{"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/global-vectors-for-node-representations","title":"Global Vectors for Node Representations","arxiv_id":"1902.11004","date":"2019-02-28","proceeding":null,"authors":["Robin Brochier","Adrien Guille","Julien Velcin"],"abstract":"Most network embedding algorithms consist in measuring co-occurrences of\nnodes via random walks then learning the embeddings using Skip-Gram with\nNegative Sampling. While it has proven to be a relevant choice, there are\nalternatives, such as GloVe, which has not been investigated yet for network\nembedding. Even though SGNS better handles non co-occurrence than GloVe, it has\na worse time-complexity. In this paper, we propose a matrix factorization\napproach for network embedding, inspired by GloVe, that better handles non\nco-occurrence with a competitive time-complexity. We also show how to extend\nthis model to deal with networks where nodes are documents, by simultaneously\nlearning word, node and document representations. Quantitative evaluations show\nthat our model achieves state-of-the-art performance, while not being so\nsensitive to the choice of hyper-parameters. Qualitatively speaking, we show\nhow our model helps exploring a network of documents by generating\ncomplementary network-oriented and content-oriented keywords.","url_abs":"http://arxiv.org/abs/1902.11004v1","url_pdf":"http://arxiv.org/pdf/1902.11004v1.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":"global-vectors-for-node-representations","repo_url":"https://github.com/brochier/gvnr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"network-embedding","task_name":"Network Embedding"}],"methods":[{"method_slug":"glove","method_name":"GloVe"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.11004","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}