Research map / Federated learning and privacy / Communication-efficient FL
Federated Multi-Task Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 multi-task learning instead of a global model | SVM · Human Activity | prediction error: 2.23 (0.30) -> 0.46 (0.11) | Helped |
| Use multi-task learning instead of a local model | SVM · Human Activity | prediction error: 1.34 (0.21) -> 0.46 (0.11) | Helped |
| Use multi-task learning instead of a global model | SVM · Google Glass | prediction error: 5.34 (0.26) -> 2.02 (0.15) | Helped |
| Use multi-task learning instead of a local model | SVM · Google Glass | prediction error: 4.92 (0.26) -> 2.02 (0.15) | Helped |
| Use multi-task learning instead of a global model | SVM · Vehicle Sensor | prediction error: 13.4 (0.26) -> 6.59 (0.21) | Helped |
| Use multi-task learning instead of a local model | SVM · Vehicle Sensor | prediction error: 7.81 (0.13) -> 6.59 (0.21) | Helped |
| Allow per-node approximation levels to vary rather than using a fixed shared approximation (ablation) | MOCHA · Statistical heterogeneity simulations | performance | Helped |
| Use MOCHA's per-node approximation flexibility instead of fixed-parameter CoCoA | Distributed multi-task learning · Statistical heterogeneity simulations | performance | Helped |
| Allow devices to periodically drop updates (ablation) | MOCHA · Dropped-node simulations | performance | No clear effect |
| Have a node never send updates (ablation) | MOCHA · Dropped-node simulations | convergence | Hurt |
Closest papers by meaning
- FedHCA2: Towards Hetero-Client Federated Multi-Task Learning (CVPR 2024 · similarity 0.88)
- A Swiss Army Knife for Heterogeneous Federated Learning: Flexible Coupling via Trace Norm (NeurIPS 2024 · similarity 0.87)
- FedLPS: Heterogeneous Federated Learning for Multiple Tasks with Local Parameter Sharing (AAAI 2024 · similarity 0.86)
- WHALE-FL: Wireless and Heterogeneity Aware Latency Efficient Federated Learning over Mobile Devices via Adaptive Subnetwork Scheduling (AAAI 2025 · similarity 0.85)
- Towards Diverse Device Heterogeneous Federated Learning via Task Arithmetic Knowledge Integration (NeurIPS 2024 · similarity 0.85)
- FedECADO: A Dynamical System Model of Federated Learning (ICML 2025 · similarity 0.85)
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.