Research map / Federated learning and privacy / Personalized and heterogeneous FL
On Bridging Generic and Personalized Federated Learning for Image Classification
Hong-You Chen, Wei-Lun Chao
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 |
|---|---|---|---|
| Replace empirical risk with BRM in FedAvg (ablation) | FedAvg · CIFAR-10 Dir(0.3) | G-FL accuracy: 68.6 -> 76.8 | Improved |
| Replace empirical risk with BRM in FedAvg (ablation) | FedAvg · CIFAR-10 Dir(0.3) | P-FL accuracy: 85.1 -> 76.1 | Hurt |
| Add a personalized predictor trained with client empirical risk (ablation) | FedAvg (BRM) · CIFAR-10 Dir(0.3) | P-FL accuracy: 76.1 -> 86.4 | Improved |
| Replace the client-specific linear personalized head with a hypernetwork-generated head (ablation) | Fed-RoD (linear, BRM) · CIFAR-10 Dir(0.3) | P-FL accuracy: 86.4 -> 86.8 | Improved |
| Fine-tune the FedAvg (BRM) model on client data (ablation) | FedAvg (BRM) · CIFAR-10 Dir(0.3) | P-FL accuracy: 76.1 -> 84.5 | Improved |
| Use balanced softmax rather than cross entropy for BRM (ablation) | Fed-RoD · CIFAR-10 Dir(0.3) | G-FL accuracy: 68.6 -> 76.9 | Improved |
| Use balanced softmax rather than cross entropy for BRM (ablation) | Fed-RoD · CIFAR-10 Dir(0.3) | P-FL accuracy: 85.1 -> 86.8 | Improved |
| Combine FedDyn with Fed-RoD | Fed-RoD (hyper) · FMNIST Dir(0.1) | G-FL accuracy: 83.9 -> 85.9 | Improved |
| Combine FedDyn with Fed-RoD | Fed-RoD (hyper) · FMNIST Dir(0.1) | P-FL accuracy: 92.9 -> 95.3 | Improved |
| Combine FedDyn with Fed-RoD | Fed-RoD (hyper) · CIFAR-10 Dir(0.3) | G-FL accuracy: 76.9 -> 74.6 | Hurt |
| Combine FedDyn with Fed-RoD | Fed-RoD (hyper) · CIFAR-10 Dir(0.3) | P-FL accuracy: 86.8 -> 85.6 | Hurt |
| Use a hypernetwork conditioned on class distribution to produce personalized predictors for new clients (ablation) | Fed-RoD (linear) · CIFAR-10 Dir(0.3), future clients | P-FL accuracy before fine-tuning: 62.4 -> 75.7 | Improved |
Closest papers by meaning
- FedBABU: Toward Enhanced Representation for Federated Image Classification (ICLR 2022 · similarity 0.90)
- Personalized Federated Learning via Feature Distribution Adaptation (NeurIPS 2024 · similarity 0.89)
- Guiding The Last Layer in Federated Learning with Pre-Trained Models (NeurIPS 2023 · similarity 0.89)
- Flexible Sharpness-Aware Personalized Federated Learning (AAAI 2025 · similarity 0.88)
- FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Data (ICLR 2024 · similarity 0.88)
- Fine-Tuning Personalization in Federated Learning to Mitigate Adversarial Clients (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.
