Meta-Learning with Graph Neural Networks: Methods and Applications

2021-02-27 · Debmalya Mandal, Sourav Medya, Brian Uzzi, Charu Aggarwal

Graph Neural Networks (GNNs), a generalization of deep neural networks on graph data have been widely used in various domains, ranging from drug discovery to recommender systems. However, GNNs on such applications are limited when there are few available samples. Meta-learning has been an important framework to address the lack of samples in machine learning, and in recent years, researchers have started to apply meta-learning to GNNs. In this work, we provide a comprehensive survey of different meta-learning approaches involving GNNs on various graph problems showing the power of using these two approaches together. We categorize the literature based on proposed architectures, shared representations, and applications. Finally, we discuss several exciting future research directions and open problems.

📄 PDF Abstract BibTeX arXiv:2103.00137

Code (0)

등록된 구현이 없습니다.

Tasks

Drug Discovery Meta-Learning Recommendation Systems

MetaFill: Text Infilling for Meta-Path Generation on Heterogeneous Information Networks

2022-10-14 · Zequn Liu, Kefei Duan, Junwei Yang, Hanwen Xu 외

Heterogeneous Information Network (HIN) is essential to study complicated networks containing multiple edge types and node types. Meta-path, a sequence of node types and edge types, is the core technique to embed HINs. S…

Graph Embedding Language Modelling Link Prediction Node Classification+1

Robust Graph Meta-learning for Weakly-supervised Few-shot Node Classification

2021-06-12 · Kaize Ding, Jianling Wang, Jundong Li, James Caverlee 외

Graphs are widely used to model the relational structure of data, and the research of graph machine learning (ML) has a wide spectrum of applications ranging from drug design in molecular graphs to friendship recommendat…

Classification Drug Design Graph Learning Hallucination+3

Node Classification on Graphs with Few-Shot Novel Labels via Meta Transformed Network Embedding

2020-07-06 · NeurIPS 2020 12 · Lin Lan, Pinghui Wang, Xuefeng Du, Kaikai Song 외

We study the problem of node classification on graphs with few-shot novel labels, which has two distinctive properties: (1) There are novel labels to emerge in the graph; (2) The novel labels have only a few representati…

General Classification Graph structure learning Meta-Learning Network Embedding+2

SHGNN: Structure-Aware Heterogeneous Graph Neural Network

2021-12-12 · Wentao Xu, Yingce Xia, Weiqing Liu, Jiang Bian 외

Many real-world graphs (networks) are heterogeneous with different types of nodes and edges. Heterogeneous graph embedding, aiming at learning the low-dimensional node representations of a heterogeneous graph, is vital f…

Graph Embedding Graph Neural Network Node Classification

Supervised Graph Contrastive Learning for Few-shot Node Classification

2022-03-29 · Zhen Tan, Kaize Ding, Ruocheng Guo, Huan Liu

Graphs are present in many real-world applications, such as financial fraud detection, commercial recommendation, and social network analysis. But given the high cost of graph annotation or labeling, we face a severe gra…

Classification Contrastive Learning Data Augmentation Few-Shot Learning+3