Knowledge-Free Correlated Agreement for Incentivizing Federated Learning

2026-05-06

Abstract

We introduce Knowledge-Free Correlated Agreement (KFCA) to reward client contributions in federated learning (FL) without relying on ground truth, a public test set, or distribution knowledge. Under categorical reports and an honest majority, KFCA is strictly truthful, addressing the label-flipping vulnerability of Correlated Agreement (CA). We evaluate KFCA on federated LLM adapter tuning and a real-world PCB inspection task, showing efficient real-time reward computation suitable for decentralized and blockchain-based incentive designs.

Problem

• Federated Learning
• Incentive Mechanism
• Truthful Reporting
• Label-Flipping Attack
• Decentralized Reward

Innovation

• Knowledge-Free Correlated Agreement
• federated learning
• incentive mechanism
• truthful mechanism
• blockchain-based incentives