Functional embeddings enable Aggregation of multi-area SEEG recordings over subjects and sessions

TL;DR

This paper introduces a scalable, functional embedding framework for aggregating multi-region SEEG recordings across subjects, enabling zero-shot transfer, cross-region modeling, and improved neural data analysis without strict task or sensor uniformity.

Contribution

The authors develop a novel representation-learning framework using Siamese encoders and transformers that captures subject-agnostic neural signatures and models inter-regional dependencies in intracranial recordings.

Findings

Embeddings support accurate within-subject discrimination.

Embeddings form clear, region-consistent clusters.

Framework transfers zero-shot to unseen channels.

Abstract

Aggregating intracranial recordings across subjects is challenging since electrode count, placement, and covered regions vary widely. Spatial normalization methods like MNI coordinates offer a shared anatomical reference, but often fail to capture true functional similarity, particularly when localization is imprecise; even at matched anatomical coordinates, the targeted brain region and underlying neural dynamics can differ substantially between individuals. We propose a scalable representation-learning framework that (i) learns a subject-agnostic functional identity for each electrode from multi-region local field potentials using a Siamese encoder with contrastive objectives, inducing an embedding geometry that is locality-sensitive to region-specific neural signatures, and (ii) tokenizes these embeddings for a transformer that models inter-regional relationships with a variable number of channels. We evaluate this framework on a 20-subject dataset spanning basal ganglia-thalamic regions collected during flexible rest/movement recording sessions with heterogeneous electrode layouts. The learned functional space supports accurate within-subject discrimination and forms clear, region-consistent clusters; it transfers zero-shot to unseen channels. The transformer, operating on functional tokens without subject-specific heads or supervision, captures cross-region dependencies and enables reconstruction of masked channels, providing a subject-agnostic backbone for downstream decoding. Together, these results indicate a path toward large-scale, cross-subject aggregation and pretraining for intracranial neural data where strict task structure and uniform sensor placement are unavailable.