REVIEW 2 cited by
D2P-Fed: Differentially Private Federated Learning With Efficient Communication
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
In this paper, we propose the discrete Gaussian based differentially private federated learning (D2P-Fed), a unified scheme to achieve both differential privacy (DP) and communication efficiency in federated learning (FL). In particular, compared with the only prior work taking care of both aspects, D2P-Fed provides stronger privacy guarantee, better composability and smaller communication cost. The key idea is to apply the discrete Gaussian noise to the private data transmission. We provide complete analysis of the privacy guarantee, communication cost and convergence rate of D2P-Fed. We evaluated D2P-Fed on INFIMNIST and CIFAR10. The results show that D2P-Fed outperforms the-state-of-the-art by 4.7% to 13.0% in terms of model accuracy while saving one third of the communication cost.
Forward citations
Cited by 2 Pith papers
-
Sketched Gaussian Mechanism for Private Federated Learning
A sketched Gaussian mechanism is shown to have privacy loss that shrinks as the sketch dimension grows, giving communication-efficient federated learning with stronger privacy per noise budget.
-
Quantification of the energy consumption of entanglement distribution
The paper proves that entanglement irreversibility implies a non-zero lower bound on the standard energy cost of distributing an ebit through a noisy quantum channel.
Discussion (0). Continue with ORCID to comment.