Research map / Federated learning and privacy / Personalized and heterogeneous FL
Feature-Aware One-Shot Federated Learning via Hierarchical Token Sequences
Shudong Liu, Hanwen Zhang, Xiuling Wang, Yuesheng Zhu, Guibo Luo
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 hierarchical scale encoding (HSE) (ablation) | FALCON · Average over all settings | accuracy (%): 82.32 -> 85.92 | Improved |
| add hierarchical scale encoding (HSE) (ablation) | FALCON · Pneumonia (mean over alpha) | accuracy (%): 82.12 -> 86.85 | Improved |
| add hierarchical scale encoding (HSE) (ablation) | FALCON · PACS | accuracy (%): 96.16 -> 96.42 | No clear effect |
| add knowledge distillation (ablation) | FALCON · Average over all settings | accuracy (%): 82.82 -> 85.92 | Improved |
| add knowledge distillation (ablation) | FALCON · OfficeHome | accuracy (%): 86.87 -> 89.68 | Improved |
| use M-AR generator instead of vanilla AR (ablation) | FALCON · Pneumonia (mean over alpha) | accuracy (%): 72.76 -> 86.85 | Improved |
| use M-AR generator instead of non-autoregressive generator (ablation) | FALCON · PMRAM (mean over alpha) | accuracy (%): 78.67 -> 84.70 | Improved |
| use M-AR generator instead of AR for synthetic token fidelity (ablation) | FALCON · Tuberculosis | MMD: 0.003868 -> 0.003227 | Improved |
| use FALCON vs best OSFL baseline on Tuberculosis | FedCGS · Tuberculosis | accuracy (%): 53.50 -> 87.20 | Improved |
| use FALCON vs FedCGS on Tiny-ImageNet alpha=0.1 | FedCGS · Tiny-ImageNet (alpha=0.1) | accuracy (%): 81.53 -> 79.93 | Hurt |
| upload synthetic token sequences rather than real ones for privacy | FALCON · OfficeHome reconstruction attack | PSNR: 27.18 -> 13.30 | Improved |
Closest papers by meaning
- FedBiP: Heterogeneous One-Shot Federated Learning with Personalized Latent Diffusion Models (CVPR 2025 · similarity 0.88)
- One-shot Federated Learning via Synthetic Distiller-Distillate Communication (NeurIPS 2024 · similarity 0.87)
- FedVCK: Non-IID Robust and Communication-Efficient Federated Learning via Valuable Condensed Knowledge for Medical Image Analysis (AAAI 2025 · similarity 0.86)
- MH-pFLID: Model Heterogeneous personalized Federated Learning via Injection and Distillation for Medical Data Analysis (ICML 2024 · similarity 0.86)
- Personalized Federated Learning via Feature Distribution Adaptation (NeurIPS 2024 · similarity 0.85)
- One-Shot Heterogeneous Federated Learning with Local Model-Guided Diffusion Models (ICML 2025 · similarity 0.85)
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.
