{"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/learning-structural-node-embeddings-via","title":"Learning Structural Node Embeddings Via Diffusion Wavelets","arxiv_id":"1710.10321","date":"2017-10-27","proceeding":"KDD 2018 6","authors":["Claire Donnat","Marinka Zitnik","David Hallac","Jure Leskovec"],"abstract":"Nodes residing in different parts of a graph can have similar structural\nroles within their local network topology. The identification of such roles\nprovides key insight into the organization of networks and can be used for a\nvariety of machine learning tasks. However, learning structural representations\nof nodes is a challenging problem, and it has typically involved manually\nspecifying and tailoring topological features for each node. In this paper, we\ndevelop GraphWave, a method that represents each node's network neighborhood\nvia a low-dimensional embedding by leveraging heat wavelet diffusion patterns.\nInstead of training on hand-selected features, GraphWave learns these\nembeddings in an unsupervised way. We mathematically prove that nodes with\nsimilar network neighborhoods will have similar GraphWave embeddings even\nthough these nodes may reside in very different parts of the network, and our\nmethod scales linearly with the number of edges. Experiments in a variety of\ndifferent settings demonstrate GraphWave's real-world potential for capturing\nstructural roles in networks, and our approach outperforms existing\nstate-of-the-art baselines in every experiment, by as much as 137%.","url_abs":"http://arxiv.org/abs/1710.10321v4","url_pdf":"http://arxiv.org/pdf/1710.10321v4.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":"learning-structural-node-embeddings-via","repo_url":"https://github.com/benedekrozemberczki/GraphWaveMachine","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1710.10321","atlas_url":"https://app.syntology.ai/?focus=1710.10321","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}