Research map / Federated learning and privacy / Communication-efficient FL
Adaptive Guidance for Local Training in Heterogeneous Federated Learning
Jianqing Zhang, Yang Liu, Hua Yang, Zhenzhe Zheng, Han Yu, Yuyin Zhou, Jian Cao, Qiang Yang
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 global guiding vectors (FedL2G-l) over local training only (ablation) | local training · Cifar100 (Dirichlet) | accuracy (%): 35.6 -> 42.3 | Improved |
| add global guiding vectors (FedL2G-f) over local training only (ablation) | local training · Cifar10 (Dirichlet) | accuracy (%): 83.2 -> 87.6 | Improved |
| use feature-space sharing (FedL2G-f) instead of logit space | FedL2G-l · Cifar100 (pathological) | accuracy (%): 59.2 -> 64.2 | Improved |
| use feature-space sharing (FedL2G-f) instead of logit space | FedL2G-l · TinyImageNet (Dirichlet) | accuracy (%): 49.5 -> 50.3 | Improved |
| add warm-up period T'=50 to FedL2G-f (ablation) | FedL2G-f · Cifar100 (Dirichlet) | accuracy (%): 40.9 -> 43.8 | Improved |
| add warm-up period T'=50 to FedL2G-l (ablation) | FedL2G-l · Cifar100 (Dirichlet) | accuracy (%): 41.7 -> 42.3 | No clear effect |
| raise server learning rate eta_s of FedL2G-f from 1 to 100 (ablation) | FedL2G-f · Cifar100 (Dirichlet) | accuracy (%): 41.1 -> 43.8 | Improved |
| shrink quiz set size from 10 to 2 (ablation) | FedL2G-f · Cifar100 (Dirichlet) | accuracy (%): 43.8 -> 44.2 | No clear effect |
| add Gaussian noise to guiding-vector gradients (s=0.05, p=0.2) (ablation) | FedL2G-f · Cifar100 (Dirichlet) | accuracy (%): 43.8 -> 42.6 | Hurt |
| increase heterogeneity to HtFE9 with FedL2G-f vs FedProto | FedProto · Cifar100 (Dirichlet, HtFE9) | accuracy (%): 32.7 -> 45.7 | Improved |
| increase clients to 100 with participation 0.1 | FedMRL · Cifar100 (Dirichlet, 100 clients, rho=0.1) | accuracy (%): 41.7 -> 42.3 | Improved |
| FedL2G-f vs best baseline FedDistill at beta=0.01 | FedDistill · Cifar100 (Dirichlet, beta=0.01) | accuracy (%): 67.0 -> 70.6 | Improved |
Closest papers by meaning
- One-Shot Heterogeneous Federated Learning with Local Model-Guided Diffusion Models (ICML 2025 · similarity 0.90)
- Convergence Analysis of Split Federated Learning on Heterogeneous Data (NeurIPS 2024 · similarity 0.89)
- FedDAT: An Approach for Foundation Model Finetuning in Multi-Modal Heterogeneous Federated Learning (AAAI 2024 · similarity 0.89)
- FedQS: Optimizing Gradient and Model Aggregation for Semi-Asynchronous Federated Learning (NeurIPS 2025 · similarity 0.89)
- FedLPS: Heterogeneous Federated Learning for Multiple Tasks with Local Parameter Sharing (AAAI 2024 · similarity 0.88)
- Fake It Till Make It: Federated Learning with Consensus-Oriented Generation (ICLR 2024 · 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.
