Research map / Federated learning and privacy / Personalized and heterogeneous FL
FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout
Samuel Horváth, Stefanos Laskaridis, Mario Almeida, Ilias Leontiadis, Stylianos Venieris, Nicholas Donald Lane
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 ordered nested submodels instead of random dropout | FjORD · CIFAR10 | accuracy: 1.53-34.87 percentage points (pp) ($19.22$ pp avg. across $p$ values) | Improved |
| use ordered nested submodels instead of random dropout | FjORD · FEMNIST | accuracy: 1.57-6.27 pp ($3.41$ pp avg.) | Improved |
| use ordered nested submodels instead of random dropout | FjORD · Shakespeare | negative perplexity: 0.01-0.82 points (p) ($0.46$ p avg.) | Improved |
| add eFD random dropout (ablation) | FjORD · all three datasets | accuracy / negative perplexity: 0.71-2.66 pp ($1.79$ avg.), up to $2.56$ pp ($1.35$ pp avg.), 0.12-$0.22$ p ($0.18$ p avg.) | Hurt |
| add knowledge distillation (ablation) | FjORD · CIFAR10, p > 0.4 | accuracy: $0.18, 0.68$ and $0.87$ pp for submodels of size $0.6, 0.8$ and $1$ | Improved |
| add knowledge distillation (ablation) | FjORD · FEMNIST | accuracy: $1.96, 2.39$ and $2.65$ pp | Improved |
| add knowledge distillation (ablation) | FjORD · Shakespeare | negative perplexity: $0.10$ p | Improved |
| add knowledge distillation (ablation) | FjORD · CIFAR10 and FEMNIST, p <= 0.4 | accuracy | No clear effect |
| increase p granularity from uniform-5 to uniform-10 (ablation) | FjORD · FEMNIST and Shakespeare | accuracy per submodel | No clear effect |
| allocate a larger share of clients to the highest-capability cluster (ablation) | FjORD · uniform-5, drop scale 0.5 vs 1.0 | accuracy of smaller submodels | No clear effect |
| adapt random dropout rates to client capability | eFD vs FD · CIFAR10 | accuracy: 27.13-33 percentage points (pp) (30.94 pp avg.) | Improved |
| adapt random dropout rates to client capability | eFD vs FD · FEMNIST | accuracy: 4.59-9.04 pp (7.13 pp avg.) | Improved |
Closest papers by meaning
- FedAdaVR: Adaptive Variance Reduction for Robust Federated Learning under Limited Client Participation (NeurIPS 2026 · similarity 0.87)
- FedQS: Optimizing Gradient and Model Aggregation for Semi-Asynchronous Federated Learning (NeurIPS 2025 · similarity 0.87)
- Federated Learning with Heterogeneous LLMs: Integrating Small Student Client Models with a Large Hungry Model (AAAI 2025 · similarity 0.87)
- Federated Learning with Sample-level Client Drift Mitigation (AAAI 2025 · similarity 0.87)
- FedGPS: Statistical Rectification Against Data Heterogeneity in Federated Learning (NeurIPS 2025 · similarity 0.87)
- Recurrent Early Exits for Federated Learning with Heterogeneous Clients (ICML 2024 · 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.
