Reputation-Driven Asynchronous Federated Learning for Enhanced Trajectory Prediction with Blockchain

TL;DR

This paper introduces a reputation-driven asynchronous federated learning framework utilizing blockchain and graph neural networks to improve data security and prediction accuracy in autonomous vehicle trajectory prediction.

Contribution

It presents a novel reputation quantization mechanism combined with deep reinforcement learning for efficient, secure, and privacy-preserving federated data sharing in autonomous driving.

Findings

Enhanced trajectory prediction accuracy

Improved data security through blockchain and differential privacy

Efficient reputation-based data aggregation

Abstract

Federated learning combined with blockchain empowers secure data sharing in autonomous driving applications. Nevertheless, with the increasing granularity and complexity of vehicle-generated data, the lack of data quality audits raises concerns about multi-party mistrust in trajectory prediction tasks. In response, this paper proposes an asynchronous federated learning data sharing method based on an interpretable reputation quantization mechanism utilizing graph neural network tools. Data providers share data structures under differential privacy constraints to ensure security while reducing redundant data. We implement deep reinforcement learning to categorize vehicles by reputation level, which optimizes the aggregation efficiency of federated learning. Experimental results demonstrate that the proposed data sharing scheme not only reinforces the security of the trajectory prediction task but also enhances prediction accuracy.