TLP-FSNC icon indicating copy to clipboard operation
TLP-FSNC copied to clipboard

Published 20 hours ago • verified publisher icon Zhen-Tan-dmml
→

Metadata

Pytorch Implementation of LoG 22 [Oral] -- Transductive Linear Probing: A Novel Framework for Few-Shot Node Classification

Transductive Linear Probing: A Novel Framework for Few-Shot Node Classification [LoG 2022] [Paper]

Dataset

[Pytorch Link]

Sufficient number of classes: A. CoraFull B. Coauthor-CS C. Ogbn-Arxiv

Insufficient number of classes: D. Cora E. CiteSeer, F. Amazon-Computer

Methods

Meta-learning

Full Paper List

Name Paper Original Code
MAML [ICML 2017] Model-agnostic Meta-learning for Fast Adaptation of Deep Networks PyTorch
ProtoNet [NeurIPS 2017] Prototypical Networks for Few-shot Learning PyTorch
Meta-GNN [CIKM 2019] Meta-GNN: On Few-shot Node Classification in Graph Meta-learning PyTorch
GPN [CIKM 2020] Graph Prototypical Networks for Few-shot Learning on Attributed Networks PyTorch
AMM-GNN [CIKM 2020] Graph Few-shot Learning with Attribute Matching [N/A]
G-Meta [NeurIPS 2020] Graph Meta Learning via Local Subgraphs PyTorch
TENT [SIGKDD 2022] Task-Adaptive Few-shot Node Classification PyTorch

Contrastive Learning for TLP

Full Paper List

Name Paper Original Code
FT-GNN [ECCV 2020] Rethinking few-shot image classification: a good embedding is all you need? PyTorch
MVGRL [ICML 2020] Contrastive Multi-View Representation Learning on Graphs PyTorch
GRACE [ICML 2020 Workshop] Deep Graph Contrastive Representation Learning PyTorch
GraphCL [NeurIPS 2020] Graph Contrastive Learning with Augmentations PyTorch
MERIT [IJCAI 2021] Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learning PyTorch
BGRL [ICLR 2022] LARGE-SCALE REPRESENTATION LEARNING ON GRAPHS VIA BOOTSTRAPPING PyTorch
SUGRL [AAAI 2022] Simple Unsupervised Graph Representation Learning PyTorch

Running Time on Cora

Methods MAML ProtoNet Meta-GNN GPN AMM-GNN G-Meta TENT MVGRL GraphCL Grace MERIT SUGRL
Time (s) 9.89 2.99 28.30 4.79 42.45 50.78 35.37 90.40 55.57 11.62 869.56 7.17

Citation

@inproceedings{tantransductive,
  title={Transductive Linear Probing: A Novel Framework for Few-Shot Node Classification},
  author={Tan, Zhen and Wang, Song and Ding, Kaize and Li, Jundong and Liu, Huan},
  booktitle={Learning on Graphs Conference}
}

← Metadata

15
Stars
1
Forks
Watchers

Owner

verified publisher icon Zhen-Tan-dmml

Metadata

Pytorch Implementation of LoG 22 [Oral] -- Transductive Linear Probing: A Novel Framework for Few-Shot Node Classification

Back