ABSTRACT
Meta-learning has received a tremendous recent attention as a possible approach for mimicking human intelligence, i.e., acquiring new knowledge and skills with little or even no demonstration. Most of the existing meta-learning methods are proposed to tackle few-shot learning problems such as image and text, in rather Euclidean domain. However, there are very few works applying meta-learning to non-Euclidean domains, and the recently proposed graph neural networks (GNNs) models do not perform effectively on graph few-shot learning problems. Towards this, we propose a novel graph meta-learning framework -- Meta-GNN -- to tackle the few-shot node classification problem in graph meta-learning settings. It obtains the prior knowledge of classifiers by training on many similar few-shot learning tasks and then classifies the nodes from new classes with only few labeled samples. Additionally, Meta-GNN is a general model that can be straightforwardly incorporated into any existing state-of-the-art GNN. Our experiments conducted on three benchmark datasets demonstrate that our proposed approach not only improves the node classification performance by a large margin on few-shot learning problems in meta-learning paradigm, but also learns a more general and flexible model for task adaption.
- Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-agnostic metalearning for fast adaptation of deep networks. In ICML.Google Scholar
- Aditya Grover and Jure Leskovec. 2016. node2vec: Scalable feature learning for networks. In KDD.Google Scholar
- Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. In NIPS.Google Scholar
- Thomas N Kipf and MaxWelling. 2017. Semi-supervised classification with graph convolutional networks. In ICLR.Google Scholar
- Qimai Li, Zhichao Han, and Xiao-Ming Wu. 2018. Deeper insights into graph convolutional networks for semi-supervised learning. In AAAI.Google Scholar
- Bryan Perozzi, Rami Al-Rfou, and Steven Skiena. 2014. Deepwalk: Online learning of social representations. In KDD.Google ScholarDigital Library
- Sachin Ravi and Hugo Larochelle. 2016. Optimization as a model for few-shot learning. In ICLR.Google Scholar
- Prithviraj Sen, Galileo Namata, Mustafa Bilgic, Lise Getoor, Brian Galligher, and Tina Eliassi-Rad. 2008. Collective classification in network data. AI magazine 29, 3 (2008), 93--93.Google Scholar
- Jake Snell, Kevin Swersky, and Richard Zemel. 2017. Prototypical networks for few-shot learning. In NIPS.Google Scholar
- Oriol Vinyals, Charles Blundell, Timothy Lillicrap, Daan Wierstra, et al. 2016. Matching networks for one shot learning. In NIPS.Google Scholar
- Felix Wu, Tianyi Zhang, Amauri Holanda Souza Jr., Christopher Fifty, Tao Yu, and Kilian Q. Weinberger. 2019. Simplifying Graph Convolutional Networks. In ICML.Google Scholar
- Zonghan Wu, Shirui Pan, Fengwen Chen, Guodong Long, Chengqi Zhang, and Philip S Yu. 2019. A Comprehensive Survey on Graph Neural Networks. arXiv.org (2019).Google Scholar
- Shengzhong Zhang, Ziang Zhou, Zengfeng Huang, and ZhongyuWei. 2018. Fewshot Classification on Graphs with Structural Regularized GCNs. arXiv preprint (2018).Google Scholar
Index Terms
- Meta-GNN: On Few-shot Node Classification in Graph Meta-learning
Recommendations
Task-Equivariant Graph Few-shot Learning
KDD '23: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data MiningAlthough 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 ...
Multimodal Graph Meta Contrastive Learning
CIKM '21: Proceedings of the 30th ACM International Conference on Information & Knowledge ManagementIn recent years, graph contrastive learning has achieved promising node classification accuracy using graph neural networks (GNNs), which can learn representations in an unsupervised manner. However, such representations cannot be generalized to unseen ...
Robust Graph Meta-Learning for Weakly Supervised Few-Shot Node Classification
Graph machine learning (Graph ML) models typically require abundant labeled instances to provide sufficient supervision signals, which is commonly infeasible in real-world scenarios since labeled data for newly emerged concepts (e.g., new categorizations ...
Comments