Saved in:
Bibliographic Details
Main Authors: Kommineni, Aditya, Zhou, Emily, Avramidis, Kleanthis, Segaard, Simon Bock, Münster, Jeppe Roden, Hansen, Andreas Peter Juhl, Medani, Takfarinas, Feng, Tiantian, Leahy, Richard, Narayanan, Shrikanth
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.26434
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914602447536128
author Kommineni, Aditya
Zhou, Emily
Avramidis, Kleanthis
Segaard, Simon Bock
Münster, Jeppe Roden
Hansen, Andreas Peter Juhl
Medani, Takfarinas
Feng, Tiantian
Leahy, Richard
Narayanan, Shrikanth
author_facet Kommineni, Aditya
Zhou, Emily
Avramidis, Kleanthis
Segaard, Simon Bock
Münster, Jeppe Roden
Hansen, Andreas Peter Juhl
Medani, Takfarinas
Feng, Tiantian
Leahy, Richard
Narayanan, Shrikanth
contents EEG foundation models, pre-trained on large-scale unlabelled EEG data, have emerged as a promising direction towards learning generalizable EEG representations. Despite showing positive results in data-rich regimes, they often fail to outperform significantly smaller supervised models in low-resource settings compared to fully supervised models. We provide a mechanistic account of this shortcoming, attributing it to a fundamental mismatch between reconstruction-based pretext tasks and the idiosyncratic spectral structure of EEG signals, which decompose into distinct high-power aperiodic and low-power oscillatory components. Using controlled, synthetically-generated EEG inputs, we demonstrate that EEG foundation model embeddings are biased to capture the aperiodic components of the EEG signal while under-representing oscillatory components, particularly at higher frequencies. Additionally, linear probe evaluations on real-world BCI datasets further reveal that embeddings encode subject identity more strongly than task-relevant information, thereby reinforcing the low-frequency and aperiodic component bias in foundation model embeddings trained primarily on reconstruction based objectives. Together, these findings elucidate a failure mode in reconstruction based EEG foundation models and motivate future work to incorporate auxiliary losses explicitly targeting high-frequency oscillatory structure as a path toward more capable and generalizable EEG representations.
format Preprint
id arxiv_https___arxiv_org_abs_2605_26434
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Aperiodic and Low-Frequency Spectral Bias in Reconstruction based EEG Foundation Models
Kommineni, Aditya
Zhou, Emily
Avramidis, Kleanthis
Segaard, Simon Bock
Münster, Jeppe Roden
Hansen, Andreas Peter Juhl
Medani, Takfarinas
Feng, Tiantian
Leahy, Richard
Narayanan, Shrikanth
Machine Learning
Artificial Intelligence
EEG foundation models, pre-trained on large-scale unlabelled EEG data, have emerged as a promising direction towards learning generalizable EEG representations. Despite showing positive results in data-rich regimes, they often fail to outperform significantly smaller supervised models in low-resource settings compared to fully supervised models. We provide a mechanistic account of this shortcoming, attributing it to a fundamental mismatch between reconstruction-based pretext tasks and the idiosyncratic spectral structure of EEG signals, which decompose into distinct high-power aperiodic and low-power oscillatory components. Using controlled, synthetically-generated EEG inputs, we demonstrate that EEG foundation model embeddings are biased to capture the aperiodic components of the EEG signal while under-representing oscillatory components, particularly at higher frequencies. Additionally, linear probe evaluations on real-world BCI datasets further reveal that embeddings encode subject identity more strongly than task-relevant information, thereby reinforcing the low-frequency and aperiodic component bias in foundation model embeddings trained primarily on reconstruction based objectives. Together, these findings elucidate a failure mode in reconstruction based EEG foundation models and motivate future work to incorporate auxiliary losses explicitly targeting high-frequency oscillatory structure as a path toward more capable and generalizable EEG representations.
title Aperiodic and Low-Frequency Spectral Bias in Reconstruction based EEG Foundation Models
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2605.26434