AI Paper Atlas

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

FedARA: Resource-adaptive Low-rank Personalized Federated Learning via Anchor-driven Representation Alignment on Heterogeneous Edge Devices

Ruonan Zhao, Zheng Wang, Debin Liu, Shijie Lv, Laurence Tianruo Yang

CVPR 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Personalization with global-local trade-off

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 anchor-driven feature alignment constraint (lambda > 0) (ablation)FedARA (heterogeneous models) · CIFAR100test accuracyImproved
increase anchor constraint strength lambda up to a moderate value (ablation)FedARA (heterogeneous models) · CIFAR100convergence speed and accuracyImproved
set anchor constraint strength too large (lambda = 20) (ablation)FedARA (heterogeneous models) · CIFAR100convergence and accuracyHurt
use low-rank extractor (rank 0.5) instead of full-rank (ablation)FedARA (homogeneous CNN) · CIFAR100 averageaccuracy (%): 60.49 -> 59.45Mixed
use low-rank extractor (rank 0.5) instead of full-rank (ablation)FedARA (homogeneous CNN) · CIFAR10 averageaccuracy (%): 88.21 -> 87.93No clear effect
use FedARA instead of FedAS with homogeneous modelsPFL · CIFAR100 averageaccuracy (%): 55.36 -> 60.49Improved
use FedARA with heterogeneous models instead of best baselinePFL · Tiny-ImageNet Practical alpha=0.1accuracy (%): 29.19 -> 38.70Improved
reduce data heterogeneity (larger alpha or more classes per client)all PFL methods incl. FedARA · CIFAR100accuracy: FedARA 54.54 -> 38.27 -> 30.41 (alpha 0.1/0.5/1.0)Hurt
compare communication cost of FedARA to FedTGP and FedKD in heterogeneous settingFedARA · communication cost at target accuracycommunication costHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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