Research map / Federated learning and privacy / Communication-efficient FL
Scaling Law Analysis in Federated Learning: How to Select the Optimal Model Size?
Xuanyu Chen, Nan Yang, Shuai Wang, Dong Yuan
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 |
|---|---|---|---|
| increase number of FL clients at fixed total compute | ViT MAE linear probing · CIFAR-100 and ImageNet (10% LP) | optimal model size: slopes in [-0.28, -0.48], R2 > 0.88 | Hurt |
| switch from centralized to federated training with same data | ViT MAE linear probing · CIFAR-100 and ImageNet | LP accuracy | Hurt |
| increase number of clients | ViT MAE linear probing · CIFAR-100 | LP accuracy gap to centralized | Hurt |
| train on one client's data only vs full FL | ViT · CIFAR-100 and ImageNet | optimal model size | No clear effect |
| replace ViT with ResNet | FL scaling analysis · CIFAR-100 and ImageNet | optimal model size trend | No clear effect |
Closest papers by meaning
- FedLLM-Bench: Realistic Benchmarks for Federated Learning of Large Language Models (NeurIPS 2024 · similarity 0.89)
- Federated Learning with Heterogeneous LLMs: Integrating Small Student Client Models with a Large Hungry Model (AAAI 2025 · similarity 0.89)
- FlowerTune: A Cross-Domain Benchmark for Federated Fine-Tuning of Large Language Models (NeurIPS 2025 · similarity 0.89)
- Improving Generalization in Federated Learning with Model-Data Mutual Information Regularization: A Posterior Inference Approach (NeurIPS 2024 · similarity 0.88)
- Benchmarking Algorithms for Federated Domain Generalization (ICLR 2024 · similarity 0.88)
- Low Precision Local Training is Enough for Federated Learning (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.
