Mixed-Precision Quantization for Federated Learning on Resource-Constrained Heterogeneous Devices
This work addresses efficiency challenges in federated learning for resource-constrained heterogeneous devices, though it is incremental as it adapts an existing technique to a new setting.
The paper tackles the problem of deploying mixed-precision quantization in federated learning to address communication and computational bottlenecks on resource-constrained heterogeneous devices, resulting in FedMPQ outperforming fixed-precision quantization baselines with minor computational overhead.
While federated learning (FL) systems often utilize quantization to battle communication and computational bottlenecks, they have heretofore been limited to deploying fixed-precision quantization schemes. Meanwhile, the concept of mixed-precision quantization (MPQ), where different layers of a deep learning model are assigned varying bit-width, remains unexplored in the FL settings. We present a novel FL algorithm, FedMPQ, which introduces mixed-precision quantization to resource-heterogeneous FL systems. Specifically, local models, quantized so as to satisfy bit-width constraint, are trained by optimizing an objective function that includes a regularization term which promotes reduction of precision in some of the layers without significant performance degradation. The server collects local model updates, de-quantizes them into full-precision models, and then aggregates them into a global model. To initialize the next round of local training, the server relies on the information learned in the previous training round to customize bit-width assignments of the models delivered to different clients. In extensive benchmarking experiments on several model architectures and different datasets in both iid and non-iid settings, FedMPQ outperformed the baseline FL schemes that utilize fixed-precision quantization while incurring only a minor computational overhead on the participating devices.