Uniting Heterogeneity, Inductiveness, and Efficiency for Graph Representation Learning

Tong Chen, Hongzhi Yin, Jie Ren, Zi Huang, Xiangliang Zhang, Hao Wang

Research output: Contribution to journalArticlepeer-review

Abstract

Recently, bearing the message passing paradigm, graph neural networks(GNNs) have greatly advanced the performance of node representation learning on graphs. However, a majority class of GNNs are only designed for homogeneous graphs, leading to inferior adaptivity to the more informative heterogeneous graphs with various types of nodes and edges. Also, despite the necessity of inductively producing representations for completely new nodes (e.g., in streaming scenarios), few heterogeneous GNNs can bypass the transductive learning scheme where all nodes must be known during training. Furthermore, the training efficiency of most heterogeneous GNNs has been hindered by their sophisticated designs for extracting the semantics associated with each meta path or relation. In this paper, we propose a wide and deep message passing network (WIDEN) to cope with the aforementioned problems about heterogeneity, inductiveness, and efficiency that are rarely investigated together in graph representation learning. In WIDEN, we propose a novel inductive, meta path-free message passing scheme that packs up heterogeneous node features with their associated edges from both low- and high-order neighbor nodes. To further improve the training efficiency, we innovatively present an active down-sampling strategy that drops unimportant neighbor nodes to facilitate faster information propagation.
Original languageEnglish (US)
Pages (from-to)1-1
Number of pages1
JournalIEEE Transactions on Knowledge and Data Engineering
DOIs
StatePublished - Jul 27 2021

Fingerprint

Dive into the research topics of 'Uniting Heterogeneity, Inductiveness, and Efficiency for Graph Representation Learning'. Together they form a unique fingerprint.

Cite this