Research map / Federated learning and privacy / Personalized and heterogeneous FL
Revisiting Weighted Aggregation in Federated Learning with Neural Networks
Zexi Li, Tao Lin, Xinyi Shang, Chao Wu
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 FedLAW instead of the strongest listed baseline | federated aggregation · FashionMNIST IID, MLP | Top-1 test accuracy (%): 89.29 -> 88.51 | Hurt |
| Use FedLAW instead of the strongest listed baseline | federated aggregation · CIFAR-10 IID, ResNet | Top-1 test accuracy (%): 77.94 -> 80.46 | Improved |
| Use FedLAW instead of the strongest listed baseline | federated aggregation · CIFAR-100 NonIID α=0.1, ResNet | Top-1 test accuracy (%): 29.00 -> 25.31 | Hurt |
| Apply fixed global weight shrinking with γ=0.93 instead of γ=1.0 (ablation) | FedAvg on CIFAR-10 IID α=100, SimpleCNN · CIFAR-10 IID α=100, E=2 | test accuracy: 65.53 -> 70.16 | Improved |
| Apply fixed global weight shrinking with γ=0.93 instead of γ=1.0 (ablation) | FedAvg on CIFAR-10 NonIID α=1, SimpleCNN · CIFAR-10 NonIID α=1, E=2 | test accuracy: 65.58 -> 69.28 | Improved |
| Use a fixed shrinking factor that is too small or too large rather than the setting-specific best (ablation) | global weight shrinking · CIFAR-10, varying IID and NonIID settings | test accuracy | Hurt |
| Add local weight decay to adaptive GWS (ablation) | adaptive GWS on CIFAR-10 IID α=100 · CIFAR-10 IID α=100, E=2 | test accuracy: 71.47; 71.36; 71.35; 71.44; 71.54 | No clear effect |
| Add local weight decay to adaptive GWS (ablation) | adaptive GWS on CIFAR-10 NonIID α=1 · CIFAR-10 NonIID α=1, E=2 | test accuracy: 70.31; 69.93; 70.44; 70.47; 69.99 | No clear effect |
| Combine adaptive global weight shrinking with local weight decay (ablation) | FedAvg · CIFAR-10 IID and NonIID, E=2 | test accuracy: 66.43 -> 71.47; 65.35 -> 70.31 | Improved |
| Add SWA to FedLAW (ablation) | FedLAW · FashionMNIST NonIID α=0.1, MLP | Top-1 test accuracy (%): 86.30 -> 86.89 | Improved |
| Add SWA to FedLAW (ablation) | FedLAW · CIFAR-10 NonIID α=0.1, ResNet | Top-1 test accuracy (%): 52.83 -> 57.08 | Improved |
| Use early-stopped attentive LAW, then data-sized weights after the critical point (ablation) | attentive LAW · CIFAR-10 hybrid client heterogeneity | test accuracy | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- FedBE — FedBE: Making Bayesian Model Ensemble Applicable to Federated Learning (ICLR 2021) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- FedLWS: Federated Learning with Adaptive Layer-wise Weight Shrinking (ICLR 2025 · similarity 0.91)
- FedAWA: Adaptive Optimization of Aggregation Weights in Federated Learning Using Client Vectors (CVPR 2025 · similarity 0.91)
- Improving Federated Domain Generalization Through Dynamical Weights Calculated from Data Influences on Global Model Update (AAAI 2025 · similarity 0.89)
- Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight Averaging (ICML 2025 · similarity 0.88)
- AFL: A Single-Round Analytic Approach for Federated Learning with Pre-trained Models (CVPR 2025 · similarity 0.88)
- FedQS: Optimizing Gradient and Model Aggregation for Semi-Asynchronous Federated Learning (NeurIPS 2025 · 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.
