Research map / Learning theory and algorithms / Combinatorial and search optimization
Self-Paced 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 self-paced selection of both tasks and instances instead of treating them equally | SPMTL · Toy dataset, OHSUMED, and Isolet | rMSE | Helped |
| Use self-paced selection of both tasks and instances instead of treating them equally | SPMTL · Toy dataset, OHSUMED, and Isolet | nMSE | Helped |
| Add instance-level easy-to-hard weighting (set γ=0) (ablation) | SPMTL · Toy dataset, 15% train | prediction performance | Helped |
| Add task-level easy-to-hard weighting alongside instance-level weighting (ablation) | SPIWL · Toy dataset, 15% train | prediction performance | Helped |
Closest papers by meaning
- AdaMerging: Adaptive Model Merging for Multi-Task Learning (ICLR 2024 · similarity 0.85)
- Towards Principled Task Grouping for Multi-Task Learning (NeurIPS 2026 · similarity 0.85)
- Quantifying Task Priority for Multi-Task Optimization (CVPR 2024 · similarity 0.85)
- Amalgamating Multi-Task Models with Heterogeneous Architectures (AAAI 2024 · similarity 0.84)
- Hard Tasks First: Multi-Task Reinforcement Learning Through Task Scheduling (ICML 2024 · similarity 0.84)
- DMTG: One-Shot Differentiable Multi-Task Grouping (ICML 2024 · similarity 0.84)
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.