{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T11:48:02Z","timestamp":1753876082649,"version":"3.41.2"},"reference-count":32,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2024,2,21]],"date-time":"2024-02-21T00:00:00Z","timestamp":1708473600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"name":"Canadian Department of National Defense"},{"DOI":"10.13039\/501100000038","name":"NSERC","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,2,21]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>An embedding is a mapping from a set of nodes of a network into a real vector space. Embeddings can have various aims like capturing the underlying graph topology and structure, node-to-node relationship, or other relevant information about the graph, its subgraphs or nodes themselves. A practical challenge with using embeddings is that there are many available variants to choose from. Selecting a small set of most promising embeddings from the long list of possible options for a given task is challenging and often requires domain expertise. Embeddings can be categorized into two main types: classical embeddings and structural embeddings. Classical embeddings focus on learning both local and global proximity of nodes, while structural embeddings learn information specifically about the local structure of nodes\u2019 neighbourhood. For classical node embeddings, there exists a framework which helps data scientists to identify (in an unsupervised way) a few embeddings that are worth further investigation. Unfortunately, no such framework exists for structural embeddings. In this article, we propose a framework for unsupervised ranking of structural graph embeddings. The proposed framework, apart from assigning an aggregate quality score for a structural embedding, additionally gives a data scientist insights into properties of this embedding. It produces information which predefined node features the embedding learns, how well it learns them, and which dimensions in the embedded space represent the predefined node features. Using this information, the user gets a level of explainability to an otherwise complex black-box embedding algorithm.<\/jats:p>","DOI":"10.1093\/comnet\/cnae003","type":"journal-article","created":{"date-parts":[[2024,2,23]],"date-time":"2024-02-23T00:05:22Z","timestamp":1708646722000},"source":"Crossref","is-referenced-by-count":1,"title":["Unsupervised framework for evaluating and explaining structural node embeddings of graphs"],"prefix":"10.1093","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-5032-4720","authenticated-orcid":false,"given":"Ashkan","family":"Dehghan","sequence":"first","affiliation":[{"name":"Department of Mathematics, Toronto Metropolitan University , 350 Victoria Street , Toronto, ON M5B 2K3, Canada"}]},{"given":"Kinga","family":"Siuta","sequence":"additional","affiliation":[{"name":"Department of Mathematics, Toronto Metropolitan University , 350 Victoria Street , Toronto, ON M5B 2K3, Canada"},{"name":"SGH Warsaw School of Economics , al. Niepodleg\u0142o\u015bci 162 , 02-554 Warszawa, Poland"}]},{"given":"Agata","family":"Skorupka","sequence":"additional","affiliation":[{"name":"Department of Mathematics, Toronto Metropolitan University , 350 Victoria Street , Toronto, ON M5B 2K3, Canada"},{"name":"SGH Warsaw School of Economics , al. Niepodleg\u0142o\u015bci 162 , 02-554 Warszawa, Poland"}]},{"given":"Andrei","family":"Betlen","sequence":"additional","affiliation":[{"name":"Patagona Technologies , Pickering, ON, Canada"}]},{"given":"David","family":"Miller","sequence":"additional","affiliation":[{"name":"Patagona Technologies , Pickering, ON, Canada"}]},{"given":"Bogumi\u0142","family":"Kami\u0144ski","sequence":"additional","affiliation":[{"name":"SGH Warsaw School of Economics , al. Niepodleg\u0142o\u015bci 162 , 02-554 Warszawa, Poland"}]},{"given":"Pawe\u0142","family":"Pra\u0142at","sequence":"additional","affiliation":[{"name":"Department of Mathematics, Toronto Metropolitan University , 350 Victoria Street , Toronto, ON M5B 2K3, Canada"}]}],"member":"286","published-online":{"date-parts":[[2024,2,22]]},"reference":[{"year":"2013","author":"Mikolov","key":"2024022300051527600_cnae003-B1"},{"first-page":"13","year":"2000","author":"Neville","key":"2024022300051527600_cnae003-B2"},{"key":"2024022300051527600_cnae003-B3","doi-asserted-by":"crossref","first-page":"626","DOI":"10.1007\/s10618-014-0365-y","article-title":"Graph based anomaly detection and description: a survey","volume":"29","author":"Akoglu","year":"2015","journal-title":"Data Min. Knowl. Discov"},{"key":"2024022300051527600_cnae003-B4","first-page":"243","volume-title":"A survey of link prediction in social networks. Social Network Data Analytics","author":"Al Hasan","year":"2011"},{"first-page":"221","year":"2023","author":"Pankratz","key":"2024022300051527600_cnae003-B5"},{"first-page":"1","year":"2022","author":"Chami","key":"2024022300051527600_cnae003-B6"},{"year":"2017","author":"Hamilton","key":"2024022300051527600_cnae003-B7"},{"volume-title":"Machine Learning in Social Networks: Embedding Nodes, Edges, Communities, and Graphs","year":"2020","author":"Aggarwal","key":"2024022300051527600_cnae003-B8"},{"volume-title":"Mining Complex Networks","year":"2022","author":"Kami\u0144ski","key":"2024022300051527600_cnae003-B9"},{"first-page":"388","year":"2022","author":"Stolman","key":"2024022300051527600_cnae003-B10"},{"first-page":"1231","year":"2012","author":"Henderson","key":"2024022300051527600_cnae003-B11"},{"first-page":"385","year":"2017","author":"Ribeiro","key":"2024022300051527600_cnae003-B12"},{"first-page":"1320","year":"2018","author":"Donnat","key":"2024022300051527600_cnae003-B13"},{"year":"2018","author":"Ahmed","key":"2024022300051527600_cnae003-B14"},{"key":"2024022300051527600_cnae003-B15","doi-asserted-by":"crossref","first-page":"cnac030","DOI":"10.1093\/comnet\/cnac030","article-title":"Evaluating node embeddings of complex networks","volume":"10","author":"Dehghan-Kooshkghazi","year":"2022","journal-title":"J. Complex Netw"},{"key":"2024022300051527600_cnae003-B16","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1017\/nws.2022.27","article-title":"A multi-purposed unsupervised framework for comparing embeddings of undirected and directed graphs","volume":"10","author":"Kami\u0144ski","year":"2022","journal-title":"Netw. Sci"},{"key":"2024022300051527600_cnae003-B17","doi-asserted-by":"crossref","first-page":"cnz043","DOI":"10.1093\/comnet\/cnz043","article-title":"An unsupervised framework for comparing graph embeddings","volume":"8","author":"Kami\u0144ski","year":"2020","journal-title":"J. Complex Netw"},{"first-page":"52","year":"2020","author":"Kami\u0144ski","key":"2024022300051527600_cnae003-B18"},{"year":"2023","author":"Dehghan","key":"2024022300051527600_cnae003-B19"},{"first-page":"483","year":"2020","author":"Rossi","key":"2024022300051527600_cnae003-B20"},{"key":"2024022300051527600_cnae003-B21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2518176","article-title":"Scalable and axiomatic ranking of network role similarity","volume":"8","author":"Jin","year":"2014","journal-title":"ACM Trans. Knowl. Discov. Data"},{"key":"2024022300051527600_cnae003-B22","doi-asserted-by":"crossref","first-page":"1112","DOI":"10.1109\/TKDE.2014.2349913","article-title":"Role discovery in networks","volume":"27","author":"Rossi","year":"2015","journal-title":"IEEE Trans. Knowl. Data Eng"},{"first-page":"1225","year":"2016","author":"Wang","key":"2024022300051527600_cnae003-B23"},{"key":"2024022300051527600_cnae003-B24","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3397191","article-title":"On proximity and structural role-based embeddings in networks: misconceptions, techniques, and applications","volume":"14","author":"Rossi","year":"2020","journal-title":"ACM Trans. Knowl. Discov. Data"},{"first-page":"333","year":"2018","author":"Kumar","key":"2024022300051527600_cnae003-B25"},{"first-page":"221","year":"2016","author":"Kumar","key":"2024022300051527600_cnae003-B26"},{"year":"2022","author":"Dehghan","key":"2024022300051527600_cnae003-B27"},{"first-page":"855","year":"2016","author":"Grover","key":"2024022300051527600_cnae003-B28"},{"first-page":"701","year":"2014","author":"Perozzi","key":"2024022300051527600_cnae003-B29"},{"year":"2021","author":"Rozemberczki","key":"2024022300051527600_cnae003-B30"},{"key":"2024022300051527600_cnae003-B31","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1016\/j.socnet.2020.02.001","article-title":"Unpacking Burt\u2019s constraint measure","volume":"62","author":"Everett","year":"2020","journal-title":"Soc. Netw"},{"key":"2024022300051527600_cnae003-B32","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1609\/icwsm.v3i1.13937","article-title":"Gephi: an open source software for exploring and manipulating networks","volume":"3","author":"Bastian","year":"2009","journal-title":"Proceedings of the international AAAI conference on web and social media"}],"container-title":["Journal of Complex Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/comnet\/article-pdf\/12\/2\/cnae003\/56744816\/cnae003.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/comnet\/article-pdf\/12\/2\/cnae003\/56744816\/cnae003.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,23]],"date-time":"2024-02-23T00:05:34Z","timestamp":1708646734000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/comnet\/article\/doi\/10.1093\/comnet\/cnae003\/7612927"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,21]]},"references-count":32,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,2,21]]}},"URL":"https:\/\/doi.org\/10.1093\/comnet\/cnae003","relation":{},"ISSN":["2051-1329"],"issn-type":[{"type":"electronic","value":"2051-1329"}],"subject":[],"published-other":{"date-parts":[[2024,4,1]]},"published":{"date-parts":[[2024,2,21]]},"article-number":"cnae003"}}