SCOPE-FL: A Strategy-proof Chain-based Optimal pareto efficient Federated Learning System

2026-06-16

AI Summary

This work addresses the lack of Pareto efficiency and strategyproofness in client selection mechanisms for hierarchical federated learning, which often leads to suboptimal resource allocation and incentive misalignment due to preference misreporting. The authors formulate this problem as a two-sided school choice model and propose a novel framework that integrates the Top Trading Cycle algorithm to achieve Pareto-optimal and strategyproof client matching. Fair contribution-based rewards are allocated via a one-round reconstruction-based Shapley value approximation (OR method). The entire mechanism is implemented through blockchain smart contracts to ensure incentive compatibility and on-chain verifiability. Experimental results on MNIST, Fashion-MNIST, and CIFAR-10 demonstrate that the proposed approach significantly outperforms baseline methods such as DA and IAS in terms of accuracy, convergence speed, and reward efficiency, while maintaining comparable communication overhead and substantially reducing blockchain costs in large-scale settings.

Abstract

Hierarchical Federated Learning (HFL) enables scalable collaborative model training across distributed devices while preserving data privacy. However, existing HFL client selection mechanisms suffer from a fundamental strategic inefficiency. By prioritizing stability over Pareto efficiency (PE), they produce suboptimal resource allocations, and without strategy proofness (SP), participants are incentivized to misrepresent their true preferences, both failures degrading system overall welfare in the Pareto sense in practice. To address it, we propose SCOPE-FL (Strategy-proof Chain-based Optimal pareto efficient Federated Learning), a synchronous HFL framework that formulates client selection as a two-sided school choice problem solved through the Top Trading Cycle (TTC) algorithm that simultaneously guarantees PE and SP. For reward distribution, SCOPE-FL employs a scalable Shapley value approximation based on One-Round Reconstruction (OR), ensuring compensation proportional to each client's contribution. The entire mechanism executes via blockchain smart contracts, providing the tamper-proof environment required for the SP guarantees to hold in practice. A comprehensive evaluation on MNIST, Fashion-MNIST, and CIFAR-10 demonstrates that SCOPE-FL outperforms state-of-the-art approaches, including DA, IAS, and other methods across model accuracy, convergence rate, and reward efficiency, while achieving communication latency comparable to DA and blockchain overhead significantly lower than DA at scale.

Problem

• Hierarchical Federated Learning
• Pareto efficiency
• Strategy-proofness
• Client selection
• Resource allocation

Innovation

• Strategy-proof
• Pareto efficiency
• Top Trading Cycle
• Shapley value approximation
• Blockchain smart contracts