Disentangling Shared and Private Neural Dynamics with SPIRE: A Latent Modeling Framework for Deep Brain Stimulation
This work addresses a central challenge in neural data analysis for researchers studying brain stimulation, offering a practical tool, though it appears incremental as it builds on existing autoencoder methods with novel losses.
The paper tackled the problem of disentangling shared and private neural dynamics in multi-region data, introducing SPIRE, a deep autoencoder framework that factorizes recordings into latent subspaces. It showed that SPIRE outperforms classical models on synthetic benchmarks and reliably encodes stimulation-specific signatures in deep brain stimulation recordings, generalizing across sites and frequencies.
Disentangling shared network-level dynamics from region-specific activity is a central challenge in modeling multi-region neural data. We introduce SPIRE (Shared-Private Inter-Regional Encoder), a deep multi-encoder autoencoder that factorizes recordings into shared and private latent subspaces with novel alignment and disentanglement losses. Trained solely on baseline data, SPIRE robustly recovers cross-regional structure and reveals how external perturbations reorganize it. On synthetic benchmarks with ground-truth latents, SPIRE outperforms classical probabilistic models under nonlinear distortions and temporal misalignments. Applied to intracranial deep brain stimulation (DBS) recordings, SPIRE shows that shared latents reliably encode stimulation-specific signatures that generalize across sites and frequencies. These results establish SPIRE as a practical, reproducible tool for analyzing multi-region neural dynamics under stimulation.