Research map / Federated learning and privacy / Communication-efficient FL
Few-Round Learning for Federated Learning
Younghyun Park, Dong-Jun Han, Do-Yeon Kim, Jun Seo, Jaekyun Moon
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 global prototype-assisted learning (GPAL) to distance-based FRL (ablation) | FRL · CIFAR-100 unseen, IID | accuracy: 69.74 -> 72.93 | Improved |
| add GPAL to distance-based FRL (ablation) | FRL · CIFAR-100 unseen, non-IID | accuracy: 63.85 -> 66.87 | Improved |
| add GPAL to distance-based FRL (ablation) | FRL · FEMNIST unseen, non-IID | accuracy: 88.60 -> 92.42 | Improved |
| add GPAL to distance-based FRL (ablation) | FRL · miniImageNet unseen, IID | accuracy: 68.05 -> 69.31 | Improved |
| distance-based instead of linear classifier (ablation) | FRL · CIFAR-100 unseen, non-IID | accuracy: 52.98 -> 63.85 | Improved |
| distance-based instead of linear classifier (ablation) | FRL · CIFAR-100 unseen, IID | accuracy: 67.32 -> 69.74 | Improved |
| distance-based instead of linear classifier (ablation) | FRL · miniImageNet unseen, IID | accuracy: 67.75 -> 68.05 | Improved |
| meta-learned initialization (FRL linear) instead of FedAvg fine-tuning (ablation) | FRL · miniImageNet unseen, non-IID | accuracy: 33.39 -> 53.51 | Improved |
| pretrain with FedAvg before deployment instead of random init (ablation) | FedAvg · CIFAR-100 unseen, IID | accuracy: 51.55 -> 63.18 | Improved |
| pretrain with FedAvg before deployment instead of random init (ablation) | FedAvg · FEMNIST unseen, non-IID | accuracy: 59.22 -> 58.23 | No clear effect |
| use one-shot FL fine-tuning instead of FedAvg fine-tuning (ablation) | fine-tuning baseline · CIFAR-100 unseen, non-IID | accuracy: 44.33 -> 35.11 | Hurt |
| use one-shot FL fine-tuning instead of FedAvg fine-tuning (ablation) | fine-tuning baseline · CIFAR-100 unseen, IID | accuracy: 63.18 -> 64.71 | Improved |
Closest papers by meaning
- Rethinking the Starting Point: Collaborative Pre-Training for Federated Downstream Tasks (AAAI 2025 · similarity 0.89)
- FedQS: Optimizing Gradient and Model Aggregation for Semi-Asynchronous Federated Learning (NeurIPS 2025 · similarity 0.88)
- Knowledge Transfer via Compact Model in Federated Learning (Student Abstract) (AAAI 2024 · similarity 0.88)
- Federated Learning under Periodic Client Participation and Heterogeneous Data: A New Communication-Efficient Algorithm and Analysis (NeurIPS 2024 · similarity 0.88)
- Revisiting Ensembling in One-Shot Federated Learning (NeurIPS 2024 · similarity 0.88)
- One-shot Federated Learning via Synthetic Distiller-Distillate Communication (NeurIPS 2024 · similarity 0.88)
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.
