sung-won-kim / TEG

The official source code for Task-Equivariant Graph Few-shot Learning (TEG) at KDD 2023.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Task-Equivariant Graph Few-shot Learning (TEG)

The official source code for Task-Equivariant Graph Few-shot Learning at KDD 2023.

Abstract

Although Graph Neural Networks (GNNs) have been successful in node classification tasks, their performance heavily relies on the availability of a sufficient number of labeled nodes per class. In real-world situations, not all classes have many labeled nodes and there may be instances where the model needs to classify new classes, making manual labeling difficult. To solve this problem, it is important for GNNs to be able to classify nodes with a limited number of labeled nodes, known as few-shot node classification. Previous episodic meta-learning based methods have demonstrated success in few-shot node classification, but our findings suggest that optimal performance can only be achieved with a substantial amount of diverse training meta-tasks. To address this challenge of meta-learning based few-shot learning (FSL), we propose a new approach, the Task-Equivariant Graph few-shot learning (TEG) framework. Our TEG framework enables the model to learn transferable task-adaptation strategies using a limited number of training meta-tasks, allowing it to acquire meta-knowledge for a wide range of meta-tasks. By incorporating equivariant neural networks, TEG can utilize these strengths to learn highly adaptable task-specific strategies. As a result, TEG achieves state-of-the-art performance with limited training meta-tasks. Our experiments on various benchmark datasets demonstrate TEG's superiority in terms of accuracy and generalization ability, even when using minimal meta-training data, highlighting the effectiveness of our proposed approach in addressing the challenges of meta-learning based few-shot node classification.

image

Requirements

  • python=3.8.13
  • pytorch=1.10.1
  • numpy=1.23.4
  • torch-geometric=2.0.3

Datasets

You can download the datasets, including Amazon Clothing, Amazon Electronics, CoraFull, Coauthor-CS, DBLP, and OGBN-arxiv, using the following link:
Download datasets

After extracting dataset.zip, put the dataset folder in the same directory as the main.py file.

How to run

python main.py --dataset corafull --way 5 --shot 3

Flags

dataset : Amazon_clothing, Amazon_electronics, corafull, dblp, coauthorCS, ogbn-arxiv
way : N-way
shot : K-shot
qry : M-query

Citation

@article{kim2023task,
  title={Task-Equivariant Graph Few-shot Learning},
  author={Kim, Sungwon and Lee, Junseok and Lee, Namkyeong and Kim, Wonjoong and Choi, Seungyoon and Park, Chanyoung},
  journal={arXiv preprint arXiv:2305.18758},
  year={2023}
}

About

The official source code for Task-Equivariant Graph Few-shot Learning (TEG) at KDD 2023.

License:MIT License


Languages

Language:Python 100.0%