{"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/enhancing-network-embedding-with-auxiliary","title":"Enhancing Network Embedding with Auxiliary Information: An Explicit Matrix Factorization Perspective","arxiv_id":"1711.04094","date":"2017-11-11","proceeding":null,"authors":["Junliang Guo","Linli Xu","Xunpeng Huang","Enhong Chen"],"abstract":"Recent advances in the field of network embedding have shown the\nlow-dimensional network representation is playing a critical role in network\nanalysis. However, most of the existing principles of network embedding do not\nincorporate auxiliary information such as content and labels of nodes flexibly.\nIn this paper, we take a matrix factorization perspective of network embedding,\nand incorporate structure, content and label information of the network\nsimultaneously. For structure, we validate that the matrix we construct\npreserves high-order proximities of the network. Label information can be\nfurther integrated into the matrix via the process of random walk sampling to\nenhance the quality of embedding in an unsupervised manner, i.e., without\nleveraging downstream classifiers. In addition, we generalize the Skip-Gram\nNegative Sampling model to integrate the content of the network in a matrix\nfactorization framework. As a consequence, network embedding can be learned in\na unified framework integrating network structure and node content as well as\nlabel information simultaneously. We demonstrate the efficacy of the proposed\nmodel with the tasks of semi-supervised node classification and link prediction\non a variety of real-world benchmark network datasets.","url_abs":"http://arxiv.org/abs/1711.04094v2","url_pdf":"http://arxiv.org/pdf/1711.04094v2.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":"enhancing-network-embedding-with-auxiliary","repo_url":"https://github.com/lemmonation/APNE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"enhancing-network-embedding-with-auxiliary","repo_url":"https://github.com/lemmonation/G2-EMF","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"network-embedding","task_name":"Network Embedding"},{"task_slug":"node-classification","task_name":"Node Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}