FAST: Enhancing Federated Learning Through Adaptive Data Sampling and Local Training

The emerging paradigm of federated learning (FL) strives to enable devices to cooperatively train models without exposing their raw data. In most cases, the data across devices are non-independently and identically distributed in FL. Thus, the local models trained over different data distributions will inevitably deviate from the global optima, which induces optimization inconsistency and even hurts global convergence. Moreover, the resource-constrained devices with heterogeneous training capacities (e.g., computing and communication) further slow down the convergence rate. To this end, we introduce an
F
L framework with
a
daptive data
s
ampling and local
t
raining, namely FAST. Specifically, even without devices’ private data distributions, FAST enables each device to sample different rates of data points from each of its local classes to rebuild a dataset for training, thus adjusting the convergence direction of the aggregated global model to be closer to the global optima. The theoretical analysis shows that the convergence bound depends on the sampling rates as well as the number of local iterations executed on the sampled data. To achieve resource-effective and convergence-guaranteed FL, we then design an online learning algorithm that jointly optimizes the data sampling and local training strategies so as to encourage the decrease of global loss under the given time budget. Extensive experiments on physical and simulated environments show that, FAST improves the model accuracy by about 1.55%-6.78% given the same time budget, and accelerates training by about 1.39-5.89× with the same target accuracy, compared with the baselines.