{"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/outlier-aware-network-embedding-for","title":"Outlier Aware Network Embedding for Attributed Networks","arxiv_id":"1811.07609","date":"2018-11-19","proceeding":null,"authors":["Sambaran Bandyopadhyay","Lokesh N","M. N. Murty"],"abstract":"Attributed network embedding has received much interest from the research\ncommunity as most of the networks come with some content in each node, which is\nalso known as node attributes. Existing attributed network approaches work well\nwhen the network is consistent in structure and attributes, and nodes behave as\nexpected. But real world networks often have anomalous nodes. Typically these\noutliers, being relatively unexplainable, affect the embeddings of other nodes\nin the network. Thus all the downstream network mining tasks fail miserably in\nthe presence of such outliers. Hence an integrated approach to detect anomalies\nand reduce their overall effect on the network embedding is required.\n  Towards this end, we propose an unsupervised outlier aware network embedding\nalgorithm (ONE) for attributed networks, which minimizes the effect of the\noutlier nodes, and hence generates robust network embeddings. We align and\njointly optimize the loss functions coming from structure and attributes of the\nnetwork. To the best of our knowledge, this is the first generic network\nembedding approach which incorporates the effect of outliers for an attributed\nnetwork without any supervision. We experimented on publicly available real\nnetworks and manually planted different types of outliers to check the\nperformance of the proposed algorithm. Results demonstrate the superiority of\nour approach to detect the network outliers compared to the state-of-the-art\napproaches. We also consider different downstream machine learning applications\non networks to show the efficiency of ONE as a generic network embedding\ntechnique. The source code is made available at\nhttps://github.com/sambaranban/ONE.","url_abs":"http://arxiv.org/abs/1811.07609v1","url_pdf":"http://arxiv.org/pdf/1811.07609v1.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":"outlier-aware-network-embedding-for","repo_url":"https://github.com/sambaranban/ONE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"outlier-aware-network-embedding-for","repo_url":"https://github.com/Kaslanarian/SAGOD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"outlier-aware-network-embedding-for","repo_url":"https://github.com/pygod-team/pygod","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"network-embedding","task_name":"Network Embedding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.07609","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}