Heterogeneous Graph Sparsification for Efficient Representation Learning

• URL: http://arxiv.org/abs/2211.07518v1
• Date: Mon, 14 Nov 2022 16:47:06 GMT
• Title: Heterogeneous Graph Sparsification for Efficient Representation Learning
• Authors: Chandan Chunduru, Chun Jiang Zhu, Blake Gains, and Jinbo Bi
• Abstract summary: We develop sampling-based algorithms for constructing sparsifiers that are provably sparse and preserve important information in the original graphs. We have performed extensive experiments to confirm that the proposed method can improve time and space complexities of representation learning while achieving comparable, or even better performance in subsequent graph learning tasks.
• Score: 15.075580975708654
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Graph sparsification is a powerful tool to approximate an arbitrary graph and has been used in machine learning over homogeneous graphs. In heterogeneous graphs such as knowledge graphs, however, sparsification has not been systematically exploited to improve efficiency of learning tasks. In this work, we initiate the study on heterogeneous graph sparsification and develop sampling-based algorithms for constructing sparsifiers that are provably sparse and preserve important information in the original graphs. We have performed extensive experiments to confirm that the proposed method can improve time and space complexities of representation learning while achieving comparable, or even better performance in subsequent graph learning tasks based on the learned embedding.

Related papers

Err

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.