AI Paper Atlas

Research map / Federated learning and privacy / Communication-efficient FL

Distributed Distillation for On-Device Learning

Ilai Bistritz, Ariana Mann, Nicholas Bambos

NeurIPS 2020 · Federated learning and privacy › Communication-efficient FL · approach: Decentralized peer-to-peer training · 29 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add 90x communication reduction (tau=10, 8-bit quantization, Top-K) on top of D-DistillationD-Distillation · MNIST / CIFAR10test accuracy: 46x -> 9,370x total communication reductionNo clear effect
reduce network batch size b communicated per round (ablation)D-Distillation · MNIST / CIFAR10test accuracyNo clear effect
allow heterogeneous local models across devices vs D-SGD on separate subsetsD-Distillation · CIFAR10, 8 devicestest accuracyImproved
increase number of devices (more private data)D-Distillation · MNISTtest accuracyImproved
D-Distillation vs Silo-SGD (no communication)devices' classifiers · MNIST 16 devicestest accuracyImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy