Neural Topographic Factor Analysis for fMRI Data
This work addresses the challenge of analyzing small-sample neuroimaging data for researchers in neuroscience, though it appears incremental as it builds on existing topographic methods.
The authors tackled the problem of modeling individual participant and stimulus variations in fMRI data by proposing Neural Topographic Factor Analysis (NTFA), a probabilistic factor analysis model that infers embeddings, and demonstrated improved predictive generalization to unseen data compared to previous topographic methods.
Neuroimaging studies produce gigabytes of spatio-temporal data for a small number of participants and stimuli. Rarely do researchers attempt to model and examine how individual participants vary from each other -- a question that should be addressable even in small samples given the right statistical tools. We propose Neural Topographic Factor Analysis (NTFA), a probabilistic factor analysis model that infers embeddings for participants and stimuli. These embeddings allow us to reason about differences between participants and stimuli as signal rather than noise. We evaluate NTFA on data from an in-house pilot experiment, as well as two publicly available datasets. We demonstrate that inferring representations for participants and stimuli improves predictive generalization to unseen data when compared to previous topographic methods. We also demonstrate that the inferred latent factor representations are useful for downstream tasks such as multivoxel pattern analysis and functional connectivity.