Research map / Federated learning and privacy / Communication-efficient FL
Federated Block Coordinate Descent Scheme for Learning Global and Personalized Models
Ruiyuan Wu, Anna Scaglione, Hoi-To Wai, Nurullah Karakoc, Kari Hreinsson, Wing-Kin Ma
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 |
|---|---|---|---|
| Allow personalized edge models to deviate from the global model using a quadratic penalty | FedBCD and FedBCD-I · MNIST and CIFAR-10 | personalized test accuracy | Improved |
| Use FedBCD-I, which allows offline local training before the intermittent cloud adjustment | FedBCD · CIFAR-10 | personalized test accuracy | Improved |
| Use FedBCD-I, which allows offline local training before the intermittent cloud adjustment | FedBCD · CIFAR-10 | global test accuracy | No clear effect |
| Replace synchronous cloud aggregation with asynchronous first-available cloud-server aggregation | FedBCD · MNIST | runtime to improve model performance | Improved |
| Use asynchronous cloud updates | FedBCD-I · MNIST | runtime to reach global performance | Improved |
| Decrease the fraction of cloud servers participating in each update | Async-cloud FedBCD · MNIST | update progress per round | Hurt |
| Increase data-label diversity | FedBCD · MNIST | smoothness of global performance improvement | Improved |
| Use the rigorous asynchronous protocol, which performs isolated updates on servers outside the selected group (ablation) | Async-cloud FedBCD · FedBCD protocol comparison | performance | No clear effect |
| Allow local models to deviate from the global model rather than enforcing model consensus | FedBCD and FedBCD-I · MNIST and CIFAR-10 | global test accuracy | Mixed |
Closest papers by meaning
- Overcoming Data and Model heterogeneities in Decentralized Federated Learning via Synthetic Anchors (ICML 2024 · similarity 0.87)
- Efficient Asynchronous Federated Learning with Prospective Momentum Aggregation and Fine-Grained Correction (AAAI 2024 · similarity 0.87)
- Decentralized Directed Collaboration for Personalized Federated Learning (CVPR 2024 · similarity 0.87)
- Locally Estimated Global Perturbations are Better than Local Perturbations for Federated Sharpness-aware Minimization (ICML 2024 · similarity 0.87)
- FedASMU: Efficient Asynchronous Federated Learning with Dynamic Staleness-Aware Model Update (AAAI 2024 · similarity 0.86)
- Low Precision Local Training is Enough for Federated Learning (NeurIPS 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.
