STAMP: Spatial-Temporal Adapter with Multi-Head Pooling

Brad Shook, Abby Turner, Jieshi Chen, Michal Wilinski, Mononito Goswami, Jonathan Elmer, Artur Dubrawski
Proceedings of the Fifth Machine Learning for Health Symposium, PMLR 297:1159-1177, 2026.

Abstract

Time series foundation models ({TSFM}s) 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 ({EEGFM}s) versus general {TSFM}s 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 {EEGFM}s. 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 {TSFM}s.

Cite this Paper

BibTeX
@InProceedings{pmlr-v297-shook26a, title = {{STAMP}: Spatial-Temporal Adapter with Multi-Head Pooling}, author = {Shook, Brad and Turner, Abby and Chen, Jieshi and Wilinski, Michal and Goswami, Mononito and Elmer, Jonathan and Dubrawski, Artur}, booktitle = {Proceedings of the Fifth Machine Learning for Health Symposium}, pages = {1159--1177}, year = {2026}, editor = {Argaw, Peniel and Zhang, Haoran and Jabbour, Sarah and Chandak, Payal and Ji, Jerry and Mukherjee, Sumit and Salaudeen, Olawale and Chang, Trenton and Healey, Elizabeth and Gröger, Fabian and Adibi, Amin and Hegselmann, Stefan and Wild, Benjamin and Noori, Ayush}, volume = {297}, series = {Proceedings of Machine Learning Research}, month = {13--14 Dec}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v297/main/assets/shook26a/shook26a.pdf}, url = {https://proceedings.mlr.press/v297/shook26a.html}, abstract = {Time series foundation models ({TSFM}s) 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 ({EEGFM}s) versus general {TSFM}s 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 {EEGFM}s. 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 {TSFM}s.} }
Endnote
%0 Conference Paper %T STAMP: Spatial-Temporal Adapter with Multi-Head Pooling %A Brad Shook %A Abby Turner %A Jieshi Chen %A Michal Wilinski %A Mononito Goswami %A Jonathan Elmer %A Artur Dubrawski %B Proceedings of the Fifth Machine Learning for Health Symposium %C Proceedings of Machine Learning Research %D 2026 %E Peniel Argaw %E Haoran Zhang %E Sarah Jabbour %E Payal Chandak %E Jerry Ji %E Sumit Mukherjee %E Olawale Salaudeen %E Trenton Chang %E Elizabeth Healey %E Fabian Gröger %E Amin Adibi %E Stefan Hegselmann %E Benjamin Wild %E Ayush Noori %F pmlr-v297-shook26a %I PMLR %P 1159--1177 %U https://proceedings.mlr.press/v297/shook26a.html %V 297 %X Time series foundation models ({TSFM}s) 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 ({EEGFM}s) versus general {TSFM}s 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 {EEGFM}s. 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 {TSFM}s.
APA
Shook, B., Turner, A., Chen, J., Wilinski, M., Goswami, M., Elmer, J. & Dubrawski, A.. (2026). STAMP: Spatial-Temporal Adapter with Multi-Head Pooling. Proceedings of the Fifth Machine Learning for Health Symposium, in Proceedings of Machine Learning Research 297:1159-1177 Available from https://proceedings.mlr.press/v297/shook26a.html.

Related Material