AI Paper Atlas

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

OPTION: An Online Pricing Strategy for Asynchronous Federated Learning Against Free-Riding Attacks

Bangqi Pan, Jianfeng Lu, Shuqin Cao, Xiao Zhang, Gang Li, Guanghui Wen

AAAI 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Non-IID federated learning · 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 OPTION online pricing instead of FRADasynchronous FL · CIFAR-10global test accuracy: 78.35 -> 85.25Improved
use OPTION instead of ANALYTICSasynchronous FL · CIFAR-10global test accuracy: 72.21 -> 85.25Improved
use OPTION instead of OIMAFasynchronous FL · CIFAR-10average client accuracy: 73.34 -> 81.65Improved
use OPTION instead of FRADasynchronous FL · CINIC-10global test accuracy: 24.49 -> 40.95Improved
use OPTION instead of OIMAFasynchronous FL · MNISTglobal test accuracy: 92.42 -> 93.76Improved
replace linear convergence model with non-convex objective (NCX-OPTION) (ablation)OPTION · CINIC-10global test accuracy: 40.95 -> 42.47Improved
replace linear convergence model with non-convex objective (NCX-OPTION) (ablation)OPTION · CIFAR-10global test accuracy: 85.25 -> 82.33Hurt
replace linear convergence model with non-convex objective (NCX-OPTION) (ablation)OPTION · MNISTaverage client accuracy: 93.41 -> 91.43Hurt
use OPTION closed-form pricing instead of FRAD/OIMAF pricingpricing computation · cumulative calculation timecomputation time reduction: 75.42% and 85.78% reductionImproved
use OPTION online pricing instead of next best online pricingasynchronous FL · offline devicesvalid client updates: 23.97%Improved
lower penalty coefficient mu (0.01 to 0.001) (ablation)utility queue length · UTYLengthqueue lengthImproved

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