Owen Sampling Accelerates Contribution Estimation in Federated Learning
This addresses the scalability issue in contribution estimation for Federated Learning, enabling faster convergence in large federations, though it is incremental as it builds on existing Shapley value approximations.
The paper tackled the problem of efficiently estimating client contributions in Federated Learning to improve model convergence, proposing FedOwen which uses Owen sampling and adaptive client selection to achieve up to 23% higher final accuracy under the same communication rounds compared to state-of-the-art methods.
Federated Learning (FL) aggregates information from multiple clients to train a shared global model without exposing raw data. Accurately estimating each client's contribution is essential not just for fair rewards, but for selecting the most useful clients so the global model converges faster. The Shapley value is a principled choice, yet exact computation scales exponentially with the number of clients, making it infeasible for large federations. We propose FedOwen, an efficient framework that uses Owen sampling to approximate Shapley values under the same total evaluation budget as existing methods while keeping the approximation error small. In addition, FedOwen uses an adaptive client selection strategy that balances exploiting high-value clients with exploring under-sampled ones, reducing bias and uncovering rare but informative data. Under a fixed valuation cost, FedOwen achieves up to 23 percent higher final accuracy within the same number of communication rounds compared to state-of-the-art baselines on non-IID benchmarks.