Cross-Modal Representational Knowledge Distillation for Enhanced Spike-Informed LFP Modeling

TL;DR

This paper introduces a cross-modal knowledge distillation method that transfers high-quality spike model representations to improve LFP modeling, enhancing predictive accuracy and generalization in neural data analysis.

Contribution

It presents a novel framework for transferring knowledge from spike transformer models to LFP models, addressing inherent challenges in LFP signal modeling.

Findings

Distilled LFP models outperform baselines in various settings.

Models generalize to new sessions without additional training.

Cross-modal distillation improves LFP predictive power.

Abstract

Local field potentials (LFPs) can be routinely recorded alongside spiking activity in intracortical neural experiments, measure a larger complementary spatiotemporal scale of brain activity for scientific inquiry, and can offer practical advantages over spikes, including greater long-term stability, robustness to electrode degradation, and lower power requirements. Despite these advantages, recent neural modeling frameworks have largely focused on spiking activity since LFP signals pose inherent modeling challenges due to their aggregate, population-level nature, often leading to lower predictive power for downstream task variables such as motor behavior. To address this challenge, we introduce a cross-modal knowledge distillation framework that transfers high-fidelity representational knowledge from pretrained multi-session spike transformer models to LFP transformer models. Specifically, we first train a teacher spike model across multiple recording sessions using a masked autoencoding objective with a session-specific neural tokenization strategy. We then align the latent representations of the student LFP model to those of the teacher spike model. Our results show that the Distilled LFP models consistently outperform single- and multi-session LFP baselines in both fully unsupervised and supervised settings, and can generalize to other sessions without additional distillation while maintaining superior performance. These findings demonstrate that cross-modal knowledge distillation is a powerful and scalable approach for leveraging high-performing spike models to develop more accurate LFP models.