FedCD: Improving Performance in non-IID Federated Learning
arXiv:2006.09637
Abstract
Federated learning has been widely applied to enable decentralized devices, which each have their own local data, to learn a shared model. However, learning from real-world data can be challenging, as it is rarely identically and independently distributed (IID) across edge devices (a key assumption for current high-performing and low-bandwidth algorithms). We present a novel approach, FedCD, which clones and deletes models to dynamically group devices with similar data. Experiments on the CIFAR-10 dataset show that FedCD achieves higher accuracy and faster convergence compared to a FedAvg baseline on non-IID data while incurring minimal computation, communication, and storage overheads.
Accepted for Oral Presentation at ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2020) International workshop on Artificial Intelligence of Things