Research map / Federated learning and privacy / Communication-efficient FL
Countering the Communication Bottleneck in Federated Learning: A Highly Efficient Zero-Order Optimization Technique
Elissa Mhanna, Mohamad Assaad
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 |
|---|---|---|---|
| use 2P-ZOFL (two scalars per round) instead of FedAvg | federated learning · FashionMNIST shirts vs sneakers (MLP, 197602 params) | scalars uploaded per device: 59280600 -> 4000 | Improved |
| use 2P-ZOFL instead of FedZO | federated learning · FashionMNIST shirts vs sneakers (MLP, 197602 params) | scalars uploaded per device: 148201500 -> 4000 | Improved |
| use 2P-ZOFL instead of FedAvg regarding rounds needed | federated learning · FashionMNIST shirts vs sneakers (MLP, 197602 params) | communication rounds to convergence: 300 -> 2000 | Hurt |
| switch from IID to non-IID data distribution | 2P-ZOFL · FashionMNIST shirts vs sneakers (MLP, 197602 params) | accuracy / convergence speed | No clear effect |
| increase wireless noise variance (ablation) | 2P-ZOFL · MNIST 0 vs 1 non-convex sigmoid, sigma_n^2 in {0.25, 1, 2.25, 3.1684, 10.0489} | convergence speed: worst-case loss of 2.5% accuracy | Hurt |
| use constant instead of vanishing step sizes (ablation) | 2P-ZOFL · Mushroom, strictly convex logistic regression | convergence speed | Improved |
| add wireless noise (ablation) | 2P-ZOFL · Mushroom, strictly convex logistic regression | convergence speed | Hurt |
| use constant step sizes with gradient-dominated loss (ablation) | 2P-ZOFL · MNIST 0 vs 1, kappa-gradient dominated loss | convergence rate | Improved |
Closest papers by meaning
- Achieving Dimension-Free Communication in Federated Learning via Zeroth-Order Optimization (ICLR 2025 · similarity 0.90)
- Low Precision Local Training is Enough for Federated Learning (NeurIPS 2024 · similarity 0.89)
- Communication-Efficient Federated Learning with Accelerated Client Gradient (CVPR 2024 · similarity 0.89)
- Decentralized Sporadic Federated Learning: A Unified Algorithmic Framework with Convergence Guarantees (ICLR 2025 · similarity 0.88)
- SILVER: Single-loop variance reduction and application to federated learning (ICML 2024 · similarity 0.88)
- SpaFL: Communication-Efficient Federated Learning With Sparse Models And Low Computational Overhead (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.
