ISFL: Federated Learning for Non-i.i.d. Data with Local Importance Sampling
This addresses a key bottleneck in federated learning for distributed systems with non-i.i.d. data, offering a novel local sampling approach that is incremental but with theoretical guarantees.
The paper tackles the problem of poor performance and convergence in federated learning due to non-i.i.d. data by proposing ISFL, which uses local importance sampling, and shows experimental improvements on CIFAR-10 in performance, sampling efficiency, and explainability.
As a promising learning paradigm integrating computation and communication, federated learning (FL) proceeds the local training and the periodic sharing from distributed clients. Due to the non-i.i.d. data distribution on clients, FL model suffers from the gradient diversity, poor performance, bad convergence, etc. In this work, we aim to tackle this key issue by adopting importance sampling (IS) for local training. We propose importance sampling federated learning (ISFL), an explicit framework with theoretical guarantees. Firstly, we derive the convergence theorem of ISFL to involve the effects of local importance sampling. Then, we formulate the problem of selecting optimal IS weights and obtain the theoretical solutions. We also employ a water-filling method to calculate the IS weights and develop the ISFL algorithms. The experimental results on CIFAR-10 fit the proposed theorems well and verify that ISFL reaps better performance, sampling efficiency, as well as explainability on non-i.i.d. data. To the best of our knowledge, ISFL is the first non-i.i.d. FL solution from the local sampling aspect which exhibits theoretical compatibility with neural network models. Furthermore, as a local sampling approach, ISFL can be easily migrated into other emerging FL frameworks.