Graph Adapter of EEG Foundation Models for Parameter Efficient Fine Tuning
원문 초록
In diagnosing neurological disorders from electroencephalography (EEG) data, foundation models such as Transformers have been employed to capture temporal dynamics. Additionally, Graph Neural Networks (GNNs) are critical for representing the spatial relationships among EEG sensors. However, fine-tuning these large-scale models for both temporal and spatial features can be prohibitively large in computational cost, especially under the limited availability of labeled EEG datasets. We propose EEG-GraphAdapter (EGA), a parameter-efficient fine-tuning (PEFT) approach designed to address these challenges. EGA is integrated into a pre-trained temporal backbone model as a GNN-based module, freezing the backbone and allowing only the adapter to be fine-tuned. This enables the effective acquisition of EEG spatial representations, significantly reducing computational overhead and data requirements. Experimental evaluations on two healthcare-related downstream tasks-Major Depressive Disorder (MDD) and Abnormality Detection (TUAB)-show that EGA improves performance by up to 16.1% in F1-score compared with the backbone BENDR model, highlighting its potential for scalable and accurate EEG-based predictions.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Chi-Square Wavelet Graph Neural Networks for Heterogeneous Graph Anomaly Detection
Towards High-Resolution 3D Anomaly Detection: A Scalable Dataset and Real-Time Framework for Subtle Industrial Defects
eegFloss: A Python package for refining sleep EEG recordings using machine learning models
LoSiA: Efficient High-Rank Fine-Tuning via Subnet Localization and Optimization
Evaluating Language Models For Threat Detection in IoT Security Logs
DBConformer: Dual-Branch Convolutional Transformer for EEG Decoding
토론
이 논문과 연결된 포럼 글이 아직 없습니다.