Research map / Federated learning and privacy / Communication-efficient FL
Communication-Efficient Federated Bilevel Optimization with Global and Local Lower Level Problems
Junyi Li, Feihu Huang, Heng Huang
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 more clients sampled per epoch | FedBiOAcc · Federated Data Cleaning (MNIST, 10 clients) | validation error vs communication rounds | Improved |
| Increase number of local steps I under larger label noise | FedBiOAcc · Federated Data Cleaning (MNIST) | validation error vs communication rounds | Improved |
| Add momentum-based variance reduction (FedBiOAcc vs FedBiO) (ablation) | FedBiO · Federated Data Cleaning and Hyper-representation | validation error vs communication rounds | Improved |
| Add multiple local steps (I=5) instead of one-step distributed version (ablation) | FedBiOAcc-Local · Omniglot and MiniImageNet N-way-K-shot | validation error vs communication rounds | Improved |
| Compare FedBiOAcc with FedAvg trained on noisy data at high noise rho=0.95 | FedBiOAcc · Federated Data Cleaning (MNIST) | validation error | Improved |
| Compare FedBiOAcc against FedNest, CommFedBiO, AggITD, FedMBO, Local-BSGVR across noise levels | FedBiOAcc · Federated Data Cleaning, rho 0.1 to 0.95 | validation error vs communication rounds | Improved |
Closest papers by meaning
- First-Order Federated Bilevel Learning (AAAI 2025 · similarity 0.92)
- Distributed Bilevel Optimization with Communication Compression (ICML 2024 · similarity 0.88)
- Communication-Efficient Federated Learning with Accelerated Client Gradient (CVPR 2024 · similarity 0.87)
- Federated Optimization with Doubly Regularized Drift Correction (ICML 2024 · similarity 0.87)
- Efficient Adaptive Federated Optimization (NeurIPS 2025 · similarity 0.87)
- Achieving Dimension-Free Communication in Federated Learning via Zeroth-Order Optimization (ICLR 2025 · similarity 0.87)
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.
