Matrix von Neumann entropy of final-layer gradients acts as a data-free proxy for client contribution in federated learning, showing high correlation with standalone accuracy on non-IID benchmarks.
Guiding neural collapse: Optimising towards the nearest simplex equiangular tight frame.Advances in Neural Information Processing Systems, 37:35544–35573
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Data-Free Contribution Estimation in Federated Learning using Gradient von Neumann Entropy
Matrix von Neumann entropy of final-layer gradients acts as a data-free proxy for client contribution in federated learning, showing high correlation with standalone accuracy on non-IID benchmarks.