Research map / Federated learning and privacy / Communication-efficient FL
EvoFed: Leveraging Evolutionary Strategies for Communication-Efficient Federated Learning
Mohammad Mahdi Rahimi, Hasnain Irshad Bhatti, Younghyun Park, Humaira Kousar, Do-Yeon Kim, Jaekyun Moon
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 model-parameter exchange with PBGE fitness-vector exchange | FedAvg-style federated learning · MNIST | communication cost at max accuracy: 73.7 -> 9.2 MB | Improved |
| Replace model-parameter exchange with PBGE fitness-vector exchange | FedAvg-style federated learning · FMNIST | communication cost at max accuracy: 40.99 -> 7.78 MB | Improved |
| Replace model-parameter exchange with PBGE fitness-vector exchange | FedAvg-style federated learning · CIFAR-10 | accuracy: 50.22% -> 54.12% | Improved |
| Replace model-parameter exchange with PBGE fitness-vector exchange | FedAvg-style federated learning · CIFAR-10 | communication cost at max accuracy: 2.134 -> 0.023 GB | Improved |
| Use a larger initial population (ablation) | EvoFed · FMNIST | accuracy | Improved |
| Increase population size beyond 128 (ablation) | EvoFed · FMNIST | accuracy | No clear effect |
| Increase the number of clients above 5 (ablation) | EvoFed · image classification experiments | accuracy | Hurt |
| Sparsify the population to fewer remaining members (ablation) | EvoFed · image classification | performance | Hurt |
| Start with a larger population, then sparsify to a smaller set (ablation) | EvoFed · image classification | performance | Improved |
| Quantize fitness values, including to 2 bits (ablation) | EvoFed · image classification | performance | Hurt |
| Transmit fitness ranks instead of fitness values (ablation) | EvoFed · image classification | performance | Improved |
| Use quantization rather than ranking at the same bit budget (ablation) | EvoFed · image classification | performance | Improved |
Closest papers by meaning
- FedSMU: Communication-Efficient and Generalization-Enhanced Federated Learning through Symbolic Model Updates (ICML 2025 · similarity 0.87)
- Communication-Efficient Federated Learning with Accelerated Client Gradient (CVPR 2024 · similarity 0.87)
- Local Superior Soups: A Catalyst for Model Merging in Cross-Silo Federated Learning (NeurIPS 2024 · similarity 0.87)
- Decentralized Sporadic Federated Learning: A Unified Algorithmic Framework with Convergence Guarantees (ICLR 2025 · similarity 0.87)
- Efficient Adaptive Federated Optimization (NeurIPS 2025 · similarity 0.86)
- SpaFL: Communication-Efficient Federated Learning With Sparse Models And Low Computational Overhead (NeurIPS 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.
