HG-Meta: Graph Meta-learning over Heterogeneous Graphs

Qiannan Zhang*, Xiaodong Wu*, Qiang Yang*, Chuxu Zhang*, Xiangliang Zhang

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

6 Scopus citations


Prevailing supervised graph neural networks suffer from potential performance degradation in the label sparsity case. Though increasing attention has been paid to graph few-shot learning methods for learning effective graph embeddings under the scarcity of labeled data, most existing works study homogeneous graphs while ignoring the ubiquitousness of heterogeneous graphs (HG), where multi-typed nodes are interconnected by multi-typed edges. To this end, we propose to tackle few-shot learning on HG and develop a novel model for Heterogeneous Graph Meta-learning (a.k.a. HG-Meta). Regarding the graph heterogeneity, HG-Meta firstly builds a graph encoder to aggregate heterogeneous neighbors information from multiple semantic contexts (generated by meta-paths). Secondly, to train the graph encoder with meta-learning in a few-shot scenario, HG-Meta tackles meta-task differences produced from meta-task sampling procedure on HG with a task feature scaling module and a degree based task attention module. To further alleviate low-data problem, HG-Meta leverages unlabelled information in HG with auxiliary self-supervised learning task alongside the meta-optimization process to facilitate node embedding. Extensive experiments on two HG datasets demonstrate that HG-Meta outperforms state-of-the-art methods for multiple few-shot node classification tasks.

Original languageEnglish (US)
Title of host publicationProceedings of the 2022 SIAM International Conference on Data Mining, SDM 2022
PublisherSociety for Industrial and Applied Mathematics Publications
Number of pages9
ISBN (Electronic)9781611977172
StatePublished - 2022
Event2022 SIAM International Conference on Data Mining, SDM 2022 - Virtual, Online
Duration: Apr 28 2022Apr 30 2022

Publication series

NameProceedings of the 2022 SIAM International Conference on Data Mining, SDM 2022


Conference2022 SIAM International Conference on Data Mining, SDM 2022
CityVirtual, Online

Bibliographical note

Publisher Copyright:
Copyright © 2022 by SIAM.

ASJC Scopus subject areas

  • Computer Science Applications
  • Software


Dive into the research topics of 'HG-Meta: Graph Meta-learning over Heterogeneous Graphs'. Together they form a unique fingerprint.

Cite this