Research map / Federated learning and privacy / Communication-efficient FL
MAS: Towards Resource-Efficient Federated Multiple-Task Learning
Weiming Zhuang, Yonggang Wen, Lingjuan Lyu, Shuai Zhang
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 |
|---|---|---|---|
| merge FL tasks into one multi-task all-in-one model, then split by affinity | multiple simultaneous FL tasks · Taskonomy sdnkt | training time and energy: ~2x training time reduction, ~40% less energy | Improved |
| initialize each split from all-in-one model instead of from scratch (ablation) | MAS splits · Taskonomy sdnkt/erckt | total test loss: optimal split sdnkt-2: 0.622 -> 0.595 | Improved |
| use MAS affinity-based splitting instead of optimal split found by exhaustive search (ablation) | MAS · Taskonomy sdnkt (2 splits) | total test loss: 0.595 -> 0.578 | Improved |
| apply GradNorm or FedProx to all-in-one training | all-in-one FL · Taskonomy sdnkt | total test loss | No clear effect |
| increase number of splits (MAS-2 to MAS-3 to MAS-4) (ablation) | MAS · Taskonomy sdnkt | total test loss: 0.578 -> 0.555 (2 to 3 splits) | Improved |
| increase number of splits on nine-task set sdnkterca (ablation) | MAS · Taskonomy sdnkterca | total test loss | No clear effect |
| train all-in-one for R0 of 30 to 40 rounds before splitting (of 100) (ablation) | MAS · Taskonomy task sets | total test loss | Improved |
| increase local epochs E from 5 to 10 (ablation) | all-in-one FL · Taskonomy sdnkt | total test loss | No clear effect |
| increase selected clients K from 4 to 8 (ablation) | MAS-2 · Taskonomy sdnkt | total test loss: All-in-one 0.618 -> MAS-2 0.512 at K=8 | Improved |
| use HOA task grouping instead of MAS | task grouping · Taskonomy sdnkt | training time and energy: around 4-6x of ours | Hurt |
Closest papers by meaning
- FedLPS: Heterogeneous Federated Learning for Multiple Tasks with Local Parameter Sharing (AAAI 2024 · similarity 0.88)
- 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 0.88)
- FedQS: Optimizing Gradient and Model Aggregation for Semi-Asynchronous Federated Learning (NeurIPS 2025 · similarity 0.88)
- Revisiting Ensembling in One-Shot Federated Learning (NeurIPS 2024 · similarity 0.87)
- WHALE-FL: Wireless and Heterogeneity Aware Latency Efficient Federated Learning over Mobile Devices via Adaptive Subnetwork Scheduling (AAAI 2025 · similarity 0.87)
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.
