Rate-Constrained Quantization for Communication-Efficient Federated Learning

• Published in: Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) pp. 1 - 5
• Main Authors: Hamidi, Shayan Mohajer, Bereyhi, Ali
• Format: Conference Proceeding
• Language: English
• Published: IEEE 06.04.2025
• Subjects: Accuracy; Acoustic distortion; Convergence; Costs; Federated learning; Huffman coding; Lloyd-Max algorithm; Optimization; Quantization (signal); scalar quantization; Signal processing algorithms; source coding; Speech processing
• ISSN: 2379-190X
• DOI: 10.1109/ICASSP49660.2025.10889213

Quantization is a common approach to mitigate the communication cost of federated learning (FL). In practice, the quantized local parameters are further encoded via an entropy coding technique, such as Huffman coding, for efficient data compression. In this case, the exact communication overhead is...