Client Adaptation improves Federated Learning with Simulated Non-IID Clients
This addresses the challenge of data heterogeneity in federated learning, which is common in real-world applications, though it appears incremental as it builds on existing methods with a specific adaptation technique.
The paper tackled the problem of learning robust models in federated learning with non-IID data across clients by simulating heterogeneous clients and using client-specific conditioning, resulting in improved model performance on balanced and imbalanced datasets from audio and image domains.
We present a federated learning approach for learning a client adaptable, robust model when data is non-identically and non-independently distributed (non-IID) across clients. By simulating heterogeneous clients, we show that adding learned client-specific conditioning improves model performance, and the approach is shown to work on balanced and imbalanced data set from both audio and image domains. The client adaptation is implemented by a conditional gated activation unit and is particularly beneficial when there are large differences between the data distribution for each client, a common scenario in federated learning.