BACE: Behavior-Adaptive Connectivity Estimation for Interpretable Graphs of Neural Dynamics

Mehrnaz Asadi, Sina Javadzadeh, Rahil Soroushmojdehi, S. Alireza Seyyed Mousavi, Terence Sanger

Keywords: Effective Connectivity - Neural Forecasting - Graph Neural Networks

Abstract:

Understanding how distributed brain regions coordinate to produce behavior requires
models that are both predictive and interpretable. We introduce Behavior-
Adaptive Connectivity Estimation (BACE), an end-to-end framework that learns
context-specific, directed inter-regional connectivity directly from multi-region intracranial
local field potentials (LFP). BACE aggregates many micro-contacts
within each anatomical region via per-region temporal encoders, applies a learnable
adjacency specific to each behavioral context, and is trained on a forecasting
objective. On synthetic multivariate time series with known graphs, BACE accurately
recovers ground-truth directed interactions while achieving forecasting
performance comparable to state-of-the-art baselines. Applied to human subcortical
LFP recorded simultaneously from eight regions during a cued reaching task,
BACE yields an explicit 8×8 connectivity matrix for each within-trial behavioral
context. The resulting behavioral context-specific graphs reveal behavior-aligned reconfiguration
of inter-regional influence and provide compact, interpretable adjacency
matrices for comparing network organization across behavioral contexts. By
linking predictive success to explicit connectivity estimates, BACE offers a practical
tool for generating data-driven hypotheses about the dynamic coordination
of subcortical regions during behavior.

Primary Area: applications to neuroscience & cognitive science

Submission Number: 8089