A Gated Graph Neural Network Approach to Fast-Convergent Dynamic Average Estimation

2026-06-18

AI Summary

This work addresses the challenges of slow convergence and topology sensitivity in dynamic average consensus within multi-agent systems. It introduces, for the first time, Gated Graph Neural Networks (GGNNs) to this task and proposes a distributed autoregressive learning framework. The approach employs an encoder–decoder architecture to compress communication overhead and incorporates a convergence-regularization term during training to ensure stability. Evaluated across diverse network conditions, the method significantly outperforms conventional model-driven algorithms, achieving high estimation accuracy while substantially accelerating convergence and enhancing robustness to topological changes.

Abstract

Dynamic average estimation is a critical problem in multi-agent systems, enabling agents to collaboratively estimate time-varying signals using only local information exchange. Traditional model-based approaches often face challenges related to convergence speed and sensitivity to network topology changes. This paper introduces a novel learning-based solution leveraging Gated Graph Neural Networks (GGNNs) for fast-convergent dynamic average estimation in a fully distributed manner. Taking advantage of the inherent structure of GGNNs, the proposed method models the estimation process as a distributed autoregressor, ensuring rapid convergence while maintaining stability. We incorporate a regularization term during training to enforce convergence guarantees and introduce an encoding-decoding mechanism to reduce communication overhead without sacrificing accuracy compared to standard GGNNs. Extensive numerical experiments demonstrate that our approach significantly outperforms conventional model-based estimators in terms of both convergence speed and precision, making it a promising alternative for multi-agent applications that require dynamic average estimation.

Problem

• dynamic average estimation
• multi-agent systems
• fast convergence
• distributed estimation
• time-varying signals

Innovation

• Gated Graph Neural Networks
• dynamic average estimation
• distributed autoregressor
• convergence guarantee
• communication efficiency