AI Paper Atlas

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

Personalized Federated Learning towards Communication Efficiency, Robustness and Fairness

Shiyun Lin, Yuze Han, Xiang Li, Zhihua Zhang

NeurIPS 2022 · Federated learning and privacy › Communication-efficient FL · approach: Communication-efficient heterogeneous FL · 3 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 lp-proj instead of FedAvg under a fixed byte budgetFedAvg · Synthetic(0,0)test accuracy: 0.625 -> 0.885Improved
use lp-proj instead of FedAvg under a fixed byte budgetFedAvg · EMNISTtest accuracy: 0.906Improved
use lp-proj-1 instead of FedAvg to reach target accuracyFedAvg · Synthetic(0,0)bytes used: 597800 -> 4620Improved
use lp-proj-1 instead of FedAvg to reach target accuracyFedAvg · EMNISTbytes used: 445851400 -> 174720Improved
use lp-proj instead of gradient compression (QSGD)QSGD · Synthetic(0,0)test accuracy: 0.115 -> 0.885Improved
use lp-proj instead of SketchSketch · Synthetic(0,0)test accuracy: 0.456 -> 0.885Improved
lp-proj-2 (L2) instead of lp-proj-1 (L1) regulariserlp-proj · EMNISTbytes used: 174720 -> 196560Hurt
lp-proj-2 (L2) instead of lp-proj-1 (L1) regulariserlp-proj · Synthetic(0,0)test accuracy: 0.885 -> 0.888No clear effect
lp-proj-1 versus RSA on fairnessRSA · CIFARtest accuracy: 77.68% -> 79.22%Improved
lp-proj-2 versus Ditto on fairnessDitto · EMNISTtest accuracy: 90.89% -> 90.70%No clear effect
increase fraction of malicious clients under weak attacks (same-value, Gaussian)lp-proj · EMNISTtest accuracyNo clear effect
increase fraction of malicious clients under strong attacks (sign-flipping, data poisoning)lp-proj · CIFARtest accuracyHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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