STAMP: Spatial-Temporal Adapter with Multi-Head Pooling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shook, Brad, Turner, Abby, Chen, Jieshi, Wiliński, Michał, Goswami, Mononito, Elmer, Jonathan, Dubrawski, Artur
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913095225442304
author Shook, Brad
Turner, Abby
Chen, Jieshi
Wiliński, Michał
Goswami, Mononito
Elmer, Jonathan
Dubrawski, Artur
author_facet Shook, Brad
Turner, Abby
Chen, Jieshi
Wiliński, Michał
Goswami, Mononito
Elmer, Jonathan
Dubrawski, Artur
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_10848
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle STAMP: Spatial-Temporal Adapter with Multi-Head Pooling
Shook, Brad
Turner, Abby
Chen, Jieshi
Wiliński, Michał
Goswami, Mononito
Elmer, Jonathan
Dubrawski, Artur
Machine Learning
Artificial Intelligence
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.
title STAMP: Spatial-Temporal Adapter with Multi-Head Pooling
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2511.10848