Pre-Deployment Complexity Estimation for Federated Perception Systems

2026-03-30

AI Summary

This work addresses the lack of effective methods to estimate the accuracy and communication overhead of federated learning tasks prior to deployment. The authors propose a classifier-agnostic, pre-deployment framework that, for the first time, integrates key characteristics—including data dimensionality, sparsity, heterogeneity, and client composition—to jointly model intrinsic data properties and the distributed environment. This integration yields a lightweight complexity metric capable of efficiently predicting both model performance and communication costs in federated settings. Through data attribute analysis, federated simulation, and correlation modeling, the proposed metric demonstrates strong alignment with actual training outcomes across multiple variants of MNIST and CIFAR benchmarks. The results highlight its practical utility for resource planning and feasibility assessment of federated learning tasks.

Abstract

Edge AI systems increasingly rely on federated learning to train perception models in distributed, privacy-preserving, and resource-constrained environments. Yet, before training begins, practitioners often lack practical tools to estimate how difficult a federated learning task will be in terms of achievable accuracy and communication cost. This paper presents a classifier-agnostic, pre-deployment framework for estimating learning complexity in federated perception systems by jointly modeling intrinsic properties of the data and characteristics of the distributed environment. The proposed complexity metric integrates dataset attributes such as dimensionality, sparsity, and heterogeneity with factors related to the composition of participating clients. Using federated learning as a representative distributed training setting, we examine how learning difficulty varies across different federated configurations. Experiments on multiple variants of the MNIST dataset and CIFAR dataset show that the proposed metric strongly correlates with federated learning performance and the communication effort required to reach fixed accuracy targets. These findings suggest that complexity estimation can serve as a practical diagnostic tool for resource planning, dataset assessment, and feasibility evaluation in edge-deployed perception systems.

Problem

• federated learning
• complexity estimation
• pre-deployment
• perception systems
• edge AI

Innovation

• federated learning
• complexity estimation
• pre-deployment analysis
• edge AI
• data heterogeneity