Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
LEARNING TO PROPAGATE LABELS: TRANSDUCTIVE PROPAGATION NETWORK FOR FEW-SHOT 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 learned transductive label propagation instead of the strongest listed baseline | few-shot classification · miniImageNet 5-way 1-shot | accuracy: 50.83 -> 53.75 | Helped |
| use learned transductive label propagation instead of the strongest listed baseline | few-shot classification · tieredImageNet 5-way 1-shot | accuracy: 54.48 -> 57.53 | Helped |
| train with more shots per episode (ablation) | TPN · miniImageNet 5-way 1-shot | accuracy: 53.75 -> 55.51 | Helped |
| train with more shots per episode (ablation) | TPN · tieredImageNet 5-way 1-shot | accuracy: 57.53 -> 59.91 | Helped |
| use iterative updates rather than the closed-form label propagation solution (ablation) | TPN · miniImageNet 5-way 1-shot | accuracy: 53.75 -> 53.05 | Hurt |
| use iterative updates rather than the closed-form label propagation solution (ablation) | TPN · miniImageNet 5-way 5-shot | accuracy: 69.43 -> 68.75 | Hurt |
| increase test query count while keeping training query count fixed at 15 (ablation) | TPN · miniImageNet 1-shot | accuracy: 52.29 -> 54.57 | Helped |
| vary training query count while holding test query count at 15 (ablation) | TPN · miniImageNet 1-shot | accuracy: 53.53 -> 53.75 -> 52.79 | No clear effect |
| apply TPN-semi instead of the best listed semi-supervised baseline | semi-supervised few-shot learning · miniImageNet 1-shot | accuracy: 50.41 -> 52.78 | Helped |
| apply TPN-semi instead of the best listed semi-supervised baseline | semi-supervised few-shot learning · tieredImageNet 1-shot w/D | accuracy: 51.38 -> 53.45 | Helped |
Closest papers by meaning
- Meta Propagation Networks for Graph Few-shot Semi-supervised Learning (AAAI 2022 · similarity 0.91)
- Learning to Propagate for Graph Meta-Learning (NeurIPS 2019 · similarity 0.90)
- Transductive Few-Shot Learning With Prototype-Based Label Propagation by Iterative Graph Refinement (CVPR 2023 · similarity 0.90)
- ECKPN: Explicit Class Knowledge Propagation Network for Transductive Few-Shot Learning (CVPR 2021 · similarity 0.90)
- Node Classification on Graphs with Few-Shot Novel Labels via Meta Transformed Network Embedding (NeurIPS 2020 · similarity 0.90)
- Label Propagation for Deep Semi-Supervised Learning (CVPR 2019 · similarity 0.89)
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.