aiqbench analysis
This research introduces USE-FM, a lightweight EEG foundation model that achieves competitive performance in cross-disorder transfer with only 1.46 million parameters. By freezing the encoder after self-supervised pretraining, it offers a computationally efficient alternative to larger models for tasks like seizure recognition and abnormal EEG detection. The study demonstrates that smaller architectures can learn semantic neural representations comparable to massive foundation models, addressing critical resource constraints in clinical applications.
Lightweight Semantic EEG Foundation Model for Frozen Cross-Disorder Transfer
arXiv:2610.05503v1 Announce Type: new Abstract: Large-scale EEG foundation models have demonstrated promising transferability across neurological disorders, but often require millions of parameters and substantial computational resources. In this paper, we present the Universal Semantic EEG Foundation Model (USE-FM), a lightweight EEG foundation model that learns transferable neural representations through self-supervised signal reconstruction on the Temple University Hospital EEG Corpus (TUEG). After pretraining, the encoder is frozen and evaluated on two clinically distinct downstream tasks, abnormal EEG detection (TUAB) and epileptic seizure recognition (TUEP), using a unified frozen-transfer protocol against recent EEG foundation models, including LUNA-Base and CBraMod. With only 1.46 million parameters, approximately one-fifth the size of existing models, USE-FM achieves competitive overall performance, including strong sensitivity and F1-score on TUEP (SEN $75.00 \pm 14.14$, F1 $70.37 \pm 4.01$), while maintaining competitive performance on TUAB (AUC $85.24 \pm 5.61$). Beyond downstream classification, latent representation analysis using $k$-means clustering together with PCA and t-SNE demonstrates that USE-FM learns organized semantic EEG representations comparable to substantially larger foundation models. These results suggest that large-scale self-supervised pretraining enables lightweight architectures to learn transferable semantic EEG representations, providing a computationally efficient foundation for cross-disorder analysis and future clinical decision support in neurological disorders.
Abstract:Large-scale EEG foundation models have demonstrated promising transferability across neurological disorders, but often require millions of parameters and substantial computational resources. In this paper, we present the Universal Semantic EEG Foundation Model (USE-FM), a lightweight EEG foundation model that learns transferable neural representations through self-supervised signal reconstruction on the Temple University Hospital EEG Corpus (TUEG). After pretraining, the encoder is frozen and evaluated on two clinically distinct downstream tasks, abnormal EEG detection (TUAB) and epileptic seizure recognition (TUEP), using a unified frozen-transfer protocol against recent EEG foundation models, including LUNA-Base and CBraMod. With only 1.46 million parameters, approximately one-fifth the size of existing models, USE-FM achieves competitive overall performance, including strong sensitivity and F1-score on TUEP (SEN $75.00 \pm 14.14$, F1 $70.37 \pm 4.01$), while maintaining competitive performance on TUAB (AUC $85.24 \pm 5.61$). Beyond downstream classification, latent representation analysis using $k$-means clustering together with PCA and t-SNE demonstrates that USE-FM learns organized semantic EEG representations comparable to substantially larger foundation models. These results suggest that large-scale self-supervised pretraining enables lightweight architectures to learn transferable semantic EEG representations, providing a computationally efficient foundation for cross-disorder analysis and future clinical decision support in neurological disorders.
Machine Learning (cs.LG); Signal Processing (eess.SP); Neurons and Cognition (q-bio.NC)
arXiv:2610.05503 [cs.LG]
(or arXiv:2610.05503v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2610.05503 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 295 words
Related coverage
Foundation Models for Face Presentation Attack Detection: A Unified Linear-Probing Benchmark
arXiv · Jul 30, 2026
G2G: Exploiting Intra-Group Geometry for Inter-Group Pose Estimation
arXiv · Jun 9, 2026
DPNeXt: A Lightweight Multi-Scale Feature Fusion Framework for Efficient ViT-Based Multi-Task Dense Prediction
arXiv · Jul 20, 2026
FedTaste: Topology-Aware Structural Transfer for Multimodal Federated Learning with Missing Modalities
arXiv · Jul 28, 2026