REVIEW 3 cited by
Slimmable Quantum Federated Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Quantum federated learning (QFL) has recently received increasing attention, where quantum neural networks (QNNs) are integrated into federated learning (FL). In contrast to the existing static QFL methods, we propose slimmable QFL (SlimQFL) in this article, which is a dynamic QFL framework that can cope with time-varying communication channels and computing energy limitations. This is made viable by leveraging the unique nature of a QNN where its angle parameters and pole parameters can be separately trained and dynamically exploited. Simulation results corroborate that SlimQFL achieves higher classification accuracy than Vanilla QFL, particularly under poor channel conditions on average.
Forward citations
Cited by 3 Pith papers
-
Observable Geometry for Effective Quantum Circuits
A stabilizer-overlap score built from a Hamiltonian's eigenspaces predicts which variational circuit generators are redundant and should be removed.
-
New Insights on Unfolding and Fine-tuning Quantum Federated Learning
Deep unfolding with client-learned hyperparameters is claimed to improve quantum federated learning accuracy from roughly 55% to 90%, but the supporting proof and baseline data are not established.
-
Universal Fluctuations in the Tail Probability for d=2 Random Walks in Space-Time Random Environments
The reported d=2 random-walk universality result is unsupported: the full text is a quantum federated learning survey that never mentions random walks, tail probabilities, or lambda_ext.
Discussion (0). Sign in to comment.