FedCD: Improving Performance in non-IID Federated Learning
This addresses performance degradation in federated learning for edge devices with heterogeneous data, though it appears incremental as it builds on existing methods like FedAvg.
The paper tackles the problem of non-IID data distribution in federated learning by proposing FedCD, which clones and deletes models to group devices with similar data, resulting in higher accuracy and faster convergence on CIFAR-10 compared to FedAvg with minimal overhead.
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.