AI Paper Atlas

Research map / Federated learning and privacy / Personalized and heterogeneous FL

DReS-FL: Dropout-Resilient Secure Federated Learning for Non-IID Clients via Secret Data Sharing

Jiawei Shao, Yuchang Sun, Songze Li, Jun Zhang

NeurIPS 2022 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated learning with pretrained models · 19 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
replace FedAvg-style aggregation with DReS-FLnon-IID FL with dropout · MNISTtest accuracy (%): 96.17 -> 97.38Improved
replace FedAvg-style aggregation with DReS-FLnon-IID FL with dropout · Fashion-MNISTtest accuracy (%): 81.20 -> 86.60Improved
replace FedAvg-style aggregation with DReS-FLnon-IID FL with dropout · EMNISTtest accuracy (%): 71.50 -> 78.04Improved
replace FedAvg-style aggregation with DReS-FLnon-IID FL with dropout · CIFAR-10test accuracy (%): 89.54 -> 90.31Improved
replace FedAvg-style aggregation with DReS-FLnon-IID FL with dropout · CIFAR-100test accuracy (%): 67.71 -> 69.15Improved
replace FedAvg-style aggregation with DReS-FLnon-IID FL with dropout · SVHNtest accuracy (%): 83.82 -> 86.04Improved
weight client updates by known participation probability (FedAvg-IS)FedAvg · Fashion-MNISTtest accuracy (%): 81.20 -> 85.94Improved
use SCAFFOLD control variates under non-IID and dropoutFedAvg · CIFAR-100test accuracy (%): 67.71 -> 29.97Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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