Cross-Modal Representational Knowledge Distillation for Enhanced Spike-Informed LFP Modeling
This work addresses a domain-specific problem in neural modeling for neuroscience, offering a scalable method to improve LFP accuracy, though it is incremental as it builds on existing transformer and distillation techniques.
The paper tackled the challenge of modeling local field potentials (LFPs), which have lower predictive power than spiking activity, by introducing a cross-modal knowledge distillation framework that transfers knowledge from spike models to LFP models. The distilled LFP models outperformed baselines in unsupervised and supervised settings, generalizing to other sessions without additional distillation.
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.