Communication-efficient Decentralised Federated Learning via Low Huffman-coded Delta Quantization Scheme
Mahdi Barhoush, Ahmad Ayad, Mohammad Kohankhaki, Anke Schmeink · 2024
Federated Learning (FL) revolutionizes distributed machine learning, enabling clients to learn collaboratively while keeping data private. In contrast, Decentralized Federated Learning (DFL) offers direct communication between clients without a central server, improving fault tolerance and network efficiency, but communication overhead remains a challenge. To address this, we propose a new scheme called Low Huffman-coded Delta Quantization (LHDQ) which achieves a remarkable quantization rate of $\frac{5}{3}$ bits per parameter. We evaluate LHDQ within the DFL architecture under two proposed transmission protocols and compare it against conventional quantization schemes under various communication channel conditions. Despite a slight reduction in accuracy, LHDQ offers compelling advantages as alleviating communication bottlenecks, reducing transmitted bits, and accelerating training and convergence processes.