Research map / Federated learning and privacy / Communication-efficient FL
Federated Multi-Objective Learning
Haibo Yang, Zhuqing Liu, Jia Liu, Chaosheng Dong, Michinari Momma
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 |
|---|---|---|---|
| increase local update steps K from 1 to 20 (ablation) | FMGDA/FSMGDA · MultiMNIST i.i.d. Task L | communication rounds to 1e-2 loss: 82 -> 5 | Improved |
| increase local update steps K from 1 to 20 (ablation) | FMGDA/FSMGDA · MultiMNIST non-i.i.d. Task L | communication rounds to 1e-2 loss: 96 -> 6 | Improved |
| increase local update steps K from 1 to 20 (ablation) | FMGDA/FSMGDA · MultiMNIST non-i.i.d. Task R | communication rounds to 1e-2 loss: 82 -> 5 | Improved |
| increase local update steps K from 1 to 20 (ablation) | FMGDA/FSMGDA · MultiMNIST i.i.d. Task R | communication rounds to 1e-2 loss: 84 -> 5 | Improved |
| increase local steps K from 1 to 10 (ablation) | FMGDA/FSMGDA · MultiMNIST i.i.d. Task R | communication rounds to 1e-2 loss: 84 -> 9 | Improved |
| increase local steps K from 1 to 5 (ablation) | FMGDA/FSMGDA · MultiMNIST non-i.i.d. Task L | communication rounds to 1e-2 loss: 96 -> 24 | Improved |
| increase batch size from 16 to 256 (256 = full-batch FMGDA) (ablation) | FSMGDA · MultiMNIST non-i.i.d. training loss | convergence speed | Improved |
| federated FMGDA versus centralized MGD | FMGDA · MultiMNIST training loss after 100 rounds | training loss | No clear effect |
| federated FSMGDA versus centralized SMGD | FSMGDA · MultiMNIST training loss after 100 rounds | training loss | Hurt |
| more local steps K and larger batch size (ablation) | FMGDA/FSMGDA · River Flow (8 tasks) | normalized loss convergence | Improved |
Closest papers by meaning
- Many-Objective Multi-Solution Transport (ICLR 2025 · similarity 0.87)
- Voronoi-grid-based Pareto Front Learning and Its Application to Collaborative Federated Learning (ICML 2025 · similarity 0.86)
- FedRSPO+: A Heterogeneity-aware Algorithm for Decision-focused Federated Learning (NeurIPS 2026 · similarity 0.86)
- FedHCA2: Towards Hetero-Client Federated Multi-Task Learning (CVPR 2024 · similarity 0.85)
- A Doubly Recursive Stochastic Compositional Gradient Descent Method for Federated Multi-Level Compositional Optimization (ICML 2024 · similarity 0.85)
- FedLPS: Heterogeneous Federated Learning for Multiple Tasks with Local Parameter Sharing (AAAI 2024 · 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.
