and DREAMER (+3.55%). Our framework achieves new SOTA performance on all within-subject benchmarks: SEED (99.27%), DEAP (93.69%), and DREAMER (93.93%). We also show SOTA cross-dataset transfer, achieving 94.08% (intersection) and 93.05% (UCS) on the unseen DREAMER dataset, with the former surpassing the within-domain pre-training benchmark. Ablation studies validate our architecture: the GAT module is critical, yielding a +22.19% gain over GCN on the high-noise DEAP dataset, and its removal causes a catastrophic -16.44% performance drop. This work paves the way for more universal, scalable, and effective pre-trained models for diverse EEG analysis tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。