Scatterbrained: A flexible and expandable pattern for decentralized machine learning
This addresses a bottleneck in federated learning for domains like medicine or bandwidth-constrained environments, though it appears incremental.
The paper tackles the central server dependency in federated learning by proposing a flexible framework for decentralization, offering an open-source PyTorch-compatible implementation.
Federated machine learning is a technique for training a model across multiple devices without exchanging data between them. Because data remains local to each compute node, federated learning is well-suited for use-cases in fields where data is carefully controlled, such as medicine, or in domains with bandwidth constraints. One weakness of this approach is that most federated learning tools rely upon a central server to perform workload delegation and to produce a single shared model. Here, we suggest a flexible framework for decentralizing the federated learning pattern, and provide an open-source, reference implementation compatible with PyTorch.