Lightweight and Robust Federated Data Valuation
This work addresses scalability and robustness challenges in federated learning for real-world deployments, offering a practical alternative to existing methods, though it is incremental as it builds on prior influence estimation techniques.
The paper tackled the problem of high computational overhead in federated learning (FL) contribution evaluation methods by proposing FedIF, a framework that uses trajectory-based influence estimation to compute client contributions efficiently, achieving robustness comparable to Shapley-value-based methods while reducing aggregation overhead by up to 450x in experiments on CIFAR-10 and Fashion-MNIST.
Federated learning (FL) faces persistent robustness challenges due to non-IID data distributions and adversarial client behavior. A promising mitigation strategy is contribution evaluation, which enables adaptive aggregation by quantifying each client's utility to the global model. However, state-of-the-art Shapley-value-based approaches incur high computational overhead due to repeated model reweighting and inference, which limits their scalability. We propose FedIF, a novel FL aggregation framework that leverages trajectory-based influence estimation to efficiently compute client contributions. FedIF adapts decentralized FL by introducing normalized and smoothed influence scores computed from lightweight gradient operations on client updates and a public validation set. Theoretical analysis demonstrates that FedIF yields a tighter bound on one-step global loss change under noisy conditions. Extensive experiments on CIFAR-10 and Fashion-MNIST show that FedIF achieves robustness comparable to or exceeding SV-based methods in the presence of label noise, gradient noise, and adversarial samples, while reducing aggregation overhead by up to 450x. Ablation studies confirm the effectiveness of FedIF's design choices, including local weight normalization and influence smoothing. Our results establish FedIF as a practical, theoretically grounded, and scalable alternative to Shapley-value-based approaches for efficient and robust FL in real-world deployments.