Pith. sign in

DP-REC: Private & Communication-Efficient Federated Learning

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

Privacy and communication efficiency are important challenges in federated training of neural networks, and combining them is still an open problem. In this work, we develop a method that unifies highly compressed communication and differential privacy (DP). We introduce a compression technique based on Relative Entropy Coding (REC) to the federated setting. With a minor modification to REC, we obtain a provably differentially private learning algorithm, DP-REC, and show how to compute its privacy guarantees. Our experiments demonstrate that DP-REC drastically reduces communication costs while providing privacy guarantees comparable to the state-of-the-art.

citation-role summary

other 1

citation-polarity summary

fields

cs.IT 1

years

2025 1

verdicts

CONDITIONAL 1

roles

other 1

polarities

unclear 1

representative citing papers

Remote Channel Synthesis

cs.IT · 2025-07-21 · conditional · novelty 7.0

The paper gives a single-letter characterization of optimal rates for remote channel synthesis and proves that direct per-symbol synthesis is strictly suboptimal at low common randomness.

citing papers explorer

Showing 1 of 1 citing paper.

  • Remote Channel Synthesis cs.IT · 2025-07-21 · conditional · none · ref 24 · internal anchor

    The paper gives a single-letter characterization of optimal rates for remote channel synthesis and proves that direct per-symbol synthesis is strictly suboptimal at low common randomness.