Meta-GNN: Metagraph neural network for semi-supervised learning in Attributed Heterogeneous Information Networks

Aravind Sankar, Xinyang Zhang, Kevin Chen Chuan Chang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Heterogeneous Information Networks (HINs) comprise nodes of different types inter-connected through diverse semantic relationships. In many real-world applications, nodes in information networks are often associated with additional attributes, resulting in Attributed HINs (or AHINs). In this paper, we study semi-supervised learning (SSL) on AHINs to classify nodes based on their structure, node types and attributes, given limited supervision. Recently, Graph Convolutional Networks (GCNs) have achieved impressive results in several graph-based SSL tasks. However, they operate on homogeneous networks, while being completely agnostic to the semantics of typed nodes and relationships in real-world HINs. In this paper, we seek to bridge the gap between semantic-rich HINs and the neighborhood aggregation paradigm of graph neural networks, to generalize GCNs through metagraph semantics. We propose a novel metagraph convolution operation to extract features from local metagraph-structured neighborhoods, thus capturing semantic higher-order relationships in AHINs. Our proposed neural architecture Meta-GNN extracts features of diverse semantics by utilizing multiple metagraphs, and employs a novel metagraph-attention module to learn personalized metagraph preferences for each node. Our semi-supervised node classification experiments on multiple real-world AHIN datasets indicate significant performance gains of 6% Micro-F1 on average over state-of-the-art AHIN baselines. Visualizations on metagraph attention weights yield interpretable insights into their relative task-specific importance.

Original languageEnglish (US)
Title of host publicationProceedings of the 2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2019
EditorsFrancesca Spezzano, Wei Chen, Xiaokui Xiao
PublisherAssociation for Computing Machinery, Inc
Pages137-144
Number of pages8
ISBN (Electronic)9781450368681
DOIs
StatePublished - Aug 27 2019
Event11th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2019 - Vancouver, Canada
Duration: Aug 27 2019Aug 30 2019

Publication series

NameProceedings of the 2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2019

Conference

Conference11th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2019
CountryCanada
CityVancouver
Period8/27/198/30/19

ASJC Scopus subject areas

  • Communication
  • Computer Networks and Communications
  • Information Systems and Management
  • Sociology and Political Science

Fingerprint Dive into the research topics of 'Meta-GNN: Metagraph neural network for semi-supervised learning in Attributed Heterogeneous Information Networks'. Together they form a unique fingerprint.

  • Cite this

    Sankar, A., Zhang, X., & Chang, K. C. C. (2019). Meta-GNN: Metagraph neural network for semi-supervised learning in Attributed Heterogeneous Information Networks. In F. Spezzano, W. Chen, & X. Xiao (Eds.), Proceedings of the 2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2019 (pp. 137-144). (Proceedings of the 2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2019). Association for Computing Machinery, Inc. https://doi.org/10.1145/3341161.3342859