Research map / Label-efficient and robust learning / Semi-supervised learning
Auxiliary Learning with Joint Task and Data Scheduling
Hong Chen, Xin Wang, Chaoyu Guan, Yue Liu, Wenwu Zhu
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 joint task-data scheduler (JTDS) over naive auxiliary learning | auxiliary learning on CUB · CUB fully supervised | Accuracy(%): +2.72 over STL (77.04 vs 73.86) | Improved |
| add joint task-data scheduler | auxiliary learning on CUB · CUB semi-supervised (20% labels) | Accuracy(%): +12.86 over STL (51.21 vs 38.35) | Improved |
| remove normalized loss term from scheduler (ablation) | JTDS · CUB corrupted ratio 0.6 | Accuracy(%): -6.46 (50.70 to 44.24) | Hurt |
| remove sample feature-prototype term from scheduler (ablation) | JTDS · CUB semi-supervised (20% labels) | Accuracy(%): -6.58 (51.21 to 44.63) | Hurt |
| restrict scheduler to per-task common weights (only task) (ablation) | JTDS · CUB fully supervised | Accuracy(%): -4.14 (72.90 vs 77.04) | Hurt |
| remove auxiliary tasks (train only on target with data scheduling) (ablation) | JTDS · CUB fully supervised | Accuracy(%): -1.57 (75.47 vs 77.04) | Hurt |
| naive per-sample learnable weights (N-JTDS) instead of parameter-efficient scheduler (ablation) | auxiliary learning on CUB with 312 attribute tasks · CUB fully supervised | Accuracy(%): -5.66 vs JTDS (71.38 vs 77.04) | Hurt |
| joint task-data scheduler vs grid/gradient-based auxiliary weighting on MovieLens-1M | auxiliary learning on MovieLens-1M · MovieLens-1M fully supervised | RMSE: 0.9087 vs 0.9112 STL (lower is better) | Improved |
| add joint task-data scheduler | auxiliary learning on CIFAR10 and CIFAR100 fully supervised · CIFAR10 and CIFAR100 fully supervised | Accuracy(%): CIFAR10 +0.99 over STL (72.59 vs 71.60); CIFAR100 +1.54 (75.68 vs 74.14) | Mixed |
| naive per-sample weights (N-JTDS) in supervised pet/CIFAR settings | auxiliary learning with few tasks · Pet fully supervised | Accuracy(%): N-JTDS 67.28 vs STL 61.45 | Improved |
Closest papers by meaning
- Joint Data-Task Generation for Auxiliary Learning (NeurIPS 2023 · similarity 0.88)
- Aux-NAS: Exploiting Auxiliary Labels with Negligibly Extra Inference Cost (ICLR 2024 · similarity 0.85)
- Joint-Task Regularization for Partially Labeled Multi-Task Learning (CVPR 2024 · similarity 0.83)
- Joint Scheduling of Causal Prompts and Tasks for Multi-Task Learning (CVPR 2025 · similarity 0.83)
- Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models (ICML 2024 · similarity 0.82)
- Towards Consistent Multi-Task Learning: Unlocking the Potential of Task-Specific Parameters (CVPR 2025 · similarity 0.82)
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.
