EAD: An EEG Adapter for Automated Classification

2025-05-29

AI Summary

To address the challenge of model non-reusability caused by heterogeneous channel counts across EEG acquisition devices, this paper proposes the EEG Adapter (EAD) framework—the first approach enabling channel-agnostic, robust embedding learning. Built upon a pre-trained EEG foundation model, EAD incorporates lightweight adapters, channel-normalized embedding alignment, and zero-shot prompt-based fine-tuning, supporting zero-shot transfer and multi-task generalization across arbitrary channel configurations. Evaluated on EEG-ImageNet and BrainLat, EAD achieves 99.33% and 92.31% classification accuracy, respectively—substantially outperforming existing baselines. Its core contribution lies in breaking the conventional reliance on fixed channel layouts, establishing the first general-purpose EEG representation learning paradigm compatible with heterogeneous recording hardware.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• User Modeling, Personalization and Recommendation: User modeling for targeted and personalized online advertising
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

While electroencephalography (EEG) has been a popular modality for neural decoding, it often involves task specific acquisition of the EEG data. This poses challenges for the development of a unified pipeline to learn embeddings for various EEG signal classification, which is often involved in various decoding tasks. Traditionally, EEG classification involves the step of signal preprocessing and the use of deep learning techniques, which are highly dependent on the number of EEG channels in each sample. However, the same pipeline cannot be applied even if the EEG data is collected for the same experiment but with different acquisition devices. This necessitates the development of a framework for learning EEG embeddings, which could be highly beneficial for tasks involving multiple EEG samples for the same task but with varying numbers of EEG channels. In this work, we propose EEG Adapter (EAD), a flexible framework compatible with any signal acquisition device. More specifically, we leverage a recent EEG foundational model with significant adaptations to learn robust representations from the EEG data for the classification task. We evaluate EAD on two publicly available datasets achieving state-of-the-art accuracies 99.33% and 92.31% on EEG-ImageNet and BrainLat respectively. This illustrates the effectiveness of the proposed framework across diverse EEG datasets containing two different perception tasks: stimulus and resting-state EEG signals. We also perform zero-shot EEG classification on EEG-ImageNet task to demonstrate the generalization capability of the proposed approach.

Problem

• Develop a unified EEG classification pipeline for varying channel counts
• Enable cross-device compatibility in EEG signal processing frameworks
• Improve generalization across diverse EEG datasets and perception tasks

Innovation

• Flexible EEG framework for various devices
• Adapts foundational model for robust representations
• Achieves high accuracy across diverse datasets