FedSharp framework enhances decentralized federated learning against attacks

Researchers have developed FedSharp, a novel framework designed to enhance the robustness of decentralized federated learning systems against Byzantine attacks and channel noise. This approach addresses the issue of noise accumulation during model propagation by incorporating screened, hop-aware, ranked, and proximal averaging techniques. Experiments demonstrate FedSharp's significant performance improvements on datasets like MNIST and CIFAR-10, outperforming existing benchmarks in scenarios with a substantial number of Byzantine nodes and noisy channels. AI

IMPACT Improves security and reliability of distributed AI training, potentially enabling more robust collaborative model development.

RANK_REASON The cluster contains an academic paper detailing a new method for decentralized federated learning. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• arXiv
• CIFAR-10
• FedSharp
• Hugging Face
• MNIST database

• paper
• safety

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →