{"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/billion-scale-network-embedding-with","title":"Billion-scale Network Embedding with Iterative Random Projection","arxiv_id":"1805.02396","date":"2018-05-07","proceeding":null,"authors":["Ziwei Zhang","Peng Cui","Haoyang Li","Xiao Wang","Wenwu Zhu"],"abstract":"Network embedding, which learns low-dimensional vector representation for\nnodes in the network, has attracted considerable research attention recently.\nHowever, the existing methods are incapable of handling billion-scale networks,\nbecause they are computationally expensive and, at the same time, difficult to\nbe accelerated by distributed computing schemes. To address these problems, we\npropose RandNE (Iterative Random Projection Network Embedding), a novel and\nsimple billion-scale network embedding method. Specifically, we propose a\nGaussian random projection approach to map the network into a low-dimensional\nembedding space while preserving the high-order proximities between nodes. To\nreduce the time complexity, we design an iterative projection procedure to\navoid the explicit calculation of the high-order proximities. Theoretical\nanalysis shows that our method is extremely efficient, and friendly to\ndistributed computing schemes without any communication cost in the\ncalculation. We also design a dynamic updating procedure which can efficiently\nincorporate the dynamic changes of the networks without error aggregation.\nExtensive experimental results demonstrate the efficiency and efficacy of\nRandNE over state-of-the-art methods in several tasks including network\nreconstruction, link prediction and node classification on multiple datasets\nwith different scales, ranging from thousands to billions of nodes and edges.","url_abs":"http://arxiv.org/abs/1805.02396v2","url_pdf":"http://arxiv.org/pdf/1805.02396v2.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":"billion-scale-network-embedding-with","repo_url":"https://github.com/ZW-ZHANG/RandNE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"billion-scale-network-embedding-with","repo_url":"https://github.com/benedekrozemberczki/karateclub","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"distributed-computing","task_name":"Distributed Computing"},{"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":{"atlas_url":"https://app.syntology.ai/?focus=1805.02396","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}