Pith. sign in

REVIEW 1 cited by

Voting-based Approaches For Differentially Private 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

arxiv 2010.04851 v2 pith:7CWBZUMJ submitted 2020-10-09 cs.LG cs.CR

classification cs.LGcs.CR
keywords dpfllearningapproachesaveragingcommunicationdependencedifferentiallydimension
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Differentially Private Federated Learning (DPFL) is an emerging field with many applications. Gradient averaging based DPFL methods require costly communication rounds and hardly work with large-capacity models, due to the explicit dimension dependence in its added noise. In this work, inspired by knowledge transfer non-federated privacy learning from Papernot et al.(2017; 2018), we design two new DPFL schemes, by voting among the data labels returned from each local model, instead of averaging the gradients, which avoids the dimension dependence and significantly reduces the communication cost. Theoretically, by applying secure multi-party computation, we could exponentially amplify the (data-dependent) privacy guarantees when the margin of the voting scores are large. Extensive experiments show that our approaches significantly improve the privacy-utility trade-off over the state-of-the-arts in DPFL.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Near-real-time design of experiments for seismic monitoring of volcanoes

    physics.geo-ph 2024-11 conditional novelty 5.0 of 10

    The authors present a code package and practical guide for Bayesian experimental design of volcano seismic networks, jointly optimizing travel-time, amplitude, and array-based source location.

Pith tools