Research map / Optimization / Nonconvex and smooth optimization
DREAM: A Unified Framework for Drift-Corrected Federated Multi-Objective Learning
Yuan Zhou, Yidan Ou, Xinli Shi
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 |
|---|---|---|---|
| add the explicit control-variate correction (ablation) | DREAM · Multi-MNIST (K=40) | average accuracy: about 6% average accuracy drop without it | Improved |
| add momentum smoothing (gamma<1 instead of gamma=1) (ablation) | DREAM · Multi-MNIST | descent-direction norm stability and task weights | Improved |
| use DREAM instead of FSMGDA | CIFAR-100 fine/coarse · CIFAR-100 (i.i.d.) | test accuracy: +2.4% and +3.5% | Improved |
| use DREAM instead of FedAvg with fixed 0.5/0.5 weights | CIFAR-100 fine/coarse · CIFAR-100 (i.i.d.) | test accuracy: +2.6% and +4.3% | Improved |
| use DREAM instead of FSMGDA/FedCMOO as local steps K grow | Multi-MNIST · Multi-MNIST | average accuracy and task gap | Improved |
Closest papers by meaning
- Many-Objective Multi-Solution Transport (ICLR 2025 · similarity 0.85)
- Projection Optimization: A General Framework for Multi-Objective and Multi-Group RLHF (ICML 2025 · similarity 0.84)
- Co-Dream: Collaborative Dream Synthesis over Decentralized Models (AAAI 2025 · similarity 0.84)
- Federated Optimization with Doubly Regularized Drift Correction (ICML 2024 · similarity 0.84)
- A-FedPD: Aligning Dual-Drift is All Federated Primal-Dual Learning Needs (NeurIPS 2024 · similarity 0.83)
- MAdam: Metric-Aware Multi-Objective Adam (NeurIPS 2026 · similarity 0.83)
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.
