Mean-Field Control on Sparse Graphs: From Local Limits to GNNs via Neighborhood Distributions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Schmidt, Tobias, Cui, Kai
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917231347105792
author Schmidt, Tobias
Cui, Kai
author_facet Schmidt, Tobias
Cui, Kai
contents Mean-field control (MFC) offers a scalable solution to the curse of dimensionality in multi-agent systems but traditionally hinges on the restrictive assumption of exchangeability via dense, all-to-all interactions. In this work, we bridge the gap to real-world network structures by proposing a rigorous framework for MFC on large sparse graphs. We redefine the system state as a probability measure over decorated rooted neighborhoods, effectively capturing local heterogeneity. Our central contribution is a theoretical foundation for scalable reinforcement learning in this setting. We prove horizon-dependent locality: for finite-horizon problems, an agent's optimal policy at time t depends strictly on its (T-t)-hop neighborhood. This result renders the infinite-dimensional control problem tractable and underpins a novel Dynamic Programming Principle (DPP) on the lifted space of neighborhood distributions. Furthermore, we formally and experimentally justify the use of Graph Neural Networks (GNNs) for actor-critic algorithms in this context. Our framework naturally recovers classical MFC as a degenerate case while enabling efficient, theoretically grounded control on complex sparse topologies.
format Preprint
id arxiv_https___arxiv_org_abs_2601_21477
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Mean-Field Control on Sparse Graphs: From Local Limits to GNNs via Neighborhood Distributions
Schmidt, Tobias
Cui, Kai
Multiagent Systems
Artificial Intelligence
Machine Learning
Optimization and Control
Mean-field control (MFC) offers a scalable solution to the curse of dimensionality in multi-agent systems but traditionally hinges on the restrictive assumption of exchangeability via dense, all-to-all interactions. In this work, we bridge the gap to real-world network structures by proposing a rigorous framework for MFC on large sparse graphs. We redefine the system state as a probability measure over decorated rooted neighborhoods, effectively capturing local heterogeneity. Our central contribution is a theoretical foundation for scalable reinforcement learning in this setting. We prove horizon-dependent locality: for finite-horizon problems, an agent's optimal policy at time t depends strictly on its (T-t)-hop neighborhood. This result renders the infinite-dimensional control problem tractable and underpins a novel Dynamic Programming Principle (DPP) on the lifted space of neighborhood distributions. Furthermore, we formally and experimentally justify the use of Graph Neural Networks (GNNs) for actor-critic algorithms in this context. Our framework naturally recovers classical MFC as a degenerate case while enabling efficient, theoretically grounded control on complex sparse topologies.
title Mean-Field Control on Sparse Graphs: From Local Limits to GNNs via Neighborhood Distributions
topic Multiagent Systems
Artificial Intelligence
Machine Learning
Optimization and Control
url https://arxiv.org/abs/2601.21477