LGAIGTMay 6

Knowledge-Free Correlated Agreement for Incentivizing Federated Learning

arXiv:2605.0474763.1h-index: 3
AI Analysis

Provides a practical, trust-free incentive mechanism for federated learning, particularly relevant for decentralized and blockchain-based systems.

KFCA rewards client contributions in federated learning without ground truth or public test sets, achieving strict truthfulness under honest majority and label-flipping robustness. It demonstrates efficient real-time reward computation on LLM adapter tuning and PCB inspection tasks.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes