{"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/spectral-network-embedding-a-fast-and","title":"Spectral Network Embedding: A Fast and Scalable Method via Sparsity","arxiv_id":"1806.02623","date":"2018-06-07","proceeding":null,"authors":["Jie Zhang","Yan Wang","Jie Tang","Ming Ding"],"abstract":"Network embedding aims to learn low-dimensional representations of nodes in a\nnetwork, while the network structure and inherent properties are preserved. It\nhas attracted tremendous attention recently due to significant progress in\ndownstream network learning tasks, such as node classification, link\nprediction, and visualization. However, most existing network embedding methods\nsuffer from the expensive computations due to the large volume of networks. In\nthis paper, we propose a $10\\times \\sim 100\\times$ faster network embedding\nmethod, called Progle, by elegantly utilizing the sparsity property of online\nnetworks and spectral analysis. In Progle, we first construct a \\textit{sparse}\nproximity matrix and train the network embedding efficiently via sparse matrix\ndecomposition. Then we introduce a network propagation pattern via spectral\nanalysis to incorporate local and global structure information into the\nembedding. Besides, this model can be generalized to integrate network\ninformation into other insufficiently trained embeddings at speed. Benefiting\nfrom sparse spectral network embedding, our experiment on four different\ndatasets shows that Progle outperforms or is comparable to state-of-the-art\nunsupervised comparison approaches---DeepWalk, LINE, node2vec, GraRep, and\nHOPE, regarding accuracy, while is $10\\times$ faster than the fastest\nword2vec-based method. Finally, we validate the scalability of Progle both in\nreal large-scale networks and multiple scales of synthetic networks.","url_abs":"http://arxiv.org/abs/1806.02623v2","url_pdf":"http://arxiv.org/pdf/1806.02623v2.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":"spectral-network-embedding-a-fast-and","repo_url":"https://github.com/zxhhh97/ABot","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"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":[{"method_slug":"grarep","method_name":"GraRep"},{"method_slug":"node2vec","method_name":"node2vec"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}