{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/verse-versatile-graph-embeddings-from","title":"VERSE: Versatile Graph Embeddings from Similarity Measures","arxiv_id":"1803.04742","date":"2018-03-13","proceeding":null,"authors":["Anton Tsitsulin","Davide Mottin","Panagiotis Karras","Emmanuel Müller"],"abstract":"Embedding a web-scale information network into a low-dimensional vector space\nfacilitates tasks such as link prediction, classification, and visualization.\nPast research has addressed the problem of extracting such embeddings by\nadopting methods from words to graphs, without defining a clearly\ncomprehensible graph-related objective. Yet, as we show, the objectives used in\npast works implicitly utilize similarity measures among graph nodes.\n  In this paper, we carry the similarity orientation of previous works to its\nlogical conclusion; we propose VERtex Similarity Embeddings (VERSE), a simple,\nversatile, and memory-efficient method that derives graph embeddings explicitly\ncalibrated to preserve the distributions of a selected vertex-to-vertex\nsimilarity measure. VERSE learns such embeddings by training a single-layer\nneural network. While its default, scalable version does so via sampling\nsimilarity information, we also develop a variant using the full information\nper vertex. Our experimental study on standard benchmarks and real-world\ndatasets demonstrates that VERSE, instantiated with diverse similarity\nmeasures, outperforms state-of-the-art methods in terms of precision and recall\nin major data mining tasks and supersedes them in time and space efficiency,\nwhile the scalable sampling-based variant achieves equally good results as the\nnon-scalable full variant.","url_abs":"http://arxiv.org/abs/1803.04742v1","url_pdf":"http://arxiv.org/pdf/1803.04742v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"verse-versatile-graph-embeddings-from","repo_url":"https://github.com/xgfs/verse","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"verse-versatile-graph-embeddings-from","repo_url":"https://github.com/SabanciParallelComputing/GOSH","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"link-prediction","task_name":"Link Prediction"}],"methods":[{"method_slug":"verse","method_name":"VERSE"}],"datasets_introduced":[],"methods_introduced":[{"slug":"verse","name":"VERSE","full_name":"VERtex Similarity Embeddings"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.04742","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.04742"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xgfs/verse","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SabanciParallelComputing/GOSH","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"bd991e8225982df2","entry":"is_numbers_only","repo":"xgfs/verse","repo_kind":"official","path":"python/convert.py","file_url":"https://github.com/xgfs/verse/blob/HEAD/python/convert.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bd991e8225982df2"}},{"code_sha256_prefix":"c1e8403eefddbb58","entry":"list2mat","repo":"xgfs/verse","repo_kind":"official","path":"python/convert.py","file_url":"https://github.com/xgfs/verse/blob/HEAD/python/convert.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c1e8403eefddbb58"}},{"code_sha256_prefix":"fd3226eebddacec2","entry":"mat2csr","repo":"xgfs/verse","repo_kind":"official","path":"python/convert.py","file_url":"https://github.com/xgfs/verse/blob/HEAD/python/convert.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fd3226eebddacec2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}