Rate-Constrained Quantization for Communication-Efficient Federated Learning
This work addresses communication efficiency for federated learning systems, but it is incremental as it builds on existing quantization and entropy coding methods.
The authors tackled the communication overhead in federated learning by developing RC-FED, a framework that quantizes gradients under both fidelity and rate constraints, achieving a tunable trade-off and showing superior performance against baseline schemes on multiple datasets.
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 determined by the bit rate of the encoded gradients. Recognizing this fact, this work deviates from the existing approaches in the literature and develops a novel quantized FL framework, called \textbf{r}ate-\textbf{c}onstrained \textbf{fed}erated learning (RC-FED), in which the gradients are quantized subject to both fidelity and data rate constraints. We formulate this scheme, as a joint optimization in which the quantization distortion is minimized while the rate of encoded gradients is kept below a target threshold. This enables for a tunable trade-off between quantization distortion and communication cost. We analyze the convergence behavior of RC-FED, and show its superior performance against baseline quantized FL schemes on several datasets.