A random walk sampling on knowledge graphs for semantic-oriented statistical tasks

作者：

Highlights：

• We propose a semantic-aware sampling method on KG to collect high-quality samples.

• We present unbiased estimators to estimate the statistical results based on samples.

• We propose an optimized strategy to improve our semantic-aware sampling’s efficiency.

• We conduct extensive experiments to verify the superiority of our solution.

摘要

•We propose a semantic-aware sampling method on KG to collect high-quality samples.•We present unbiased estimators to estimate the statistical results based on samples.•We propose an optimized strategy to improve our semantic-aware sampling’s efficiency.•We conduct extensive experiments to verify the superiority of our solution.

论文关键词：Knowledge graph,Random walk sampling,Approximate estimation

论文评审过程：Received 1 September 2020, Revised 8 March 2022, Accepted 22 April 2022, Available online 5 May 2022, Version of Record 14 May 2022.

论文官网地址：https://doi.org/10.1016/j.datak.2022.102024