Work

Pretraining for Sample-Efficient Neural Interfaces

Year: 2026

Type: preprint

Abstract: Brain-computer interfaces (BCIs) decode neural activity to restore lost function. Typically, training a high-performance neural decoder requires a large labeled dataset to be collected from every new subject. One way to reduce the labeled data cost is self-supervised pretraining, which learns general neural representations from unlabeled recordings that accumulate across subjects. However, for intracranial electroencephalography (iEEG) recordings, self-supervised learning has been challenging due to differences in contact placement and neuroanatomy between subjects. We propose MAPA, an otherwise vanilla masked autoencoder with two spatial encodings, an anatomical region embedding and a relative positional encoding, which together enable it to learn neural representations that transfer to unseen subjects and across various tasks. MAPA sets a new state of the art across all three regimes of the Neuroprobe benchmark without fine-tuning: within-session, cross-session, and cross-subject. In the cross-subject regime, a linear probe on MAPA's features needs only ~164 labeled trials to reach the accuracy that takes 3,500 without pretraining. Our results show that self-supervised pretraining can scale across heterogeneous iEEG recordings and reduce the labeled data needed for accurate decoding in new subjects.

Source: PubMed

DOI: 10.48550/arxiv.2609.13507

Authors: Tang, Ben, Spalding, Zachary, Cogan, Gregory B.

Institution: Duke University

Language: English

Topic: EEG and Brain-Computer Interfaces

Subfield: Cognitive Neuroscience

Field: Neuroscience

Domain: Life Sciences

SDG: Good health and well-being

Open Access status: green