Research map / Federated learning and privacy / Personalized and heterogeneous FL
Federated Learning for Non-IID Data via Unified Feature Learning and Optimization Objective Alignment
Lin Zhang, Yong Luo, Yan Bai, Bo Du, Ling-Yu Duan
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 uniform adversarial (UAD) loss (ablation) | FedAVG · CIFAR-10 | accuracy: 59.95 -> 65.29 | Improved |
| add group consensus (CGR) loss (ablation) | FedAVG · CIFAR-10 | accuracy: 59.95 -> 65.10 | Improved |
| add global consensus (CGL) loss (ablation) | FedAVG · CIFAR-10 | accuracy: 59.95 -> 65.01 | Improved |
| add CGR loss on top of UAD (ablation) | UAD · CIFAR-10 | accuracy: 65.29 -> 66.29 | Improved |
| add CGL loss on top of UAD (ablation) | UAD · CIFAR-10 | accuracy: 65.29 -> 66.30 | Improved |
| add both consensus losses on top of UAD (ablation) | UAD · CIFAR-10 | accuracy: 65.29 -> 67.80 | Improved |
| add UAD loss on top of CGR loss (ablation) | CGR · CIFAR-10 | accuracy: 65.10 -> 66.29 | Improved |
| add dynamic sampling strategy (ablation) | All three losses · CIFAR-10 | accuracy: 67.80 -> 67.45 | Hurt |
| add dynamic sampling strategy (ablation) | All three losses · CIFAR-10 | Pstd (fairness, lower better): 7.42 -> 3.54 | Improved |
| add dynamic sampling strategy (ablation) | CGL only · CIFAR-10 | accuracy: 65.01 -> 63.07 | Hurt |
| add UAD loss (ablation) | FedAVG · CIFAR-10 | Pstd (fairness, lower better): 9.23 -> 4.21 | Improved |
| add CGR loss on top of UAD+CGL (ablation) | UAD + CGL · CIFAR-10 | Pstd (fairness, lower better): 4.21 -> 7.07 | Hurt |
Closest papers by meaning
- FedPKDA: Personalized Federated Learning with Privacy-Preserving Knowledge Dynamic Alignment (AAAI 2026 · similarity 0.88)
- A Simple Data Augmentation for Feature Distribution Skewed Federated Learning (CVPR 2025 · similarity 0.87)
- FedWon: Triumphing Multi-domain Federated Learning Without Normalization (ICLR 2024 · similarity 0.87)
- A-FedPD: Aligning Dual-Drift is All Federated Primal-Dual Learning Needs (NeurIPS 2024 · similarity 0.87)
- FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity (ICLR 2024 · similarity 0.86)
- Adaptive Latent-Space Constraints in Personalized Federated Learning (NeurIPS 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.
