Federated Visual Classification with Real-World Data Distribution
This work addresses challenges in federated learning for visual classification, providing datasets and methods to enhance performance in edge learning scenarios, though it is incremental as it builds on existing federated learning frameworks.
The paper tackled the problem of training visual models in federated learning with non-IID and imbalanced real-world data distributions, introducing two new large-scale datasets and two algorithms (FedVC, FedIR) that improved accuracy and stability in training.
Federated Learning enables visual models to be trained on-device, bringing advantages for user privacy (data need never leave the device), but challenges in terms of data diversity and quality. Whilst typical models in the datacenter are trained using data that are independent and identically distributed (IID), data at source are typically far from IID. Furthermore, differing quantities of data are typically available at each device (imbalance). In this work, we characterize the effect these real-world data distributions have on distributed learning, using as a benchmark the standard Federated Averaging (FedAvg) algorithm. To do so, we introduce two new large-scale datasets for species and landmark classification, with realistic per-user data splits that simulate real-world edge learning scenarios. We also develop two new algorithms (FedVC, FedIR) that intelligently resample and reweight over the client pool, bringing large improvements in accuracy and stability in training. The datasets are made available online.