Understanding and Correcting Low-Frequency Bias in EEG Foundation Model

• URL: http://arxiv.org/abs/2608.01898v1
• Date: Mon, 03 Aug 2026 08:36:10 GMT
• Title: Understanding and Correcting Low-Frequency Bias in EEG Foundation Model
• Abstract summary: We identify a persistent low-frequency bias in representations learned by diverse EEG foundation models.<n>Our analysis links this bias to the interaction between EEG's $1/f$-like spectral structure and neural networks' tendency to preferentially learn low-frequency components.<n>We introduce FAME, a frequency-balanced masked autoencoding framework that reconstructs time--frequency activity in predefined EEG bands from masked EEG inputs.
• Score: 12.910215709640033
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Increasing EEG pretraining data scale or model capacity does not consistently improve downstream performance. We identify a persistent low-frequency bias in representations learned by diverse EEG foundation models, which remains across dataset scales, model capacities, and pretraining objectives. Our analysis links this bias to the interaction between EEG's $1/f^α$-like spectral structure and neural networks' tendency to preferentially learn low-frequency components. In masked autoencoders, the $\ell_2$ reconstruction objective further amplifies this imbalance: under comparable relative reconstruction errors, high-power low-frequency components contribute disproportionately to the loss. To address this issue, we introduce FAME, a frequency-balanced masked autoencoding framework that reconstructs time--frequency activity in predefined EEG bands from masked EEG inputs. FAME independently standardizes the reconstruction targets within each band and assigns equal weight to all band-specific losses, thereby balancing supervision across the EEG spectrum. Evaluated on 41 downstream tasks in OmniEEG-Bench, FAME learns more spectrally balanced representations and achieves state-of-the-art performance on 24 of them. These results underscore the importance of balanced spectral supervision for learning transferable EEG representations.

Related papers

• Neonatal Hypoxic-ischaemic Encephalopathy Classification from the EEG and HRV Signals Using a Conformer based Masked Autoencoder [1.2599533416395767]
  We propose a novel self-supervised learning framework for representation learning from unlabelled electroencephalography (EEG) and heart rate variability (HRV) signals.<n>By integrating convolutional operations with Transformer-based self-attention, MAEConformer effectively captures both local temporal patterns and long-range contextual dependencies.<n> Experimental results demonstrate that the learned representations provide strong transferability and data efficiency.
  arXiv  Detail & Related papers  (2026-07-26T09:11:03Z)
• Not All EEG Moments Are Equal: Position-Adaptive Time Scheduling for EEG Generation [13.893263438236106]
  Existing flow based approaches assume that every channel and every time segment within a sample shares a single global time progression.<n>We propose an adaptive EEG generation framework built on conditional flow matching.<n>Our framework consistently outperforms the strongest baseline, reducing TS-FID by up to 62.2% and improving downstream classification accuracy gain by up to 6.77 percentage points.
  arXiv  Detail & Related papers  (2026-07-25T00:15:14Z)
• Aperiodic and Low-Frequency Spectral Bias in Reconstruction based EEG Foundation Models [38.88255695601846]
  EEG foundation models, pre-trained on large-scale unlabelled EEG data, have emerged as a promising direction towards learning generalizable EEG representations.<n>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.
  arXiv  Detail & Related papers  (2026-05-26T01:40:36Z)
• Structured Prototype-Guided Adaptation for EEG Foundation Models [56.35233377493694]
  We show that EEG foundation models exhibit poor generalization when subject-level supervision is limited.<n>This failure stems from a structural mismatch between noisy, limited supervision and the highly plastic parameter space of EFMs.<n>We propose SCOPE, a Structured COnfidence-aware Prototype-guided adaptation framework for EFM fine-tuning.
  arXiv  Detail & Related papers  (2026-02-19T10:54:29Z)
• Back to Ear: Perceptually Driven High Fidelity Music Reconstruction [4.380428073231143]
  epsilonar-VAE is an open-source music signal reconstruction model that rethinks and optimize the Variational Autoencoders (VAEs)<n> Experiments show epsilonar-VAE at 44.1kHz substantially outperforms leading open-source models across diverse metrics.
  arXiv  Detail & Related papers  (2025-09-18T12:41:34Z)
• Tokenizing Single-Channel EEG with Time-Frequency Motif Learning [16.732494632599934]
  This paper presents TFM-Tokenizer, a novel tokenization framework.<n>It learns a vocabulary of time-frequency motifs from single-channel EEG signals and encodes them into discrete tokens.<n> Experiments on ear-EEG sleep staging, which differs from the pretraining data in signal format, channel configuration, recording device, and task, show that our tokenizer outperforms baselines by 14%.
  arXiv  Detail & Related papers  (2025-02-22T03:32:36Z)
• Graph Structure Refinement with Energy-based Contrastive Learning [56.957793274727514]
  We introduce an unsupervised method based on a joint of generative training and discriminative training to learn graph structure and representation.<n>We propose an Energy-based Contrastive Learning (ECL) guided Graph Structure Refinement (GSR) framework, denoted as ECL-GSR.<n>ECL-GSR achieves faster training with fewer samples and memories against the leading baseline, highlighting its simplicity and efficiency in downstream tasks.
  arXiv  Detail & Related papers  (2024-12-20T04:05:09Z)
• Few-shot NeRF by Adaptive Rendering Loss Regularization [78.50710219013301]
  Novel view synthesis with sparse inputs poses great challenges to Neural Radiance Field (NeRF) Recent works demonstrate that the frequency regularization of Positional rendering can achieve promising results for few-shot NeRF. We propose Adaptive Rendering loss regularization for few-shot NeRF, dubbed AR-NeRF.
  arXiv  Detail & Related papers  (2024-10-23T13:05:26Z)
• From Environmental Sound Representation to Robustness of 2D CNN Models Against Adversarial Attacks [82.21746840893658]
  This paper investigates the impact of different standard environmental sound representations (spectrograms) on the recognition performance and adversarial attack robustness of a victim residual convolutional neural network. We show that while the ResNet-18 model trained on DWT spectrograms achieves a high recognition accuracy, attacking this model is relatively more costly for the adversary.
  arXiv  Detail & Related papers  (2022-04-14T15:14:08Z)
• Generalizing electrocardiogram delineation: training convolutional neural networks with synthetic data augmentation [63.51064808536065]
  Existing databases for ECG delineation are small, being insufficient in size and in the array of pathological conditions they represent. This article delves has two main contributions. First, a pseudo-synthetic data generation algorithm was developed, based in probabilistically composing ECG traces given "pools" of fundamental segments, as cropped from the original databases, and a set of rules for their arrangement into coherent synthetic traces. Second, two novel segmentation-based loss functions have been developed, which attempt at enforcing the prediction of an exact number of independent structures and at producing closer segmentation boundaries by focusing on a reduced number of samples.
  arXiv  Detail & Related papers  (2021-11-25T10:11:41Z)
• Conditioning Trick for Training Stable GANs [70.15099665710336]
  We propose a conditioning trick, called difference departure from normality, applied on the generator network in response to instability issues during GAN training. We force the generator to get closer to the departure from normality function of real samples computed in the spectral domain of Schur decomposition.
  arXiv  Detail & Related papers  (2020-10-12T16:50:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.