Decentralized Learning

This paper proposes SketchGuard, a novel framework that scales Byzantine-robust decentralized federated learning through sketch-based compression, achieving up to 82% reduction in computation time and 50-70% communication savings while maintaining identical robustness to state-of-the-art methods.

This chapter presents a comprehensive taxonomy of blockchain-enabled federated learning (BCFL) systems, analyzing coordination structures, consensus mechanisms, storage architectures, and trust models to demonstrate how specialized protocols can enable trustless collaborative machine learning across diverse domains.