{"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-resolution-parameters-for-graph","title":"Learning Resolution Parameters for Graph Clustering","arxiv_id":"1903.05246","date":"2019-03-12","proceeding":null,"authors":["Nate Veldt","David F. Gleich","Anthony Wirth"],"abstract":"Finding clusters of well-connected nodes in a graph is an extensively studied\nproblem in graph-based data analysis. Because of its many applications, a large\nnumber of distinct graph clustering objective functions and algorithms have\nalready been proposed and analyzed. To aid practitioners in determining the\nbest clustering approach to use in different applications, we present new\ntechniques for automatically learning how to set clustering resolution\nparameters. These parameters control the size and structure of communities that\nare formed by optimizing a generalized objective function. We begin by\nformalizing the notion of a parameter fitness function, which measures how well\na fixed input clustering approximately solves a generalized clustering\nobjective for a specific resolution parameter value. Under reasonable\nassumptions, which suit two key graph clustering applications, such a parameter\nfitness function can be efficiently minimized using a bisection-like method,\nyielding a resolution parameter that fits well with the example clustering. We\nview our framework as a type of single-shot hyperparameter tuning, as we are\nable to learn a good resolution parameter with just a single example. Our\ngeneral approach can be applied to learn resolution parameters for both local\nand global graph clustering objectives. We demonstrate its utility in several\nexperiments on real-world data where it is helpful to learn resolution\nparameters from a given example clustering.","url_abs":"http://arxiv.org/abs/1903.05246v1","url_pdf":"http://arxiv.org/pdf/1903.05246v1.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-resolution-parameters-for-graph","repo_url":"https://github.com/nveldt/LearnResParams","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"graph-clustering","task_name":"Graph Clustering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}