Leveraging Leash Tasks to Accelerate Convergence in Federated Learning on Non-IID Data

The Dog Walking Theory formulates federated learning as a dog walking process, where the server acts as the dog walker and the clients as the dogs. The key missing element in existing federated learning algorithms is the "leash" that guides the convergence of the clients. The proposed FedWalk algorithm leverages an easy-to-converge leash task defined on a public dataset to boost the convergence of federated learning, especially on non-IID data.