用轻量适配器让通用时序模型高效处理脑电数据
STAMP: Spatial-Temporal Adapter with Multi-Head Pooling
- 基于通用时序模型的单变量嵌入，通过多头池化建模脑电信号时空特征
- 在8个临床任务数据集上达到与顶尖脑电专用模型相当的性能
- 参数量少、输入灵活，适合快速部署到各类脑电分析场景
时序基础模型（TSFMs）在多领域数据预训练后，在多种建模任务中表现优异。尽管已有研究致力于开发针对脑电图（EEG）数据的专用基础模型（EEGFMs），但尚未有研究在脑电特异性任务上对EEGFMs与通用TSFMs进行系统比较。本文提出一种新型时空适配器——多头池化时空适配器（STAMP），利用通用TSFM生成的单变量嵌入，隐式建模EEG数据的时空特性，其性能可媲美当前最先进的EEGFMs。我们在8个临床任务基准数据集上进行了全面评估，并开展消融实验。所提出的适配器具有少量可训练参数，且对输入形式具有高度灵活性，支持使用通用时序模型便捷建模脑电数据。
原文摘要 · Abstract (English)
Time series foundation models (TSFMs) pretrained on data from multiple domains have shown strong performance on diverse modeling tasks. Various efforts have been made to develop foundation models specific to electroencephalography (EEG) data, which records brain electrical activity as time series. However, no comparative analysis of EEG-specific foundation models (EEGFMs) versus general TSFMs has been performed on EEG-specific tasks. We introduce a novel Spatial-Temporal Adapter with Multi-Head Pooling (STAMP), which leverages univariate embeddings produced by a general TSFM, implicitly models spatial-temporal characteristics of EEG data, and achieves performance comparable to state-of-the-art EEGFMs. A comprehensive analysis is performed on 8 benchmark datasets of clinical tasks using EEG for classification, along with ablation studies. Our proposed adapter is lightweight in trainable parameters and flexible in the inputs it can accommodate, supporting easy modeling of EEG data using TSFMs.
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。