[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82718-en":3,"doc-seo-82718-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},82718,4810365810221,"Aurora","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Scalable Maximal Frequent Episode Mining with Desbordante","Episode mining extracts event subsequences with distinctive properties that can be treated as useful facts. Maximal frequent episode mining targets frequently appearing subsequences that are not contained in any other larger frequent subsequence, improving usability over exhaustive frequent episode lists. The MaxFEM method accelerates search using pruning but becomes impractical as minsup decreases or subsequence length increases. The work presents a high-performance C++ reimplementation plus parallelization, yielding ParMaxFEM and integration into Desbordante.","Scalable Maximal Frequent Episode Mining with  \nDesbordante  \nMaxim Ivanov 1 , Matvei Smirnov 1 , Alisa Strazdina 1 , George Chernishev 1, 2  \n1Desbordante Team  \nSaint Petersburg, Russia  \n2 Saint Petersburg State University  \nSaint Petersburg, Russia  \n{maxxim.s.ivanovv, matvei.mik.smirnov, alisastrazdina, [chernishev](chernishev}@gmail.com)[}](chernishev}@gmail.com)[@gmail.com](chernishev}@gmail.com)  \narXiv :2607 .03 188v 1 [ cs .DB] 3 Jul 2026  \nAbstract—Episode mining aims to extract subsequences of events that possess certain distinctive properties and constitute facts valuable to the user. Maximal frequent episode mining concentrates on discovery of frequently-appearing subsequences, which are not included into any other larger frequent subsequence. The state-of-the-art for this problem is the MaxFEM algorithm which enumerates possible subsequences, while applying various pruning techniques to accelerate the search.  \nHowever, this is a computationally-intensive problem: reducing the minimum number of required subsequence occurrences or increasing the length of the subsequence both substantially raise running time, which limits practical use of MaxFEM.  \nIn this paper we describe our efforts in designing a highperforming algorithm for this problem. For this we: 1) develop an efficient C++ implementation of MaxFEM, and 2) devise an efficient technique to parallelizing it. As the result, we propose an improved parallel MaxFEM variant, which we call ParMaxFEM. Additionally, we integrate the improved algorithm into Desbordante—a high-performance, open-source data profiler with deep Python integration that treats patterns as first-class entities and allows users to develop their custom programs that can include discovery and validation of patterns.  \nTo evaluate our approach we compare both C++ implementations with the original SPMF implementation. Experiments demonstrated that our reimplemented version provides up to 8 × speedup over the SPMF baseline, while our parallelization technique provides up to 35 × improvement overall (on 8 cores).  \nI. INTRODUCTION  \nData profiling [1] is concerned with extracting various types of information from data. Such information can range from simple statistics (e.g., the number of NULL values ina table column) to complex facts indicating the presence of sophisticated patterns in the data. Extracted facts can be interesting [2] on their own and can also be applied in areas such as data cleaning, data deduplication, anomaly detection, and many others.  \nData profiling can be performed on a variety of data types: tabular, transactional, graphs, and sequential. In this paper we focus on the latter.  \nSequential data is represented as one or several ordered list of events, where each one is associated with a time of occurrence.  \nEpisode mining [3] aims to extract patterns from sequential data. It has a large number of applications such as [3]: analysis  \nand anomaly detection in network data, analysis of financial data, web log analysis, and many others.  \nEpisode mining is a well-established field, with the first episode-mining algorithms introduced [4], [5] about 30 years ago. Its core task is the frequent episode mining (FEM), which is as follows. Given a single sequence of events, finding the subsequences whose number of occurrences in the input sequence is no less than a specified threshold called the minimum support (minsup) . Those subsequences are called frequent episodes.  \nHowever, solving this problem produces [6] a lot of frequent episodes some of which are included in each other.  \nThis leads to the following drawbacks:  \n1) It is inconvenient for a user to analyze a large number of similar episodes—from the end-user point of view it is better to work with a single representative subsequence from which the other subsequences can be derived.  \n2) These episodes require additional memory and computational effort to store and manipulate them. Experimental results [6] show that remo","cbCaiuIqhKoaHQLq","https://ap.wps.com/l/cbCaiuIqhKoaHQLq","pdf",412731,1,12,"English","en",105,"# Abstract\n# Introduction\n## Data profiling and sequential data\n## Frequent and maximal frequent episode mining\n## MaxFEM background and limitations","[{\"question\":\"What problem does maximal frequent episode mining address?\",\"answer\":\"It extracts frequent subsequences that are not included in any other larger frequent subsequence, avoiding overwhelming numbers of highly related episodes.\"},{\"question\":\"Why is the MaxFEM approach limited in practice?\",\"answer\":\"Runtime grows substantially when the minimum support is lowered or when the target subsequence length increases, making exhaustive mining computationally intensive.\"},{\"question\":\"What improvements are proposed in this work?\",\"answer\":\"The authors provide an efficient C++ implementation of MaxFEM, develop a parallelization technique to obtain ParMaxFEM, and integrate the improved algorithm into the Desbordante data profiler with deep Python support.\"}]",1784182469,30,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"scalable-maximal-frequent-episode-mining-with-desbordante","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/scalable-maximal-frequent-episode-mining-with-desbordante/82718/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-23","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does maximal frequent episode mining address?","Question",{"text":75,"@type":76},"It extracts frequent subsequences that are not included in any other larger frequent subsequence, avoiding overwhelming numbers of highly related episodes.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Why is the MaxFEM approach limited in practice?",{"text":80,"@type":76},"Runtime grows substantially when the minimum support is lowered or when the target subsequence length increases, making exhaustive mining computationally intensive.",{"name":82,"@type":73,"acceptedAnswer":83},"What improvements are proposed in this work?",{"text":84,"@type":76},"The authors provide an efficient C++ implementation of MaxFEM, develop a parallelization technique to obtain ParMaxFEM, and integrate the improved algorithm into the Desbordante data profiler with deep Python support.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":28,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]