Federated Gaussian Process Learning via Pseudo-Representations for Large-Scale Multi-Robot Systems

2026-02-12

AI Summary

This work addresses the challenges of scaling Gaussian processes (GPs) to large-scale multi-robot systems, where cubic computational complexity and communication constraints hinder efficient federated modeling. To overcome these limitations, the authors propose the pxpGP framework, which leverages sparse variational inference to generate compact local pseudo-representations. A novel global approximate consensus ADMM algorithm is developed, integrating local pseudo-dataset constraints, adaptive parameter updates, and warm-start initialization to enable scalable federated GP learning in both centralized and decentralized network topologies. Experimental results on synthetic and real-world datasets demonstrate that pxpGP and its decentralized variant, dec-pxpGP, outperform existing distributed GP approaches in terms of hyperparameter estimation accuracy, predictive performance, and communication efficiency in large-scale scenarios.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Intelligent Robots: State Estimation
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Multi-robot systems require scalable and federated methods to model complex environments under computational and communication constraints. Gaussian Processes (GPs) offer robust probabilistic modeling, but suffer from cubic computational complexity, limiting their applicability in large-scale deployments. To address this challenge, we introduce the pxpGP, a novel distributed GP framework tailored for both centralized and decentralized large-scale multi-robot networks. Our approach leverages sparse variational inference to generate a local compact pseudo-representation. We introduce a sparse variational optimization scheme that bounds local pseudo-datasets and formulate a global scaled proximal-inexact consensus alternating direction method of multipliers (ADMM) with adaptive parameter updates and warm-start initialization. Experiments on synthetic and real-world datasets demonstrate that pxpGP and its decentralized variant, dec-pxpGP, outperform existing distributed GP methods in hyperparameter estimation and prediction accuracy, particularly in large-scale networks.

Problem

• Federated Learning
• Gaussian Processes
• Multi-Robot Systems
• Scalability
• Distributed Inference

Innovation

• Federated Learning
• Gaussian Process
• Sparse Variational Inference
• Decentralized Optimization
• ADMM