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
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 anchor-driven feature alignment constraint (lambda > 0) (ablation) | FedARA (heterogeneous models) · CIFAR100 | test accuracy | Improved |
| increase anchor constraint strength lambda up to a moderate value (ablation) | FedARA (heterogeneous models) · CIFAR100 | convergence speed and accuracy | Improved |
| set anchor constraint strength too large (lambda = 20) (ablation) | FedARA (heterogeneous models) · CIFAR100 | convergence and accuracy | Hurt |
| use low-rank extractor (rank 0.5) instead of full-rank (ablation) | FedARA (homogeneous CNN) · CIFAR100 average | accuracy (%): 60.49 -> 59.45 | Mixed |
| use low-rank extractor (rank 0.5) instead of full-rank (ablation) | FedARA (homogeneous CNN) · CIFAR10 average | accuracy (%): 88.21 -> 87.93 | No clear effect |
| use FedARA instead of FedAS with homogeneous models | PFL · CIFAR100 average | accuracy (%): 55.36 -> 60.49 | Improved |
| use FedARA with heterogeneous models instead of best baseline | PFL · Tiny-ImageNet Practical alpha=0.1 | accuracy (%): 29.19 -> 38.70 | Improved |
| reduce data heterogeneity (larger alpha or more classes per client) | all PFL methods incl. FedARA · CIFAR100 | accuracy: 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 setting | FedARA · communication cost at target accuracy | communication cost | Hurt |
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.
- FedAS — FedAS: Bridging Inconsistency in Personalized Federated Learning (CVPR 2024) · better on 3 of 3 shared results
- FedALA — FedALA: Adaptive Local Aggregation for Personalized Federated Learning (AAAI 2023) · better on 2 of 2 shared results
- FedBABU — FedBABU: Toward Enhanced Representation for Federated Image Classification (ICLR 2022) · better on 1 of 1 shared result
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
- FedSA: A Unified Representation Learning via Semantic Anchors for Prototype-based Federated Learning (AAAI 2025 · similarity 0.89)
- Flexible Sharpness-Aware Personalized Federated Learning (AAAI 2025 · similarity 0.89)
- FedAS: Bridging Inconsistency in Personalized Federated Learning (CVPR 2024 · similarity 0.88)
- Federated Model Heterogeneous Matryoshka Representation Learning (NeurIPS 2024 · similarity 0.87)
- Causally Motivated Personalized Federated Invariant Learning with Shortcut-Averse Information-Theoretic Regularization (ICML 2024 · similarity 0.87)
- Adaptive Latent-Space Constraints in Personalized Federated Learning (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.
