paper-with-me

Papers

Owen Sampling Accelerates Contribution Estimation in Federated Learning

2025-08-28 · Hossein KhademSohi, Hadi Hemmati, Jiayu Zhou, Steve Drew arxiv

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.

📄 PDF Abstract BibTeX arXiv:2508.21261

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

A note on the Diversity Owen values

2025-05-30 · Songtao He, Erfang Shan, Xinyu Sun

B\'eal et al. (Int J Game Theory 54, 2025) introduce the Diversity Owen value for TU-games with diversity constraints, and provide axiomatic characterizations using the axioms of fairness and balanced contributions. Howe…

DiversityFairness

Highly mutually dependent unions and new axiomatizations of the Owen value

2025-04-19 · Songtao He, Erfang Shan, Hanqi Zhou

The Owen value is an well-known allocation rule for cooperative games with coalition structure.In this paper, we introduce the concept of highly mutually dependent unions. Two unions in a cooperative game with coalition …

DPVS-Shapley:Faster and Universal Contribution Evaluation Component in Federated Learning

2024-10-19 · Ketin Yin, Zonghao Guo, Zhenghan Qin

In the current era of artificial intelligence, federated learning has emerged as a novel approach to addressing data privacy concerns inherent in centralized learning paradigms. This decentralized learning model not only…

Contribution AssessmentFederated Learning

Fairness-Aware Federated Learning with Trajectory Shapley Value

2026-05-28 · Daniel Kuznetsov, Ziqi Wang arxiv

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

Efficient SAGE Estimation via Causal Structure Learning

2023-04-06 · Christoph Luther, Gunnar König, Moritz Grosse-Wentrup

The Shapley Additive Global Importance (SAGE) value is a theoretically appealing interpretability method that fairly attributes global importance to a model's features. However, its exact calculation requires the computa…