Research map / Federated learning and privacy / Personalized and heterogeneous FL
No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data
Mi Luo, Fei Chen, Dapeng Hu, Yifan Zhang, Jian Liang, Jiashi Feng
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 post-hoc classifier calibration with virtual representations (CCVR) | FedAvg · CINIC-10 | Accuracy@1: 60.20 -> 69.99 | Improved |
| add CCVR | FedAvg · CIFAR-10 alpha=0.1 | Accuracy@1: 58.55 -> 62.68 | Improved |
| add CCVR | MOON · CIFAR-10 alpha=0.05 | Accuracy@1: 49.91 -> 55.60 | Improved |
| add CCVR | FedAvg · CIFAR-100 | Accuracy@1: 66.25 -> 66.60 | Improved |
| add classifier weight L2-normalization (clsnorm) during training (ablation) | FedAvg · CIFAR-10 alpha=0.05 | Accuracy@1: 68.62 -> 69.65 (alpha=0.5); 52.33 -> 51.74 (alpha=0.05) | Mixed |
| add classifier proximal regularization (clsprox) during training (ablation) | FedAvg · CIFAR-10 alpha=0.1 | Accuracy@1: 58.55 -> 59.04 | No clear effect |
| post-calibrate classifier with real IID data (oracle) (ablation) | FedAvg · CIFAR-10 alpha=0.1 | Accuracy@1: 58.55 -> 64.70 | Improved |
| increase virtual features per class from 50 to 2000 (ablation) | CCVR on FedAvg · CIFAR-10 alpha=0.1 | Accuracy@1: 61.07 -> 62.68 | Improved |
| increase virtual features per class (50 to 1000) (ablation) | CCVR on FedAvg · CIFAR-10 alpha=0.5 | Accuracy@1: 70.99 -> 70.71 | Mixed |
| increase number of clients 10 to 100 (ablation) | CCVR on FedAvg · CIFAR-10 alpha=0.1 | Accuracy@1: 58.55 -> 62.68 (N=10); 55.42 -> 59.19 (N=100) | No clear effect |
Closest papers by meaning
- Unlocking the Potential of Model Calibration in Federated Learning (ICLR 2025 · similarity 0.90)
- FedUV: Uniformity and Variance for Heterogeneous Federated Learning (CVPR 2024 · similarity 0.90)
- FedCal: Achieving Local and Global Calibration in Federated Learning via Aggregated Parameterized Scaler (ICML 2024 · similarity 0.89)
- FedGPS: Statistical Rectification Against Data Heterogeneity in Federated Learning (NeurIPS 2025 · similarity 0.88)
- FedAdaVR: Adaptive Variance Reduction for Robust Federated Learning under Limited Client Participation (NeurIPS 2026 · similarity 0.88)
- Tackling Feature-Classifier Mismatch in Federated Learning via Prompt-Driven Feature Transformation (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.
