用梯度谱熵无数据评估联邦学习中客户端贡献，避免隐私泄露。
Data-Free Contribution Estimation in Federated Learning using Gradient von Neumann Entropy
- 基于最后一层更新的谱熵衡量信息多样性，无需客户端数据或标签。
- 在CIFAR-10/100、FEMNIST等数据集上，熵值与准确率相关性超0.85。
- 适用于需公平激励且无法获取验证数据的联邦学习场景。
联邦学习中的客户端贡献估计对识别重要性及实现公平奖励至关重要。现有方法常依赖服务器端验证数据或客户端自报信息，可能泄露隐私或易被操纵。本文提出一种无数据信号：基于最后一层更新的矩阵von Neumann（谱）熵，用于衡量所贡献信息的多样性。我们设计了两个实用方案：(i) SpectralFed，使用归一化熵作为聚合权重；(ii) SpectralFuse，通过秩自适应卡尔曼滤波融合熵与类别特异性对齐，提升每轮稳定性。在CIFAR-10/100及自然划分的FEMNIST和FedISIC基准上，熵衍生得分在多种非独立同分布（non-IID）场景下与独立客户端准确率保持高度一致的相关性（平均相关系数>0.85），且无需验证数据或客户端元信息。与现有无数据基线对比，谱熵展现出良好的贡献指示能力。
原文摘要 · Abstract (English)
Client contribution estimation in Federated Learning is necessary for identifying clients' importance and for providing fair rewards. Current methods often rely on server-side validation data or self-reported client information, which can compromise privacy or be susceptible to manipulation. We introduce a data-free signal based on the matrix von Neumann (spectral) entropy of the final-layer updates, which measures the diversity of the information contributed. We instantiate two practical schemes: (i) SpectralFed, which uses normalized entropy as aggregation weights, and (ii) SpectralFuse, which fuses entropy with class-specific alignment via a rank-adaptive Kalman filter for per-round stability. Across CIFAR-10/100 and the naturally partitioned FEMNIST and FedISIC benchmarks, entropy-derived scores show a consistently high correlation with standalone client accuracy under diverse non-IID regimes - without validation data or client metadata. We compare our results with data-free contribution estimation baselines and show that spectral entropy serves as a useful indicator of client contribution.
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。