Is Shapley Value fair? Improving Client Selection for Mavericks in Federated Learning
Shapley Value is commonly adopted to measure and incentivize client participation in federated learning. In this paper, we show -- theoretically and through simulations -- that Shapley Value underestimates the contribution of a common type of client: the Maverick. Mavericks are clients that differ both in data distribution and data quantity and can be the sole owners of certain types of data. Selecting the right clients at the right moment is important for federated learning to reduce convergence times and improve accuracy. We propose FedEMD, an adaptive client selection strategy based on the Wasserstein distance between the local and global data distributions. As FedEMD adapts the selection probability such that Mavericks are preferably selected when the model benefits from improvement on rare classes, it consistently ensures the fast convergence in the presence of different types of Mavericks. Compared to existing strategies, including Shapley Value-based ones, FedEMD improves the convergence of neural network classifiers by at least 26.9% for FedAvg aggregation compared with the state of the art.
Code (0)
등록된 구현이 없습니다.
Tasks
Federated LearningSimilar Papers 제목 키워드 기반
Maverick-Aware Shapley Valuation for Client Selection in Federated Learning
Federated Learning (FL) allows clients to train a model collaboratively without sharing their private data. One key challenge in practical FL systems is data heterogeneity, particularly in handling clients with rare data…
Federated LearningOwen Sampling Accelerates Contribution Estimation in Federated Learning
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 …
Federated LearningDon't Forget What I did?: Assessing Client Contributions in Federated Learning
Federated Learning (FL) is a collaborative machine learning (ML) approach, where multiple clients participate in training an ML model without exposing the private data. Fair and accurate assessment of client contribution…
Data PoisoningFairnessFederated LearningSchedulingMeritocratic Fairness via $K$-Shapley Values in Budgeted Combinatorial Bandits with Full-Bandit Feedback
We study meritocratic fairness in budgeted combinatorial multi-armed bandits with full-bandit feedback, where a learner selects at most $K$ arms per time step and observes only the noisy aggregate reward of the selected …
Multi-Armed BanditsFederated LearningFairness-Aware Federated Learning with Trajectory Shapley Value
Federated learning is an emerging distributed paradigm that addresses the challenges posed by heterogeneous, privacy-sensitive data. It enables multiple clients to train a model collaboratively by aggregating their local…
Federated Learning