Graph Matching Networks for Learning the Similarity of Graph Structured Objects

04/29/2019
by   Yujia Li, et al.
8

This paper addresses the challenging problem of retrieval and matching of graph structured objects, and makes two key contributions. First, we demonstrate how Graph Neural Networks (GNN), which have emerged as an effective model for various supervised prediction problems defined on structured data, can be trained to produce embedding of graphs in vector spaces that enables efficient similarity reasoning. Second, we propose a novel Graph Matching Network model that, given a pair of graphs as input, computes a similarity score between them by jointly reasoning on the pair through a new cross-graph attention-based matching mechanism. We demonstrate the effectiveness of our models on different domains including the challenging problem of control-flow-graph based function similarity search that plays an important role in the detection of vulnerabilities in software systems. The experimental analysis demonstrates that our models are not only able to exploit structure in the context of similarity learning but they can also outperform domain-specific baseline systems that have been carefully hand-engineered for these problems.

READ FULL TEXT

page 1

page 2

page 3

page 4

07/08/2020

Hierarchical Graph Matching Networks for Deep Graph Similarity Learning

While the celebrated graph neural networks yield effective representatio...
10/23/2018

Convolutional Set Matching for Graph Similarity

We introduce GSimCNN (Graph Similarity Computation via Convolutional Neu...
07/26/2020

funcGNN: A Graph Neural Network Approach to Program Similarity

Program similarity is a fundamental concept, central to the solution of ...
11/11/2019

A Contextual Hierarchical Graph Model for Generating Random Sequences of Objects with Application to Music Playlists

Recommending the right content in large scale multimedia streaming servi...
09/19/2021

Property-based Entity Type Graph Matching

We are interested in dealing with the heterogeneity of Knowledge bases (...
07/30/2021

Artist Similarity with Graph Neural Networks

Artist similarity plays an important role in organizing, understanding, ...
11/01/2021

Heterogeneous Graph Neural Networks for Large-Scale Bid Keyword Matching

Digital advertising is a critical part of many e-commerce platforms such...

Code Repositories

Graph-Matching-Networks

PyTorch implementation of Graph Matching Networks for Learning the Similarity of Graph Structured Objects (ICML 2019).


view repo

tfGMN

Graph Matching Networks for Learning the Similarity of Graph Structured Objects


view repo

Graph-Matching-Networks-PyTorch

This is a **reimplementation** of the ICLR 2019 paper "Graph Matching Networks for Learning the Similarity of Graph Structured Objects" (Li et al.) in PyTorch.


view repo