Amortized Network Intervention to Steer the Excitatory Point Processes

TL;DR

This paper introduces an Amortized Network Intervention framework using neural ODEs and mean-field approximation to efficiently steer event flows in dynamic graphs, with applications in epidemic control and traffic management.

Contribution

It proposes a novel ANI framework that enables efficient policy transfer across diverse contexts for controlling excitatory point processes on dynamic graphs.

Findings

Enhances policy learning for unseen network dynamics.

Demonstrates effectiveness on synthetic and real COVID datasets.

Improves efficiency of online planning through analytical mean-field approximation.

Abstract

Excitatory point processes (i.e., event flows) occurring over dynamic graphs (i.e., evolving topologies) provide a fine-grained model to capture how discrete events may spread over time and space. How to effectively steer the event flows by modifying the dynamic graph structures presents an interesting problem, motivated by curbing the spread of infectious diseases through strategically locking down cities to mitigating traffic congestion via traffic light optimization. To address the intricacies of planning and overcome the high dimensionality inherent to such decision-making problems, we design an Amortized Network Interventions (ANI) framework, allowing for the pooling of optimal policies from history and other contexts while ensuring a permutation equivalent property. This property enables efficient knowledge transfer and sharing across diverse contexts. Each task is solved by an H-step lookahead model-based reinforcement learning, where neural ODEs are introduced to model the dynamics of the excitatory point processes. Instead of simulating rollouts from the dynamics model, we derive an analytical mean-field approximation for the event flows given the dynamics, making the online planning more efficiently solvable. We empirically illustrate that this ANI approach substantially enhances policy learning for unseen dynamics and exhibits promising outcomes in steering event flows through network intervention using synthetic and real COVID datasets.