Tokenizing Single-Channel EEG with Time-Frequency Motif Learning

• URL: http://arxiv.org/abs/2502.16060v3
• Date: Wed, 15 Oct 2025 18:46:33 GMT
• Title: Tokenizing Single-Channel EEG with Time-Frequency Motif Learning
• Authors: Jathurshan Pradeepkumar, Xihao Piao, Zheng Chen, Jimeng Sun,
• Abstract summary: 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%.
• Score: 16.732494632599934
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Foundation models are reshaping EEG analysis, yet an important problem of EEG tokenization remains a challenge. This paper presents TFM-Tokenizer, a novel tokenization framework that learns a vocabulary of time-frequency motifs from single-channel EEG signals and encodes them into discrete tokens. We propose a dual-path architecture with time-frequency masking to capture robust motif representations, and it is model-agnostic, supporting both lightweight transformers and existing foundation models for downstream tasks. Our study demonstrates three key benefits: Accuracy: Experiments on four diverse EEG benchmarks demonstrate consistent performance gains across both single- and multi-dataset pretraining settings, achieving up to 17% improvement in Cohen's Kappa over strong baselines. Generalization: Moreover, as a plug-and-play component, it consistently boosts the performance of diverse foundation models, including BIOT and LaBraM. Scalability: By operating at the single-channel level rather than relying on the strict 10-20 EEG system, our method has the potential to be device-agnostic. 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%. A comprehensive token analysis reveals strong class-discriminative, frequency-aware, and consistent structure, enabling improved representation quality and interpretability. Code is available at https://github.com/Jathurshan0330/TFM-Tokenizer.

Related papers

• Self-Supervised Learning via Flow-Guided Neural Operator on Time-Series Data [57.85958428020496]
  Flow-Guided Neural Operator (FGNO) is a novel framework combining operator learning with flow matching for SSL training.<n>FGNO learns mappings in functional spaces by using Short-Time Fourier Transform to unify different time resolutions.<n>Unlike prior generative SSL methods that use noisy inputs during inference, we propose using clean inputs for representation extraction while learning representations with noise.
  arXiv  Detail & Related papers  (2026-02-12T18:54:57Z)
• Representation-Regularized Convolutional Audio Transformer for Audio Understanding [53.092757178419355]
  bootstrapping representations from scratch is computationally expensive, often requiring extensive training to converge.<n>We propose the Convolutional Audio Transformer (CAT), a unified framework designed to address these challenges.
  arXiv  Detail & Related papers  (2026-01-29T12:16:19Z)
• Training-Free Spectral Fingerprints of Voice Processing in Transformers [0.0]
  We show that different transformer architectures implement identical linguistic computations via distinct connectivity patterns.<n>Using graph signal processing on attention induced token graphs, we track changes in connectivity across 20 languages and three model families.
  arXiv  Detail & Related papers  (2025-10-21T23:33:43Z)
• Bidirectional Time-Frequency Pyramid Network for Enhanced Robust EEG Classification [2.512406961007489]
  BITE (Bidirectional Time-Freq Pyramid Network) is an end-to-end unified architecture featuring robust multistream synergy, pyramid time-frequency attention (PTFA), and bidirectional adaptive convolutions.<n>As a unified architecture, it combines robust performance across both MI and SSVEP tasks with exceptional computational efficiency.<n>Our work validates that paradigm-aligned spectral-temporal processing is essential for reliable BCI systems.
  arXiv  Detail & Related papers  (2025-10-11T04:14:48Z)
• IGD: Token Decisiveness Modeling via Information Gain in LLMs for Personalized Recommendation [79.22388408461458]
  We introduce an Information Gain-based Decisiveness-aware Token handling (IGD) strategy that integrates token decisiveness into both tuning and decoding.<n>IGD consistently improves recommendation accuracy, achieving significant gains on widely used ranking metrics compared to strong baselines.
  arXiv  Detail & Related papers  (2025-06-16T08:28:19Z)
• BEAST: Efficient Tokenization of B-Splines Encoded Action Sequences for Imitation Learning [24.858548048614878]
  We present the B-spline Encoded Action Sequence Tokenizer (BEAST)<n>BEAST encodes action sequences into compact discrete or continuous tokens using B-splines.<n>We evaluate BEAST across three established benchmarks consisting of 166 simulated tasks and on three distinct robot settings with a total of 8 real-world tasks.
  arXiv  Detail & Related papers  (2025-06-06T13:26:16Z)
• ALFEE: Adaptive Large Foundation Model for EEG Representation [17.166788472910806]
  We propose the Adaptive Large Foundation model for EEG signal representation(ALFEE) framework.<n>ALFEE is a novel hybrid transformer architecture with two learning stages for robust EEG representation learning.<n>After 25,000 hours of pretraining, extensive experimental results on six downstream EEG tasks demonstrate the superior performance of ALFEE over existing models.
  arXiv  Detail & Related papers  (2025-05-07T13:32:31Z)
• Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation [63.89280381800457]
  We propose TokenBridge, which maintains the strong representation capacity of continuous tokens while preserving the modeling simplicity of discrete tokens. We introduce a dimension-wise quantization strategy that independently discretizes each feature dimension, paired with a lightweight autoregressive prediction mechanism. Our approach achieves reconstruction and generation quality on par with continuous methods while using standard categorical prediction.
  arXiv  Detail & Related papers  (2025-03-20T17:59:59Z)
• A novel Fourier Adjacency Transformer for advanced EEG emotion recognition [1.1347176912133798]
  EEG emotion recognition faces significant hurdles due to noise interference, signal nonstationarity, and the inherent complexity of brain activity. We present the Fourier Adjacency Transformer, a novel framework that seamlessly integrates Fourier-based periodic analysis with graph-driven structural modeling.
  arXiv  Detail & Related papers  (2025-02-28T03:15:12Z)
• FELLE: Autoregressive Speech Synthesis with Token-Wise Coarse-to-Fine Flow Matching [51.32059240975148]
  FELLE is an autoregressive model that integrates language modeling with token-wise flow matching.<n>For each continuous-valued token, FELLE modifies the general prior distribution in flow matching by incorporating information from the previous step.<n>FELLE generates continuous-valued tokens hierarchically, conditioned on the language model's output.
  arXiv  Detail & Related papers  (2025-02-16T13:54:32Z)
• Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization [74.3339999119713]
  We develop a wavelet-based tokenizer that allows models to learn complex representations directly in the space of time-localized frequencies.<n>Our method first scales and decomposes the input time series, then thresholds and quantizes the wavelet coefficients, and finally pre-trains an autoregressive model to forecast coefficients for the forecast horizon.
  arXiv  Detail & Related papers  (2024-12-06T18:22:59Z)
• The Backpropagation of the Wave Network [26.656105779121308]
  This paper provides an in-depth analysis of Wave Network, a novel token representation method derived from the Wave Network.<n>In complex vector token representation, each token is represented with a magnitude component, capturing the global semantics of the entire input text.<n>A detailed computational complexity analysis shows that Token2Wave can significantly reduce video memory usage and training time.
  arXiv  Detail & Related papers  (2024-11-11T13:48:01Z)
• SplitSEE: A Splittable Self-supervised Framework for Single-Channel EEG Representation Learning [8.373376507515347]
  SplitSEE is a self-supervised framework for effective temporal-frequency representation learning in single-channel EEG. It learns representations solely from single-channel EEG but has even outperformed multi-channel baselines. It achieves high and stable performance using partial model layers.
  arXiv  Detail & Related papers  (2024-10-15T02:34:33Z)
• Frequency-Aware Masked Autoencoders for Multimodal Pretraining on Biosignals [7.381259294661687]
  We propose a frequency-aware masked autoencoder that learns to parameterize the representation of biosignals in the frequency space. The resulting architecture effectively utilizes multimodal information during pretraining, and can be seamlessly adapted to diverse tasks and modalities at test time.
  arXiv  Detail & Related papers  (2023-09-12T02:59:26Z)
• Large Transformers are Better EEG Learners [8.930281191465088]
  AdaCT, plug-and-play Adapters designed for Time series data into 2D pseudo-images or text forms. AdaCTI transforms multi-channel or lengthy single-channel time series data into pseudo-images for fine-tuning pre-trained vision transformers. AdaCT-T converts short single-channel data into text for fine-tuning pre-trained language transformers.
  arXiv  Detail & Related papers  (2023-08-20T12:54:17Z)
• Adaptive Frequency Filters As Efficient Global Token Mixers [100.27957692579892]
  We show that adaptive frequency filters can serve as efficient global token mixers. We take AFF token mixers as primary neural operators to build a lightweight neural network, dubbed AFFNet.
  arXiv  Detail & Related papers  (2023-07-26T07:42:28Z)
• A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity [71.11795737362459]
  ViTs with self-attention modules have recently achieved great empirical success in many tasks. However, theoretical learning generalization analysis is mostly noisy and elusive. This paper provides the first theoretical analysis of a shallow ViT for a classification task.
  arXiv  Detail & Related papers  (2023-02-12T22:12:35Z)
• Audio-Visual Efficient Conformer for Robust Speech Recognition [91.3755431537592]
  We propose to improve the noise of the recently proposed Efficient Conformer Connectionist Temporal Classification architecture by processing both audio and visual modalities. Our experiments show that using audio and visual modalities allows to better recognize speech in the presence of environmental noise and significantly accelerate training, reaching lower WER with 4 times less training steps.
  arXiv  Detail & Related papers  (2023-01-04T05:36:56Z)
• Adaptive Fourier Neural Operators: Efficient Token Mixers for Transformers [55.90468016961356]
  We propose an efficient token mixer that learns to mix in the Fourier domain. AFNO is based on a principled foundation of operator learning. It can handle a sequence size of 65k and outperforms other efficient self-attention mechanisms.
  arXiv  Detail & Related papers  (2021-11-24T05:44:31Z)
• FSR: Accelerating the Inference Process of Transducer-Based Models by Applying Fast-Skip Regularization [72.9385528828306]
  A typical transducer model decodes the output sequence conditioned on the current acoustic state. The number of blank tokens in the prediction results accounts for nearly 90% of all tokens. We propose a method named fast-skip regularization, which tries to align the blank position predicted by a transducer with that predicted by a CTC model.
  arXiv  Detail & Related papers  (2021-04-07T03:15:10Z)
• Learning from Heterogeneous EEG Signals with Differentiable Channel Reordering [51.633889765162685]
  CHARM is a method for training a single neural network across inconsistent input channels. We perform experiments on four EEG classification datasets and demonstrate the efficacy of CHARM.
  arXiv  Detail & Related papers  (2020-10-21T12:32:34Z)

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.