Research map / Federated learning and privacy / Personalized and heterogeneous FL
Addressing Heterogeneity in Federated Learning via Distributional Transformation
Haolin Yuan, Bo Hui, Yuchen Yang, Philippe Burlina, Neil Zhenqiang Gong, Yinzhi Cao
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 double-input-channel model instead of single channel (ablation) | DisTrans · CH-MNIST (DH 100%) | accuracy: 0.889 -> 0.946 | Improved |
| use double-input-channel model instead of single channel (ablation) | DisTrans · Bird-200 (DH 100%) | accuracy: 0.505 -> 0.641 | Improved |
| use double-input-channel model instead of single channel (ablation) | DisTrans · Bird-200 (DH 0%) | accuracy: 0.569 -> 0.556 | Hurt |
| use no aggregation instead of NN aggregation at high heterogeneity (ablation) | DisTrans · Bird-200 (DH 100%) | accuracy: 0.513 -> 0.641 | Improved |
| use NN aggregation instead of no aggregation at low heterogeneity (ablation) | DisTrans · CH-MNIST (DH 0%) | accuracy: 0.868 -> 0.908 | Improved |
| use NN aggregation instead of average aggregation (ablation) | DisTrans · CIFAR-10 (DH 80%) | accuracy: 0.702 -> 0.743 | Improved |
| replace FedAvg with DisTrans | FedAvg · CIFAR-100 (DH 100%) | accuracy: 0.524 -> 0.834 | Improved |
| replace FedAvg with DisTrans | FedAvg · CelebA (DH 100%) | accuracy: 0.639 -> 0.804 | Improved |
| add mixup to FedAvg | FedAvg · CH-MNIST (DH 0%) | accuracy: 0.891 -> 0.896 | Improved |
| add mixup to FedAvg | FedAvg · CH-MNIST (DH 100%) | accuracy: 0.908 -> 0.901 | Hurt |
| add AdvProp to FedAvg | FedAvg · CH-MNIST (DH 100%) | accuracy: 0.908 -> 0.919 | Improved |
| add AdvProp to FedAvg | FedAvg · CH-MNIST (DH 0%) | accuracy: 0.891 -> 0.879 | Hurt |
Closest papers by meaning
- FedGPS: Statistical Rectification Against Data Heterogeneity in Federated Learning (NeurIPS 2025 · similarity 0.89)
- Adaptive Latent-Space Constraints in Personalized Federated Learning (NeurIPS 2025 · similarity 0.88)
- Federated Learning with Sample-level Client Drift Mitigation (AAAI 2025 · similarity 0.88)
- Tackling Intertwined Data and Device Heterogeneities in Federated Learning with Unlimited Staleness (AAAI 2025 · similarity 0.87)
- FedImpro: Measuring and Improving Client Update in Federated Learning (ICLR 2024 · similarity 0.87)
- Overcoming Data and Model heterogeneities in Decentralized Federated Learning via Synthetic Anchors (ICML 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.
