Cross-Session Decoding of Neural Spiking Data via Task-Conditioned Latent Alignment

TL;DR

The paper introduces TCLA, a framework that improves neural decoding across sessions by aligning latent neural representations, especially when target session data are limited.

Contribution

TCLA is a novel task-conditioned latent alignment method that enhances cross-session neural decoding by transferring learned representations from source to target sessions.

Findings

TCLA outperforms baseline methods in decoding accuracy.

Decoding performance gains of up to 0.386 in coefficient of determination.

Effective transfer of neural representations across sessions.

Abstract

Training a high-performing neural decoder can be difficult when only limited data are available from a recording session. To address this challenge, we propose a Task-Conditioned Latent Alignment framework (TCLA) for cross-session neural decoding with limited target-session data. Building upon an autoencoder architecture, TCLA first learns a low-dimensional neural representation from a source session with sufficient data. For target sessions with limited data, TCLA then aligns the target latent representations to the source session in a task-conditioned manner, enabling effective transfer of learned neural representations to support decoder training in the target session. We evaluate TCLA on the macaque motor and oculomotor center-out datasets. Compared to baseline methods trained solely on target-session data, TCLA consistently improves decoding performance across datasets and decoding settings, with gains in the coefficient of determination of up to 0.386 for y coordinate velocity decoding in a motor dataset. These results suggest that TCLA provides an effective strategy for transferring knowledge from source to target sessions, improving neural decoding performance under conditions with limited target-session data.