AI Paper Atlas

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

HiLoRA: Hierarchical Low-Rank Adaptation for Personalized Federated Learning

Zihao Peng, Nan Zou, Jiandian Zeng, Guo Li, Ke Chen, Boyuan Li, Tian Wang

CVPR 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated prompt and LoRA tuning · 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
add cluster tier on top of root LoRA (ablation)HiLoRA · CIFAR-100mean accuracy: 0.663 -> 0.889Improved
add leaf tier on top of root+cluster (ablation)HiLoRA · CIFAR-100mean accuracy: 0.889 -> 0.934Improved
add cluster tier on top of root LoRA (ablation)HiLoRA · DomainNetmean accuracy: 0.815 -> 0.864Improved
add leaf tier on top of root+cluster (ablation)HiLoRA · DomainNetmean accuracy: 0.864 -> 0.877Improved
add LoRA-subspace clustering to hierarchical LoRA (ablation)HiLoRA · CIFAR-100personalized accuracy: 89.7 -> 92.8Improved
add cross-tier orthogonality loss (ablation)HiLoRA · CIFAR-100personalized accuracy: 92.8 -> 94.1Improved
add LoRA-subspace clustering (ablation)HiLoRA · DomainNetunseen-client accuracy: 84.2 -> 85.1Improved
add orthogonality loss (ablation)HiLoRA · DomainNetunseen-client accuracy: 85.1 -> 86.1Improved
leaf-level adaptation of 5 epochs on unseen clients (ablation)HiLoRA · CIFAR-100 unseen clientsaccuracy: 0.811 -> 0.859Improved
leaf-level adaptation of 5 epochs on unseen clients (ablation)HiLoRA · DomainNet unseen clientsaccuracy: 0.849 -> 0.861Improved
use hierarchical three-tier LoRA instead of dual-adapter designsfederated ViT LoRA · CIFAR-100 SC-Dir(3)mean accuracy: 0.912 -> 0.934Improved

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