Research map / Federated learning and privacy / Personalized and heterogeneous FL
FedDC: Federated Learning With Non-IID Data via Local Drift Decoupling and Correction
Liang Gao, Huazhu Fu, Li Li, Yingwen Chen, Ming Xu, Cheng-Zhong Xu
Check 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 |
|---|---|---|---|
| Track and correct client parameter drift with a local drift variable | FedDC · CIFAR100-iid, 100 clients, full participation | communication rounds to 40% accuracy: 56 -> 37 | Improved |
| Track and correct client parameter drift with a local drift variable | FedDC · CIFAR10-D2, 100 clients, full participation | test accuracy: 79.14 -> 84.32 | Improved |
| Add the penalized term to the FedDC local objective (ablation) | FedDC(le) · CIFAR10, iid and non-iid, 100 clients, 15% participation | test accuracy | Improved |
| Add the gradient correction term to the FedDC objective with the penalized term (ablation) | FedDC(lelp) · CIFAR10, iid and non-iid, 100 clients, 15% participation | test accuracy | Improved |
| Omit the penalized term that constrains the drift variable (ablation) | FedDC(le) and FedDC(lelg) · CIFAR10, iid and non-iid, 100 clients, 15% participation | test accuracy | Hurt |
| Increase the penalized-term weight to 0.5 or 1 (ablation) | FedDC · MNIST and CIFAR10, 100 clients, 15% participation | convergence performance | Hurt |
| Use partial client participation at 15% instead of full participation | FedDC · CIFAR10-iid, 100 clients | test accuracy: 86.18% -> 85.71% | Hurt |
Later papers that compared with this method
5 later accepted papers report FedDc as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.
- FedST: Federated Style Transfer Learning for Non-IID Image Segmentation (AAAI 2024 · better on 8 of 9 shared results)
- Communication-Efficient Federated Learning with Accelerated Client Gradient (CVPR 2024 · better on 6 of 7 shared results)
- FedNP: Towards Non-IID Federated Learning via Federated Neural Propagation (AAAI 2023 · better on 2 of 2 shared results)
- Flash: Concept Drift Adaptation in Federated Learning (ICML 2023 · better on 0 of 1 shared result)
- Towards Instance-adaptive Inference for Federated Learning (ICCV 2023 · better on 1 of 1 shared result)
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
- FedUV: Uniformity and Variance for Heterogeneous Federated Learning (CVPR 2024 · similarity 0.88)
- Federated Learning with Sample-level Client Drift Mitigation (AAAI 2025 · similarity 0.88)
- FedAdaVR: Adaptive Variance Reduction for Robust Federated Learning under Limited Client Participation (NeurIPS 2026 · similarity 0.88)
- FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Data (ICLR 2024 · similarity 0.87)
- FedQS: Optimizing Gradient and Model Aggregation for Semi-Asynchronous Federated Learning (NeurIPS 2025 · similarity 0.87)
- FedImpro: Measuring and Improving Client Update in Federated Learning (ICLR 2024 · 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.
