Research map / Federated learning and privacy / Personalized and heterogeneous FL
Federated Learning with Profile Mapping under Distribution Shifts and Drifts
Mohan Li, Dario Fenoglio, Martin Gjoreski, Marc Langheinrich
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 Feroma instead of best baseline CFL | federated aggregation · MNIST | accuracy: 76.6 -> 90.7 | Improved |
| use Feroma instead of CFL | federated aggregation · CIFAR-10 | accuracy: 33.9 -> 44.2 | Improved |
| use Feroma instead of FedEM | federated aggregation · CIFAR-100 | accuracy: 31.7 -> 39.9 | Improved |
| use Feroma instead of FedDrift | federated aggregation · CheXpert | accuracy: 72.3 -> 72.4 | No clear effect |
| use Feroma instead of FedDrift | federated aggregation · Office-Home | accuracy: 42.1 -> 42.4 | No clear effect |
| use Feroma instead of CFL under high non-IID, every-round drift | federated aggregation · MNIST high 20/20 | accuracy: 74.5 -> 90.8 | Improved |
| scale to 100 clients with Feroma instead of best baseline CFL | federated aggregation · MNIST 100 clients | accuracy: >10 pp over CFL | Improved |
Closest papers by meaning
- Federated Learning with Sample-level Client Drift Mitigation (AAAI 2025 · similarity 0.90)
- FLUX: Efficient Descriptor-Driven Clustered Federated Learning under Arbitrary Distribution Shifts (NeurIPS 2025 · similarity 0.90)
- An Aggregation-Free Federated Learning for Tackling Data Heterogeneity (CVPR 2024 · similarity 0.89)
- FedGPS: Statistical Rectification Against Data Heterogeneity in Federated Learning (NeurIPS 2025 · similarity 0.89)
- FedImpro: Measuring and Improving Client Update in Federated Learning (ICLR 2024 · similarity 0.88)
- FedQS: Optimizing Gradient and Model Aggregation for Semi-Asynchronous Federated Learning (NeurIPS 2025 · 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.
