Research map / Federated learning and privacy / Communication-efficient FL
Class-Grouped Normalized Momentum and Faster Hyperparameter Exploration to Tackle Class Imbalance in Federated Learning
Haemin Park, Diego Klabjan, Martin W. Braun, Xiuqi Li, Balakrishnan Ananthanarayanan
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 group momentum (beta=0.5) to class-grouped normalization (ablation) | FedCGN · CIFAR-10-LT imbalance 20 (K=5) | accuracy (%): 83.35 -> 85.65 | Improved |
| add group momentum (beta=0.5) to class-grouped normalization (ablation) | FedCGN · CIFAR-100-LT imbalance 20 (K=20) | accuracy (%): 38.27 -> 40.51 | Improved |
| raise momentum factor from 0.5 to 0.9 (ablation) | FedCGNM · CIFAR-10-LT imbalance 20 (K=5) | accuracy (%): 85.65 -> 83.93 | Hurt |
| use within-group variance grouping instead of naive half-split (ablation) | FedCGNM · CIFAR-10-LT imbalance 20 (K=5) | F1: 0.8382 -> 0.8565 | Improved |
| use within-group variance grouping instead of naive half-split (ablation) | FedCGNM · CIFAR-100-LT imbalance 20 (K=5) | F1: 0.4339 -> 0.4983 | Improved |
| use 3 or 4 groups instead of 2 (ablation) | FedCGNM · CIFAR-100-LT | validation loss / accuracy | No clear effect |
| add FedHOO sampling-rate search to uniform sampling | FedCGNM · CIFAR-10-LT imbalance 100 (K=5, IID) | F1: 0.7432 -> 0.7485 | Improved |
| add FedHOO sampling-rate search to uniform sampling | FedCGNM · CIFAR-10-LT imbalance 100 (K=5, Non-IID) | F1: 0.5896 -> 0.5945 | Improved |
| replace per-class normalization (FedCGN) by grouped normalized momentum (FedCGNM) | FedCGN · CIFAR-10-LT imbalance 100 (K=5, IID) | F1: 0.7054 -> 0.7432 | Improved |
| use class-weighted cross-entropy instead of plain FedAvg | FedAvg · CIFAR-10-LT imbalance 100 (K=5, IID) | F1: 0.6177 -> 0.5379 | Hurt |
| increase clients from K=5 to K=20 | FedCGNM + U · CIFAR-10-LT imbalance 100 (IID) | F1: 0.7432 -> 0.5294 | Hurt |
| use loss reweighting (Ratio Loss) under mild skew | Ratio Loss · Adult Income (mild imbalance) | F1 | No clear effect |
Closest papers by meaning
- FedWMSAM: Fast and Flat Federated Learning via Weighted Momentum and Sharpness-Aware Minimization (NeurIPS 2025 · similarity 0.89)
- TurboSVM-FL: Boosting Federated Learning through SVM Aggregation for Lazy Clients (AAAI 2024 · similarity 0.88)
- Momentum Benefits Non-iid Federated Learning Simply and Provably (ICLR 2024 · similarity 0.88)
- Momentum-Driven Adaptivity: Towards Tuning-Free Asynchronous Federated Learning (ICML 2025 · similarity 0.88)
- Efficient Federated Learning against Byzantine Attacks and Data Heterogeneity via Aggregating Normalized Gradients (NeurIPS 2025 · similarity 0.87)
- FedQS: Optimizing Gradient and Model Aggregation for Semi-Asynchronous Federated Learning (NeurIPS 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.
