mlsanityData to 14 Oct 2026

Data-Free Contribution Estimation in Federated Learning using Gradient von Neumann Entropy

arXiv 2604.22562 ↗First posted 24 Apr 2026cs.LG cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 23 references that are in the map. First posted on arXiv 24 Apr 2026.

Builds on

20 of 23 references.

References · 20

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019Advances and Open Problems in Federated Learningcited by 3,046
  3. 2020Adaptive Federated Optimizationcited by 1,046
  4. 2018LEAF: A Benchmark for Federated Settingscited by 792
  5. 2020Prevalence of Neural Collapse during the terminal phase of deep learning trainingcited by 719
  6. 2019Fantastic Generalization Measures and Where to Find Themcited by 513
  7. 2021A Geometric Analysis of Neural Collapse with Unconstrained Featurescited by 227
  8. 2018Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learningcited by 215
  9. 2022FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settingscited by 125
  10. 2020Predicting trends in the quality of state-of-the-art neural networks without access to training or testing datacited by 115
  11. 2020Collaborative Fairness in Federated Learningcited by 95
  12. 2023Fair Federated Medical Image Segmentation via Client Contribution Estimationcited by 52
8 more
  1. 2022Evaluating natural language processing models with generalization metrics that do not need access to any training or testing datacited by 19
  2. 2023Data Valuation and Detections in Federated Learningcited by 17
  3. 2024Redefining Contributions: Shapley-Driven Federated Learningcited by 17
  4. 2024Guiding Neural Collapse: Optimising Towards the Nearest Simplex Equiangular Tight Framecited by 14
  5. 2025Aequa: Fair Model Rewards in Collaborative Learning via Slimmable Networkscited by 6
  6. 2025CYCle: Choosing Your Collaborators Wisely to Enhance Collaborative Fairness in Decentralized Learningcited by 4
  7. 2024A New Perspective to Boost Performance Fairness for Medical Federated Learningcited by 2
  8. 2025FedPCA: Noise-Robust Fair Federated Learning via Performance-Capacity Analysiscited by 2

Built on by

Not cited yet.