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

arXiv: https://arxiv.org/abs/2606.20955 · HTML: https://mlsanity.com/paper/2606.20955/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 29 references that are in the map.
- First posted on arXiv 18 Jun 2026.

## Builds on (most cited first, 5 of 5)

- [Gated Graph Recurrent Neural Networks](https://mlsanity.com/paper/2002.01038/) (2020)
- [Message-Aware Graph Attention Networks for Large-Scale Multi-Robot Path Planning](https://mlsanity.com/paper/2011.13219/) (2020)
- [Multi-Robot Coverage and Exploration using Spatial Graph Neural Networks](https://mlsanity.com/paper/2011.01119/) (2020)
- [Graph Neural Networks for Decentralized Controllers](https://mlsanity.com/paper/2003.10280/) (2020)
- [Tutorial on dynamic average consensus: the problem, its applications, and the algorithms](https://mlsanity.com/paper/1803.04628/) (2018)

## Abstract (arXiv)

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.