AI Paper Atlas

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

Federated Heavy Hitter Recovery under Linear Sketching

Adria Gascon, Peter Kairouz, Ziteng Sun, Ananda Theertha Suresh

ICML 2023 · Federated learning and privacy › Communication-efficient FL · approach: Decentralized peer-to-peer training · 0 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
Use locally subsampled IBLTs instead of Count-sketchFederated heavy hitter recovery · Figure 1 setting (R = 30, τ = 50, M = 10000)communication at F1 score 0.8: 10x improvement in communicationImproved
Use local subsampling with IBLT rather than IBLT without subsampling (ablation)IBLT-based heavy hitter recovery · Figure 1 setting (R = 30, τ = 50, M = 10000)F1 scoreImproved
Adaptively tune the subsampling threshold across rounds (ablation)Subsampled IBLT · Figure 3 setting (τ = 200, M = 10000, C = 5000)F1 scoreNo clear effect
Use Count-sketch rather than the IBLT-based methods as the number of rounds increasesFederated heavy hitter recovery · Figure 2 setting (τ = 200, M = 10000, C = 10000)F1 scoreHurt

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