Taming Epilepsy: Mean Field Control of Whole-Brain Dynamics

2026-03-11

AI Summary

This work addresses the challenge of controlling high-dimensional, nonlinear neural dynamics during epileptic seizures while preserving the complex topological structure of functional brain networks. To this end, we propose a Graph-regularized Koopman Mean Field Game (GK-MFG) framework, which uniquely integrates Koopman operator theory with mean field game theory. By leveraging reservoir computing, the method embeds EEG dynamics into a low-dimensional linear latent space, and incorporates a graph Laplacian regularizer derived from phase-locking value (PLV)-based functional connectivity to retain network topology. The resulting approach enables distributionally robust, scalable, and structure-aware seizure control, significantly enhancing control performance without disrupting intrinsic brain network architecture, thereby demonstrating its efficacy and superiority in regulating high-dimensional neural dynamics.

Technology Category

• Game Theory and Economic Paradigms: Cooperative Game Theory
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Graph-based Machine Learning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

Controlling the high-dimensional neural dynamics during epileptic seizures remains a significant challenge due to the nonlinear characteristics and complex connectivity of the brain. In this paper, we propose a novel framework, namely Graph-Regularized Koopman Mean-Field Game (GK-MFG), which integrates Reservoir Computing (RC) for Koopman operator approximation with Alternating Population and Agent Control Network (APAC-Net) for solving distributional control problems. By embedding Electroencephalogram (EEG) dynamics into a linear latent space and imposing graph Laplacian constraints derived from the Phase Locking Value (PLV), our method achieves robust seizure suppression while respecting the functional topological structure of the brain.

Problem

• epilepsy
• neural dynamics
• brain connectivity
• seizure control
• high-dimensional control

Innovation

• Koopman operator
• Mean-Field Game
• Reservoir Computing
• Graph Laplacian regularization
• Epilepsy control