Subject Representation Learning from EEG using Graph Convolutional Variational Autoencoders

We propose GC-VASE, a graph convolutional-based variational autoencoder that leverages contrastive learning for subject representation learning from EEG data. Our method successfully learns robust subject-specific latent representations using the split-latent space architecture tailored for subject...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) S. 1 - 5
Hauptverfasser: Mishra, Aditya, Samin, Ahnaf Mozib, Etemad, Ali, Hashemi, Javad
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 06.04.2025
Schlagworte:
Accuracy
Adaptation models
Adapters
Autoencoders
Brain modeling
Computational modeling
Contrastive learning
EEG
Electroencephalography
GNNs
Medical diagnosis
Representation learning
Speech processing
ISSN:2379-190X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We propose GC-VASE, a graph convolutional-based variational autoencoder that leverages contrastive learning for subject representation learning from EEG data. Our method successfully learns robust subject-specific latent representations using the split-latent space architecture tailored for subject identification. To enhance the model's adaptability to unseen subjects without extensive retraining, we introduce an attention-based adapter network for fine-tuning, which reduces the computational cost of adapting the model to new subjects. Our method significantly outperforms other deep learning approaches, achieving state-of-the-art results with a subject balanced accuracy of 89.81% on the ERP-Core dataset and 70.85% on the SleepEDFx-20 dataset. After subject adaptive fine-tuning using adapters and attention layers, GC-VASE further improves the subject balanced accuracy to 90.31% on ERP-Core. Additionally, we perform a detailed ablation study to highlight the impact of the key components of our method.
ISSN:2379-190X
DOI:10.1109/ICASSP49660.2025.10890073