Cross-Session Decoding of Neural Spiking Data via Task-Conditioned Latent Alignment
This addresses a major challenge for invasive BCIs by enabling more robust neural decoding under limited data conditions, though it is incremental as it builds on autoencoder architectures.
The paper tackles the problem of cross-session nonstationarity in neural activity for brain-computer interfaces, where decoders fail to generalize across sessions with limited data, and proposes a Task-Conditioned Latent Alignment framework that improves decoding performance, achieving gains of up to 0.386 in coefficient of determination for velocity decoding.
Cross-session nonstationarity in neural activity recorded by implanted electrodes is a major challenge for invasive Brain-computer interfaces (BCIs), as decoders trained on data from one session often fail to generalize to subsequent sessions. This issue is further exacerbated in practice, as retraining or adapting decoders becomes particularly challenging when only limited data are available from a new session. To address this challenge, we propose a Task-Conditioned Latent Alignment framework (TCLA) for cross-session neural decoding. Building upon an autoencoder architecture, TCLA first learns a low-dimensional representation of neural dynamics from a source session with sufficient data. For target sessions with limited data, TCLA then aligns target latent representations to the source in a task-conditioned manner, enabling effective transfer of learned neural dynamics. We evaluate TCLA on the macaque motor and oculomotor center-out dataset. 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, enabling more robust neural decoding under conditions with limited data.