Research map / Federated learning and privacy / Personalized and heterogeneous FL
Guiding The Last Layer in Federated Learning with Pre-Trained Models
Gwen Legate, Nicolas Bernier, Lucas Caccia, Edouard Oyallon, Eugene Belilovsky
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 FedNCM initialization before fine-tuning (FedNCM+FT vs FT) | FT with FedAvg · CIFAR-10 | accuracy: 85.4 -> 87.2 | Improved |
| add FedNCM initialization before fine-tuning | FT with FedAvg · Flowers-102 | accuracy: 64.5 -> 74.9 | Improved |
| add FedNCM initialization before fine-tuning | FT with FedAvg · Stanford Cars | accuracy: 48.7 -> 54.8 | Improved |
| use FedAdam instead of FedAvg in FedNCM+FT (ablation) | FedNCM+FT · CIFAR-10 | accuracy: 87.2 -> 89.4 | Improved |
| replace FedNCM stage 1 by 5 rounds of LP (ablation) | FedNCM+FT · Flowers-102 | accuracy: 74.9 -> 68.6 | Hurt |
| replace FedNCM stage 1 by 10 rounds of LP (ablation) | FedNCM+FT · CIFAR-10 | accuracy: 87.2 -> 84.5 | Hurt |
| replace linear head by three-layer MLP in LP (ablation) | LP · CIFAR-10 | accuracy: 82.5 -> 84.1 | Improved |
| replace linear head by three-layer MLP in LP (ablation) | LP · Flowers-102 | accuracy: 74.1 -> 72.5 | Hurt |
| replace linear head by three-layer MLP in LP (ablation) | LP · EuroSAT-Sub | accuracy: 92.6 -> 91.7 | Hurt |
| replace linear head by three-layer MLP in LP (ablation) | LP · CUB | accuracy: 50.0 -> 50.3 | No clear effect |
| use native 224x224 input instead of 32x32 for CIFAR-10 (ablation) | FedNCM+FT · CIFAR-10 | accuracy: 67.9 -> 87.2 | Improved |
| FedNCM instead of FT with only 90 CIFAR-10 samples | FT · CIFAR-10 small subset (ResNet18) | accuracy: 45.2 -> 55.6 | Improved |
Closest papers by meaning
- Recurrent Early Exits for Federated Learning with Heterogeneous Clients (ICML 2024 · similarity 0.89)
- Personalized Federated Learning via Feature Distribution Adaptation (NeurIPS 2024 · similarity 0.89)
- Knowledge Transfer via Compact Model in Federated Learning (Student Abstract) (AAAI 2024 · similarity 0.88)
- FedQS: Optimizing Gradient and Model Aggregation for Semi-Asynchronous Federated Learning (NeurIPS 2025 · similarity 0.88)
- Low Precision Local Training is Enough for Federated Learning (NeurIPS 2024 · similarity 0.88)
- Tackling Feature-Classifier Mismatch in Federated Learning via Prompt-Driven Feature Transformation (NeurIPS 2025 · 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.
