{"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/graphlet-count-estimation-via-convolutional","title":"Graphlet Count Estimation via Convolutional Neural Networks","arxiv_id":"1810.03078","date":"2018-10-07","proceeding":null,"authors":["Xutong Liu","Yu-Zhen Janice Chen","John C. S. Lui","Konstantin Avrachenkov"],"abstract":"Graphlets are defined as k-node connected induced subgraph patterns. For an\nundirected graph, 3-node graphlets include close triangle and open triangle.\nWhen k = 4, there are six types of graphlets, e.g., tailed-triangle and clique\nare two possible 4-node graphlets. The number of each graphlet, called graphlet\ncount, is a signature which characterizes the local network structure of a\ngiven graph. Graphlet count plays a prominent role in network analysis of many\nfields, most notably bioinformatics and social science.\n  However, computing exact graphlet count is inherently difficult and\ncomputational expensive because the number of graphlets grows exponentially\nlarge as the graph size and/or graphlet size k grow. To deal with this\ndifficulty, many sampling methods were proposed to estimate graphlet count with\nbounded error. Nevertheless, these methods require large number of samples to\nbe statistically reliable, which is still computationally demanding. Moreover,\nthey have to repeat laborious counting procedure even if a new graph is similar\nor exactly the same as previous studied graphs.\n  Intuitively, learning from historic graphs can make estimation more accurate\nand avoid many repetitive counting to reduce computational cost. Based on this\nidea, we propose a convolutional neural network (CNN) framework and two\npreprocessing techniques to estimate graphlet count. Extensive experiments on\ntwo types of random graphs and real world biochemistry graphs show that our\nframework can offer substantial speedup on estimating graphlet count of new\ngraphs with high accuracy.","url_abs":"http://arxiv.org/abs/1810.03078v1","url_pdf":"http://arxiv.org/pdf/1810.03078v1.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":"graphlet-count-estimation-via-convolutional","repo_url":"https://github.com/jjanicechen/GraphletCountEstimationCNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}