Federated Meta-Learning with Fast Convergence and Efficient Communication
This work addresses efficiency and privacy issues in federated learning for mobile device networks, offering a novel approach with significant performance gains.
The paper tackles the challenges of training machine learning models across distributed mobile devices by proposing FedMeta, a federated meta-learning framework that shares a parameterized algorithm instead of a global model, resulting in a 2.82-4.33 times reduction in communication cost, faster convergence, and a 3.23%-14.84% increase in accuracy compared to Federated Averaging.
Statistical and systematic challenges in collaboratively training machine learning models across distributed networks of mobile devices have been the bottlenecks in the real-world application of federated learning. In this work, we show that meta-learning is a natural choice to handle these issues, and propose a federated meta-learning framework FedMeta, where a parameterized algorithm (or meta-learner) is shared, instead of a global model in previous approaches. We conduct an extensive empirical evaluation on LEAF datasets and a real-world production dataset, and demonstrate that FedMeta achieves a reduction in required communication cost by 2.82-4.33 times with faster convergence, and an increase in accuracy by 3.23%-14.84% as compared to Federated Averaging (FedAvg) which is a leading optimization algorithm in federated learning. Moreover, FedMeta preserves user privacy since only the parameterized algorithm is transmitted between mobile devices and central servers, and no raw data is collected onto the servers.