Matching Models for Graph Retrieval

TL;DR

This paper reviews neural network methods for graph retrieval, focusing on similarity prediction and extending baseline models like the Shortest Path Kernel within a generalized random walk framework.

Contribution

It introduces a generalized approach to model graph similarity, extending the Shortest Path Kernel using product graph random walks.

Findings

Neural network approaches effectively predict graph similarity.

The generalized model improves upon traditional kernels.

Baseline methods are adapted within a new probabilistic framework.

Abstract

Graph Retrieval has witnessed continued interest and progress in the past few years. In thisreport, we focus on neural network based approaches for Graph matching and retrieving similargraphs from a corpus of graphs. We explore methods which can soft predict the similaritybetween two graphs. Later, we gauge the power of a particular baseline (Shortest Path Kernel)and try to model it in our product graph random walks setting while making it more generalised.