Research map / Federated learning and privacy / Personalized and heterogeneous FL
FedNP: Towards Non-IID Federated Learning via Federated Neural Propagation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 FedNP's auxiliary global-data-distribution estimation to FedAvg | FedAvg · CIFAR-100 test | top-1 accuracy: 62.93% ± 0.3% -> 65.03% ± 0.2% | Helped |
| Add FedNP's auxiliary global-data-distribution estimation to FedAvg | FedAvg · TinyImageNet test | top-1 accuracy: 51.89% ± 0.5% -> 53.18% ± 0.3% | Helped |
| Add FedNP's auxiliary global-data-distribution estimation to FedAvg | FedAvg · CHiME-5 test | WER: 68.86±0.11 -> 64.30±0.21 | Helped |
| Add FedNP's auxiliary global-data-distribution estimation to FedProx | FedProx · CHiME-5 test | WER: 66.72±0.28 -> 64.30±0.21 | Helped |
| Use FedProx's distance-to-global-model regularization instead of FedAvg | FedAvg · CIFAR-100 test | top-1 accuracy: 62.93% ± 0.3% -> 62.11% ± 0.2% | Hurt |
| Use FedProx's distance-to-global-model regularization instead of FedAvg | FedAvg · TinyImageNet test | top-1 accuracy: 51.89% ± 0.5% -> 50.63% ± 0.2% | Hurt |
| Use FedPA Bayesian model aggregation instead of FedAvg | FedAvg · CHiME-5 test | WER: 68.86±0.11 -> 69.92±0.22 | Hurt |
Closest papers by meaning
- SparsyFed: Sparse Adaptive Federated Learning (ICLR 2025 · similarity 0.87)
- Improving Generalization in Federated Learning with Model-Data Mutual Information Regularization: A Posterior Inference Approach (NeurIPS 2024 · similarity 0.87)
- FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Data (ICLR 2024 · similarity 0.86)
- FedQS: Optimizing Gradient and Model Aggregation for Semi-Asynchronous Federated Learning (NeurIPS 2025 · similarity 0.86)
- FedUV: Uniformity and Variance for Heterogeneous Federated Learning (CVPR 2024 · similarity 0.86)
- FedSOL: Stabilized Orthogonal Learning with Proximal Restrictions in Federated Learning (CVPR 2024 · 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.