English

STAMP: Spatial-Temporal Adapter with Multi-Head Pooling

Machine Learning 2026-05-07 v2 Artificial Intelligence

Abstract

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.

Keywords

Cite

@article{arxiv.2511.10848,
  title  = {STAMP: Spatial-Temporal Adapter with Multi-Head Pooling},
  author = {Brad Shook and Abby Turner and Jieshi Chen and Michał Wiliński and Mononito Goswami and Jonathan Elmer and Artur Dubrawski},
  journal= {arXiv preprint arXiv:2511.10848},
  year   = {2026}
}

Comments

Accepted as a Proceedings paper at Machine Learning for Health (ML4H) 2025, invited presentation at the Time Series for Health (TS4H) Workshop, NeurIPS 2025. v2: Updated author affiliation and corrected a duplicated word in the text. No other changes

R2 v1 2026-07-01T07:36:44.213Z