让神经信号模型适应不同时间尺度，提升脑机接口泛化能力
Learning Time-Scale Invariant Population-Level Neural Representations
- 通过时间尺度增强预训练，构建对时间尺度变化不变的神经表征
- 在多种解码任务中显著提升对时间尺度不匹配的鲁棒性
- 适合开发通用神经基础模型的研究者与脑机接口开发者
面向神经时间序列的通用基础模型有望加速神经科学研究并推动脑机接口等应用。其中关键在于群体水平表征学习，通过跨通道信息捕捉空间与时间结构。近期方法表明，此类表征在预训练时序编码器基础上高效学习，并可有效支持多种下游解码任务。然而，现有模型对预训练与下游设置间的时间尺度不匹配仍敏感。我们系统研究了时间尺度差异对泛化性能的影响，发现现有表征缺乏不变性。为此提出时间尺度增强预训练（TSAP），显著提升不同时间尺度下的解码鲁棒性，并在表征空间中引入不变性。结果表明，处理预处理多样性是构建可泛化神经基础模型的关键一步。
原文摘要 · Abstract (English)
General-purpose foundation models for neural time series can help accelerate neuroscientific discoveries and enable applications such as brain computer interfaces (BCIs). A key component in scaling these models is population-level representation learning, which leverages information across channels to capture spatial as well as temporal structure. Population-level approaches have recently shown that such representations can be both efficient to learn on top of pretrained temporal encoders and produce useful representations for decoding a variety of downstream tasks. However, these models remain sensitive to mismatches in preprocessing, particularly on time-scales, between pretraining and downstream settings. We systematically examine how time-scale mismatches affects generalization and find that existing representations lack invariance. To address this, we introduce Time-scale Augmented Pretraining (TSAP), which consistently improves robustness to different time-scales across decoding tasks and builds invariance in the representation space. These results highlight handling preprocessing diversity as a key step toward building generalizable neural foundation models.
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。