Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Graph Attention Prototypical Network for Robust Few-Shot Classification
Tingyun Liu, Licheng Liu, Qibin Zhang, Qiying Feng, C. L. Philip Chen
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 pseudo-label guided graph constructor and edge-aware graph attention (ablation) | GAPNet · CIFAR-FS clean | accuracy (%): 65.96 -> 75.71 | Improved |
| add pseudo-label guided graph constructor and edge-aware graph attention (ablation) | GAPNet · CIFAR-FS 40% OOE noise | accuracy (%): 53.34 -> 67.91 | Improved |
| add group attention broad learning module (ablation) | GAPNet · clean datasets | accuracy (%) | Improved |
| add adaptive noise-robust prototype generator (ablation) | GAPNet · noisy and clean settings | accuracy (%) | Improved |
| add SE block after ConvNet-4 (ablation) | GAPNet · noisy and clean settings | accuracy (%) | No clear effect |
| increase prototype contrastive weight lambda from 0.01 to 0.1 or 1 (ablation) | GAPNet · few-shot classification | accuracy (%) | Hurt |
| set fixed node rate above 0.5 in GABL (ablation) | GAPNet · few-shot classification | accuracy (%) | Hurt |
| use 5 intra-class and inter-class nearest neighbours (ablation) | GAPNet · few-shot classification | accuracy (%) | Improved |
| use GAPNet with same backbone and mean prototype as ProtoNet | GAPNet · miniImageNet 40% in-episode noise | accuracy (%): 40.57 -> 47.33 | Improved |
Closest papers by meaning
- FEW-SHOT LEARNING ON GRAPHS VIA SUPER-CLASSES BASED ON GRAPH SPECTRAL MEASURES (ICLR 2020 · similarity 0.89)
- Prototypical Networks for Few-shot Learning (NeurIPS 2017 · similarity 0.88)
- Cross-Domain Few-Shot Graph Classification (AAAI 2022 · similarity 0.87)
- Cross Attention Network for Few-shot Classification (NeurIPS 2019 · similarity 0.87)
- Fast Graph Sharpness-Aware Minimization for Enhancing and Accelerating Few-Shot Node Classification (NeurIPS 2024 · similarity 0.86)
- Graph Attention is Not Always Beneficial: A Theoretical Analysis of Graph Attention Mechanisms via Contextual Stochastic Block Models (ICML 2025 · similarity 0.86)
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.
