Survey on graph embeddings and their applications to machine learning problems on graphs
Dealing with relational data always required significant computational resources, domain expertise and task-dependent feature engineering to incorporate structural information into a predictive model. Nowadays, a family of automated graph feature engineering techniques has been proposed in different...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2021-02-01
|
| Series: | PeerJ Computer Science |
| Subjects: | |
| Online Access: | https://peerj.com/articles/cs-357.pdf |
| _version_ | 1818388072431091712 |
|---|---|
| author | Ilya Makarov Dmitrii Kiselev Nikita Nikitinsky Lovro Subelj |
| author_facet | Ilya Makarov Dmitrii Kiselev Nikita Nikitinsky Lovro Subelj |
| author_sort | Ilya Makarov |
| collection | DOAJ |
| description | Dealing with relational data always required significant computational resources, domain expertise and task-dependent feature engineering to incorporate structural information into a predictive model. Nowadays, a family of automated graph feature engineering techniques has been proposed in different streams of literature. So-called graph embeddings provide a powerful tool to construct vectorized feature spaces for graphs and their components, such as nodes, edges and subgraphs under preserving inner graph properties. Using the constructed feature spaces, many machine learning problems on graphs can be solved via standard frameworks suitable for vectorized feature representation. Our survey aims to describe the core concepts of graph embeddings and provide several taxonomies for their description. First, we start with the methodological approach and extract three types of graph embedding models based on matrix factorization, random-walks and deep learning approaches. Next, we describe how different types of networks impact the ability of models to incorporate structural and attributed data into a unified embedding. Going further, we perform a thorough evaluation of graph embedding applications to machine learning problems on graphs, among which are node classification, link prediction, clustering, visualization, compression, and a family of the whole graph embedding algorithms suitable for graph classification, similarity and alignment problems. Finally, we overview the existing applications of graph embeddings to computer science domains, formulate open problems and provide experiment results, explaining how different networks properties result in graph embeddings quality in the four classic machine learning problems on graphs, such as node classification, link prediction, clustering and graph visualization. As a result, our survey covers a new rapidly growing field of network feature engineering, presents an in-depth analysis of models based on network types, and overviews a wide range of applications to machine learning problems on graphs. |
| first_indexed | 2024-12-14T04:20:01Z |
| format | Article |
| id | doaj.art-9d029711dba842a5810a03899fc6127b |
| institution | Directory Open Access Journal |
| issn | 2376-5992 |
| language | English |
| last_indexed | 2024-12-14T04:20:01Z |
| publishDate | 2021-02-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ Computer Science |
| spelling | doaj.art-9d029711dba842a5810a03899fc6127b2022-12-21T23:17:23ZengPeerJ Inc.PeerJ Computer Science2376-59922021-02-017e35710.7717/peerj-cs.357Survey on graph embeddings and their applications to machine learning problems on graphsIlya Makarov0Dmitrii Kiselev1Nikita Nikitinsky2Lovro Subelj3HSE University, Moscow, RussiaHSE University, Moscow, RussiaBig Data Research Center, National University of Science and Technology MISIS, Moscow, RussiaFaculty of Computer and Information Science, University of Ljubljana, Ljubljana, SloveniaDealing with relational data always required significant computational resources, domain expertise and task-dependent feature engineering to incorporate structural information into a predictive model. Nowadays, a family of automated graph feature engineering techniques has been proposed in different streams of literature. So-called graph embeddings provide a powerful tool to construct vectorized feature spaces for graphs and their components, such as nodes, edges and subgraphs under preserving inner graph properties. Using the constructed feature spaces, many machine learning problems on graphs can be solved via standard frameworks suitable for vectorized feature representation. Our survey aims to describe the core concepts of graph embeddings and provide several taxonomies for their description. First, we start with the methodological approach and extract three types of graph embedding models based on matrix factorization, random-walks and deep learning approaches. Next, we describe how different types of networks impact the ability of models to incorporate structural and attributed data into a unified embedding. Going further, we perform a thorough evaluation of graph embedding applications to machine learning problems on graphs, among which are node classification, link prediction, clustering, visualization, compression, and a family of the whole graph embedding algorithms suitable for graph classification, similarity and alignment problems. Finally, we overview the existing applications of graph embeddings to computer science domains, formulate open problems and provide experiment results, explaining how different networks properties result in graph embeddings quality in the four classic machine learning problems on graphs, such as node classification, link prediction, clustering and graph visualization. As a result, our survey covers a new rapidly growing field of network feature engineering, presents an in-depth analysis of models based on network types, and overviews a wide range of applications to machine learning problems on graphs.https://peerj.com/articles/cs-357.pdfGraph embeddingKnowledge representationMachine learningNetwork scienceGeometric deep learningGraph neural networks |
| spellingShingle | Ilya Makarov Dmitrii Kiselev Nikita Nikitinsky Lovro Subelj Survey on graph embeddings and their applications to machine learning problems on graphs PeerJ Computer Science Graph embedding Knowledge representation Machine learning Network science Geometric deep learning Graph neural networks |
| title | Survey on graph embeddings and their applications to machine learning problems on graphs |
| title_full | Survey on graph embeddings and their applications to machine learning problems on graphs |
| title_fullStr | Survey on graph embeddings and their applications to machine learning problems on graphs |
| title_full_unstemmed | Survey on graph embeddings and their applications to machine learning problems on graphs |
| title_short | Survey on graph embeddings and their applications to machine learning problems on graphs |
| title_sort | survey on graph embeddings and their applications to machine learning problems on graphs |
| topic | Graph embedding Knowledge representation Machine learning Network science Geometric deep learning Graph neural networks |
| url | https://peerj.com/articles/cs-357.pdf |
| work_keys_str_mv | AT ilyamakarov surveyongraphembeddingsandtheirapplicationstomachinelearningproblemsongraphs AT dmitriikiselev surveyongraphembeddingsandtheirapplicationstomachinelearningproblemsongraphs AT nikitanikitinsky surveyongraphembeddingsandtheirapplicationstomachinelearningproblemsongraphs AT lovrosubelj surveyongraphembeddingsandtheirapplicationstomachinelearningproblemsongraphs |