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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add cluster tier on top of root LoRA (ablation) | HiLoRA · CIFAR-100 | mean accuracy: 0.663 -> 0.889 | Improved |
| add leaf tier on top of root+cluster (ablation) | HiLoRA · CIFAR-100 | mean accuracy: 0.889 -> 0.934 | Improved |
| add cluster tier on top of root LoRA (ablation) | HiLoRA · DomainNet | mean accuracy: 0.815 -> 0.864 | Improved |
| add leaf tier on top of root+cluster (ablation) | HiLoRA · DomainNet | mean accuracy: 0.864 -> 0.877 | Improved |
| add LoRA-subspace clustering to hierarchical LoRA (ablation) | HiLoRA · CIFAR-100 | personalized accuracy: 89.7 -> 92.8 | Improved |
| add cross-tier orthogonality loss (ablation) | HiLoRA · CIFAR-100 | personalized accuracy: 92.8 -> 94.1 | Improved |
| add LoRA-subspace clustering (ablation) | HiLoRA · DomainNet | unseen-client accuracy: 84.2 -> 85.1 | Improved |
| add orthogonality loss (ablation) | HiLoRA · DomainNet | unseen-client accuracy: 85.1 -> 86.1 | Improved |
| leaf-level adaptation of 5 epochs on unseen clients (ablation) | HiLoRA · CIFAR-100 unseen clients | accuracy: 0.811 -> 0.859 | Improved |
| leaf-level adaptation of 5 epochs on unseen clients (ablation) | HiLoRA · DomainNet unseen clients | accuracy: 0.849 -> 0.861 | Improved |
| use hierarchical three-tier LoRA instead of dual-adapter designs | federated ViT LoRA · CIFAR-100 SC-Dir(3) | mean accuracy: 0.912 -> 0.934 | Improved |
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.
- FedALT — FedALT: Federated Fine-Tuning Through Adaptive Local Training with Rest-of-World LoRA (AAAI 2026) · better on 3 of 3 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
- Selective Aggregation for Low-Rank Adaptation in Federated Learning (ICLR 2025 · similarity 0.89)
- Ravan: Multi-Head Low-Rank Adaptation for Federated Fine-Tuning (NeurIPS 2025 · similarity 0.88)
- Adaptive LoRA Experts Allocation and Selection for Federated Fine-Tuning (NeurIPS 2025 · similarity 0.87)
- F^3OCUS - Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics (CVPR 2025 · similarity 0.87)
- Unlocking the Potential of Prompt-Tuning in Bridging Generalized and Personalized Federated Learning (CVPR 2024 · similarity 0.87)
- FedSVD: Adaptive Orthogonalization for Private Federated Learning with LoRA (NeurIPS 2025 · similarity 0.87)
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.
