Research map / Federated learning and privacy / Personalized and heterogeneous FL
Global Balanced Experts for Federated Long-Tailed Learning
Yaopei Zeng, Lei Liu, Li Liu, Li Shen, Shaoguo Liu, Baoyuan 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 global label distribution instead of local label distribution as class prior for BSM (ablation) | BSM · CIFAR-100-LT IR=100 | top-1 accuracy: 35.55 -> 38.56 | Improved |
| use GPI as class prior instead of local label distribution (ablation) | BSM · CIFAR-100-LT IR=100 | top-1 accuracy: 35.55 -> 37.19 | Improved |
| add multi-expert ensemble on top of GPI prior (ablation) | BSM with GPI · CIFAR-100-LT IR=100 | top-1 accuracy: 37.19 -> 40.42 | Improved |
| group clients randomly instead of by LPI/GPI similarity (ablation) | GBME · CIFAR-100-LT IR=100 | top-1 accuracy: 37.19 -> 37.38 | No clear effect |
| group clients by GPI cosine similarity (ablation) | GBME · CIFAR-100-LT IR=100 | top-1 accuracy: 37.19 -> 40.42 | Improved |
| increase number of experts from 1 to 4 (ablation) | GBME · CIFAR-100-LT IR=100 | top-1 accuracy: 37.19 -> 41.68 | Improved |
| increase experts from 4 to 5 (ablation) | GBME · CIFAR-100-LT IR=100 | top-1 accuracy: 41.68 -> 41.85 | No clear effect |
| client selection alpha at 0 or 1 versus about 0.6 (multiple selection) (ablation) | GBME · CIFAR-100-LT IR=100 | top-1 accuracy: 36.19 -> 40.42 | Improved |
| tighten privacy budget (lower epsilon) in GBME-p (ablation) | GBME-p · CIFAR-100-LT IR=100 | top-1 accuracy: 40.24 -> 38.50 | Hurt |
| use global instead of local label prior for re-balance methods (RIDE) (ablation) | RIDE · CIFAR-100-LT IR=100 | top-1 accuracy: 34.94 -> 34.59 | No clear effect |
| GBME with half communication rounds versus FedAvg | GBME · CIFAR-100-LT IR=100 | top-1 accuracy: 34.48 -> 35.11 | Improved |
Closest papers by meaning
- FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Data (ICLR 2024 · similarity 0.88)
- Low Precision Local Training is Enough for Federated Learning (NeurIPS 2024 · similarity 0.87)
- FedLMT: Tackling System Heterogeneity of Federated Learning via Low-Rank Model Training with Theoretical Guarantees (ICML 2024 · similarity 0.86)
- Interaction-Aware Gaussian Weighting for Clustered Federated Learning (ICML 2025 · similarity 0.86)
- A Bayesian Approach for Personalized Federated Learning in Heterogeneous Settings (NeurIPS 2024 · similarity 0.86)
- FedAWA: Adaptive Optimization of Aggregation Weights in Federated Learning Using Client Vectors (CVPR 2025 · 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.
