无需存储历史数据，用原型保留跨被试脑电知识
Prototype-Guided Non-Exemplar Continual Learning for Cross-subject EEG Decoding
- 用类级原型总结个体特征，避免遗忘
- 在BCI竞赛数据集上准确率优于现有方法
- 适合隐私敏感或内存受限的脑机接口场景
由于个体间脑电（EEG）信号差异显著，在持续脑电解码任务中引入新被试时，先前知识常被覆盖。现有方法依赖存储历史数据作为重放缓冲区，但在隐私或内存受限下不切实际。为此，我们提出原型引导的非样本持续学习框架（ProNECL），无需访问历史脑电样本即可保留先验知识。ProNECL将个体特异性判别表示归纳为类级原型，并通过基于原型的特征正则化与跨被试对齐，逐步将新被试表示与全局原型记忆对齐。在BCI竞赛IV 2a和2b数据集上的实验表明，ProNECL有效平衡了知识保留与适应性，在跨被试持续脑电解码任务中表现更优。
原文摘要 · Abstract (English)
Due to the significant variability in electroencephalo-gram (EEG) signals across individuals, knowledge acquired from previous subjects is often overwritten as new subjects are introduced in continual EEG decoding tasks. Existing methods mainly rely on storing historical data from seen subjects as replay buffers to mitigate forgetting, which is impractical under privacy or memory constraints. To address this issue, we propose a Prototype-guided Non-Exemplar Continual Learning (ProNECL) framework that preserves prior knowledge without accessing historical EEG samples. ProNECL summarizes subject-specific discriminative representations into class-level prototypes and incrementally aligns new subject representations with a global prototype memory through prototype-based feature regulariza-tion and cross-subject alignment. Experiments on the BCI Com-petition IV 2a and 2b datasets demonstrate that ProNECL effec-tively balances knowledge retention and adaptability, achieving superior performance in cross-subject continual EEG decoding 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。