Research map / Federated learning and privacy / Personalized and heterogeneous FL
Federated Learning via Meta-Variational Dropout
Insu Jeon, Minui Hong, Junhyeog Yun, Gunhee Kim
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 MetaVD to Reptile | Reptile · CIFAR-100 alpha=5.0 | accuracy: 47.87 -> 53.71 | Improved |
| add MetaVD to FedAvg | FedAvg · CIFAR-100 alpha=5.0 | accuracy: 42.35 -> 47.82 | Improved |
| add MetaVD to MAML | MAML · CIFAR-100 alpha=0.5 | accuracy: 46.33 -> 50.21 | Improved |
| add MetaVD to PerFedAvg | PerFedAvg · CIFAR-10 alpha=0.1 | accuracy: 75.42 -> 76.06 | Mixed |
| replace hypernetwork dropout with global VD (ablation) | Reptile+MetaVD · CIFAR-100 | Test accuracy: 53.71 -> 50.20 | Hurt |
| replace hypernetwork dropout with EnsembleVD (ablation) | Reptile+MetaVD · CIFAR-100 | Test accuracy: 53.71 -> 52.49 | Hurt |
| replace hypernetwork dropout with global VD (ablation) | Reptile+MetaVD · FEMNIST | OOD accuracy: 88.71 -> 85.88 | Hurt |
| add MetaVD to Reptile | Reptile · CIFAR-100 OOD alpha=0.1 | ECE (%): 0.77 -> 0.57 | Improved |
| add MetaVD to FedAvg | FedAvg · CIFAR-100 OOD alpha=0.1 | ECE (%): 0.60 -> 0.39 | Improved |
| add MetaVD to Reptile | Reptile · CIFAR-100 OOD alpha=0.1 | MCE (%): 50.52 -> 42.40 | Improved |
| add MetaVD to Reptile | Reptile · FEMNIST s=0.05 | Test accuracy: 87.86 -> 89.43 | Improved |
| add MetaVD to FedAvg | FedAvg · FEMNIST s=0.2 | OOD accuracy: 85.29 -> 85.28 | No clear effect |
Closest papers by meaning
- FedAdaVR: Adaptive Variance Reduction for Robust Federated Learning under Limited Client Participation (NeurIPS 2026 · similarity 0.87)
- Federated Generalised Variational Inference: A Robust Probabilistic Federated Learning Framework (ICML 2025 · similarity 0.86)
- A Bayesian Approach for Personalized Federated Learning in Heterogeneous Settings (NeurIPS 2024 · similarity 0.86)
- Calibrated One Round Federated Learning with Bayesian Inference in the Predictive Space (AAAI 2024 · similarity 0.86)
- Improving Generalization in Federated Learning with Model-Data Mutual Information Regularization: A Posterior Inference Approach (NeurIPS 2024 · similarity 0.86)
- SparsyFed: Sparse Adaptive Federated Learning (ICLR 2025 · similarity 0.86)
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.
