脑电解码的缩放定律：多少数据才够？
Scaling Laws for EEG Decoding: How Much Data Is Enough?
浏览论文内容
中文总结 AI 辅助
本研究通过评估五种模型在四个脑电数据集上的性能，发现数据量增加时试验与受试者缩放差异消失，幂律关系可稳健描述脑电解码性能，且外推误差低。
中文摘要 AI 辅助
深度学习已成为基于脑电（EEG）的脑解码领域的基石，每天都有越来越多的架构被提出。然而，这些不同模型的性能如何随数据量变化尚不清楚。尽管这种关系在其他领域已被表征为缩放定律，但在脑电领域仍知之甚少。本研究通过探究扫描时间和受试者多样性如何影响不同架构的性能来填补这一空白。我们在四个脑电数据集上评估了五种模型。通过交叉受试者验证，同时改变受试者数量和试验次数来控制训练数据量。然后，我们拟合幂律关系来表征由此产生的行为。我们的发现表明，随着总数据量的增加，试验缩放与受试者缩放之间的区别在很大程度上变得无关紧要。此外，我们表明幂律关系既具有模型特异性又具有数据集特异性，但它们为脑电解码性能提供了一个稳健的描述性框架。外推到更大的受试者群体时，在大多数情况下均方根误差（RMSE）值低于0.1。我们的工作通过提供脑电数据缩放的描述性框架并展示脑电研究中数据高效的实验设计，为文献做出了贡献。
英文摘要
Deep learning has become a cornerstone of EEG-based brain decoding, with a growing number of architectures proposed every day. However, how the performance of these different models scales with data volume is not clear. Although this relationship has been characterized in other fields under the name of scaling laws, it remains poorly understood in the EEG domain. The present study addresses this gap by investigating how scan time and subject diversity affect the performance of different architectures. We evaluated five models across four EEG datasets. Training data volume was controlled by varying both subject count and trial volume under cross-subject validation. We then fitted power-law relationships to characterize the resulting behavior. Our findings reveal that as total data volume increases, the distinction between trial and subject scaling becomes largely irrelevant. Furthermore, we show that power-law relationships are both model and dataset-specific, yet they provide a robust descriptive framework for EEG decoding performance. Extrapolation to larger subject pools yields RMSE values below 0.1 in most cases. Our work contributes to the literature by providing a descriptive framework for data scaling in EEG and by demonstrating data-efficient experimental design in EEG research.
发表机构
- Federal University of ABC（ABC联邦大学）
- Institut de Neuromodulation, GHU Paris（神经调节研究所，巴黎GHU）
- Yneuro
- Swartz Center for Computational Neuroscience (SCCN), Institute for Neural Computation (INC), University of California San Diego（斯瓦茨计算神经科学中心（SCCN），神经计算研究所（INC），加州大学圣地亚哥分校）
机构由 AI 辅助整理，请以论文原文为准。
