用个性化编码器提升脑电跨人识别效果，避免数据分布差异干扰。
Learning aligned EEG representations with subject-specific encoders
- 为每人配备专属编码器，让模型自动对齐个体脑电信号特征。
- 在4个运动想象数据集上，性能优于共享编码器基线模型。
- 适合需要高精度跨人脑电解码的研究者，如脑机接口开发。
跨被试脑电解码可获得更多训练数据，但也带来显著的个体间分布差异。本文探究仅靠任务监督与网络结构能否学习到个体对齐的表示。将共享的脑电编码器替换为个体专用编码器，再接一个公共分类器，与EEGNet、AttentionBaseNet和CTNet等基线模型结合欧氏对齐（EA）方法在4个运动想象数据集上对比。尽管EA通过重置个体协方差提升了共享编码器表现，但混合架构几乎内化了这一功能：移除EA后验证损失曲线与潜在空间距离分析变化极小。个体专用头部增强了类别区分度，并使每位被试靠近其自身潜在流形，整体提升多数被试性能，但仍有部分敏感子集表现依赖方法选择。结果表明，个体专用编码器可作为脑电解码中一种学习型对齐机制，而对未见被试的头部选择仍是主要瓶颈。
原文摘要 · Abstract (English)
Cross-subject EEG decoding promises more training data, but it also exposes neural networks to strong inter-subject distribution shifts. We study whether task supervision and architecture alone can learn subject-aligned representations. We replace a shared EEG encoder with subject-specific encoders followed by a common classifier, and compare this hybrid model with standard EEGNet, AttentionBaseNet, and CTNet baselines with Euclidean Alignment (EA) on four motor-imagery datasets. EA improves shared encoders by recentering subject covariances, but the hybrid encoder largely internalises this role: validation-loss curves and latent-distance analyses change little when EA is removed. Subject-specific heads increase class distinctiveness and place each subject close to its own latent manifold, improving most subjects while leaving a method-sensitive subset. These results support subject-specific encoders as a learned alignment mechanism for EEG decoding and identify head selection for unseen subjects as the remaining bottleneck.
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。