Deep graph similarity learning: a survey

DOI10.1007/S10618-020-00733-5MaRDI QIDQ2036720zbMATH OpenOpenAlexFDO

Authors Guixiang Ma, Nesreen K. Ahmed, Theodore L. Willke, Philip S. Yu

Publication date 30 June 2021

Published in Data Mining and Knowledge Discovery (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/1912.11615

zbMATH Keywords

deep graph similarity learninggraph convolutional networksgraph matchinggraph neural networksgraph similarityhigher-order networksmetric learningsimilarity learningstructural similarity

Mathematics Subject Classification ID

Small world graphs, complex networks (graph-theoretic aspects) (05C82) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Artificial neural networks and deep learning (68T07)

Abstract: In many domains where data are represented as graphs, learning a similarity metric among graphs is considered a key problem, which can further facilitate various learning tasks, such as classification, clustering, and similarity search. Recently, there has been an increasing interest in deep graph similarity learning, where the key idea is to learn a deep learning model that maps input graphs to a target space such that the distance in the target space approximates the structural distance in the input space. Here, we provide a comprehensive review of the existing literature of deep graph similarity learning. We propose a systematic taxonomy for the methods and applications. Finally, we discuss the challenges and future directions for this problem.

Recommendations

• A gentle introduction to deep learning for graphs
• Graph Kernels: State-of-the-Art and Future Challenges
• Representation learning for dynamic graphs: a survey
• Graph kernels: a survey
• Graph neural network

Cites work

• A graph distance metric based on the maximal common subgraph
• A kernel two-sample test
• Graph distances using graph union
• Graph isomorphism, general remarks
• Graph kernels
• Graph kernels based on tree patterns for molecules
• Graph Similarity and its Applications to Hardware Security
• scientific article; zbMATH DE number 3639144 (Why is no real title available?)
• Inexact graph matching for structural pattern recognition
• Nearest neighbor pattern classification
• Reducing the Dimensionality of Data with Neural Networks
• Speeding up graph edit distance computation through fast bipartite matching
• The earth mover's distance as a metric for image retrieval

Cited in

(6)

• A gentle introduction to deep learning for graphs
• Sim2vec: node similarity preserving network embedding
• Representation learning for dynamic graphs: a survey
• scientific article; zbMATH DE number 7626755 (Why is no real title available?)
• Graph representation learning for popularity prediction problem: A survey
• A comprehensive survey on deep graph representation learning methods

Describes a project that uses

Uses Software

• darch
• word2vec
• AFGen
• EMD
• FaceNet
• node2vec
• DeepWalk
• Colibri
• graph2vec
• GitHub

This page was built for publication: Deep graph similarity learning: a survey

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2036720)