A hybrid reproducing graph kernel based on information entropy

作者：

Highlights：

• We prove the H1-reproducing graph kernel satisfies the condition of Mercer kernel.

• We propose a novel reproducing graph kernel based on approximated von Neumann entropy.

• We propose a novel reproducing graph kernel based on Shannon entropy.

• We propose a hybrid reproducing graph kernel based on information entropy.

• We demonstrate the effectiveness of the proposed hybrid reproducing graph kernel.

摘要

•We prove the H1-reproducing graph kernel satisfies the condition of Mercer kernel.•We propose a novel reproducing graph kernel based on approximated von Neumann entropy.•We propose a novel reproducing graph kernel based on Shannon entropy.•We propose a hybrid reproducing graph kernel based on information entropy.•We demonstrate the effectiveness of the proposed hybrid reproducing graph kernel.

论文关键词：Differential operator,Reproducing kernel,Information entropy,Graph kernel,Graph classification

论文评审过程：Received 18 August 2016, Revised 18 June 2017, Accepted 26 July 2017, Available online 27 July 2017, Version of Record 18 September 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.07.025