用改进采样方法更快更准估算联邦学习中各客户端贡献
Owen Sampling Accelerates Contribution Estimation in Federated Learning
- 采用Owen采样技术高效逼近公平的贡献度评分
- 相同通信开销下比当前最优方法提升23%最终准确率
- 自适应选人策略兼顾高价值与稀有数据，适合真实非独立同分布场景
联邦学习在不暴露原始数据的前提下，从多个客户端聚合信息以训练共享全局模型。准确估计每个客户端的贡献至关重要，不仅关乎公平激励，也影响高效选择优质客户端以加速模型收敛。尽管Shapley值是理论上的理想选择，但其精确计算随客户端数量呈指数增长，难以应用于大规模联邦系统。本文提出FedOwen框架，利用Owen采样在与现有方法相同的评估预算下实现对Shapley值的高效近似，同时保持较低误差。此外，该框架引入自适应客户端选择策略，在利用高价值客户端与探索低频但关键样本之间取得平衡，有效降低偏差并挖掘罕见但有价值的数据。在非独立同分布（non-IID）基准测试中，相同估值成本下，FedOwen相比当前最优基线在相同通信轮次内实现了最高达23%的最终准确率提升。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。