[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-328051-105":59,"doc-detail-328051-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","breaking-structural-isolation-scalable-graph-clustering-via-community-aware-sampling-and-structural-entropy","Breaking Structural Isolation - Scalable Graph Clustering via Community-Aware Sampling and Structural Entropy","","Unsupervised graph clustering uncovers semantic structure in large-scale networks, yet mini-batch graph contrastive learning often suffers from “structural isolation,” fragmenting communities and weakening global topological coherence. SCISE addresses this by combining community-aware sampling with constrained structural entropy. It introduces SECC to optimize structural information in a restricted solution space, CSampE to expand sampling batches using community context, and StructCL to refine edge weights via intra-batch structural similarity. Experiments on six benchmarks show clear gains over state-of-the-art methods, supported by ablations and robustness analyses for real-world large graphs.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/breaking-structural-isolation-scalable-graph-clustering-via-community-aware-sampling-and-structural-entropy/328051/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/breaking-structural-isolation-scalable-graph-clustering-via-community-aware-sampling-and-structural-entropy/328051.png","ImageObject",300,407,{"name":92,"@type":93},"Noah","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-31","2026-09-21",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",12,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What problem does SCISE address in unsupervised graph clustering?","Question",{"text":113,"@type":114},"It targets “structural isolation” during mini-batch graph contrastive learning, which fragments communities and makes it difficult to capture cohesive global structure.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does SCISE preserve structural integrity during training?",{"text":118,"@type":114},"It proposes SECC to constrain and optimize structural information, CSampE to incorporate community context into sampling batches, and StructCL to refine representations using intra-batch structural similarity.",{"name":120,"@type":111,"acceptedAnswer":121},"How was SCISE evaluated and validated?",{"text":122,"@type":114},"The method was tested on six mainstream benchmark datasets, and ablation studies plus robustness analyses confirm its effectiveness and reliability for large-scale graphs.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},328051,1790459490,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":145,"read_time":146,"preview_page_count":4},8796095462418,"https://ap-avatar.wpscdn.com/avatar/80000253c1241d02b47?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778826106357471780","Breaking Structural Isolation: Scalable Graph Clustering via Community-Aware Sampling and Structural Entropy  \nJingyun Zhang  \nBeihang University Beijing, China [zhangjingyun@buaa.edu.cn](zhangjingyun@buaa.edu.cn)  \nHao Peng∗ Beihang University Beijing, China  \nHangzhou Innovation Institute, Beihang University Hangzhou, China [penghao@buaa.edu.cn](penghao@buaa.edu.cn)  \nJianxin Li Beihang University  \nBeijing, China [lijx@buaa.edu.cn](lijx@buaa.edu.cn)  \nAngsheng Li  \nBeihang University Beijing, China[angsheng@buaa.edu.cn](angsheng@buaa.edu.cn)  \nPhilip S. Yu  \nUniversity of Illinois at Chicago Chicago, USA [psyu@uic.edu](psyu@uic.edu)  \narXiv :2607 .05469v 1 [ cs .LG] 6 Jul 2026  \nABSTRACT  \nUnsupervised graph clustering is a fundamental technique for uncovering underlying semantic patterns in large-scale networks. Although Graph Contrastive Learning has demonstrated promising performance, existing methods often suffer from the \"structural isolation\" issue during mini-batch training, making it challenging to capture cohesive community structures that characterize the global topological distribution. To address these challenges, we propose SCISE, a Scalable unsupervised graph Clustering framework that preserves structural Integrity by synergizing communityaware sampling with constrained Structural Entropy. Specifically, we first introduce the Structural Entropy Community Constraint operator (SECC), which optimizes structural information within a constrained solution space to mitigate community fragmentation and enhance partition cohesion. Second, to prevent global information loss during batch training, we design a CommunityAware Sampling Expansion (CSampE) mechanism that incorporates the community context of target nodes into sampling batches, effectively breaking structural barriers and preserving topological integrity. Finally, we devise a Structural Contrastive Learning (StructCL) module that refines edge weights based on intra-batch structural similarity, guiding the encoder to learn representations ina higher-order structural space. Extensive experiments on six mainstream benchmark datasets demonstrate that SCISE significantly outperforms state-of-the-art algorithms, with ablation studies and robustness analyses further validating its effectiveness and reliability for real-world large-scale graphs.  \nPVLDB Reference Format:  \nJingyun Zhang, Hao Peng, Jianxin Li, Angsheng Li, and Philip S. Yu. Breaking Structural Isolation: Scalable Graph Clustering via Community-Aware Sampling and Structural Entropy. PVLDB, 19(1):  \nXXX-XXX, 2026 .  \ndoi:XX.XX/XXX.XX  \n∗ Corresponding author.  \nThis work is licensed under the Creative Commons BY-NC-ND 4.0 International License. Visit [https://creativecommons.org/licenses/by-nc-nd/4.0/ to view a copy of](https://creativecommons.org/licenses/by-nc-nd/4.0/ to view a copy of)[ ](https://creativecommons.org/licenses/by-nc-nd/4.0/ to view a copy of)[this license. For any use beyond those covered by this license](this license. For any use beyond those covered by this license), [obtain permission by](obtain permission by)[emailing info@vldb.org. Copyright](emailing info@vldb.org. Copyright) is held by the owner/author(s). Publication rights  \nPVLDB Artifact Availability:  \nThe source code, data, and/or other artifacts have been made available at [https://github.com/SELGroup/SCISE](https://github.com/SELGroup/SCISE).  \n1 INTRODUCTION  \nGraph-structured data has become pervasive in representing complex relational information across diverse domains, such as social media, citation networks, and biological systems [12, 16] . As a fundamental task in network analysis, unsupervised graph clustering aims to partition nodes with high topological and attribute affinities into communities without reliance on manual labeling, thereby revealing the underlying semantic patterns and structural motifs within complex networks [10, 43] . This capability is critical for numerous downstream applications, including ","cbCaicgkT9IgBLEr","https://ap.wps.com/l/cbCaicgkT9IgBLEr","pdf",4963303,18,"English","# Introduction\n## Unsupervised graph clustering and graph contrastive learning\n## Scalability bottleneck and structural isolation\n## Sampling strategies and community context","[{\"question\":\"What problem does SCISE address in unsupervised graph clustering?\",\"answer\":\"It targets “structural isolation” during mini-batch graph contrastive learning, which fragments communities and makes it difficult to capture cohesive global structure.\"},{\"question\":\"How does SCISE preserve structural integrity during training?\",\"answer\":\"It proposes SECC to constrain and optimize structural information, CSampE to incorporate community context into sampling batches, and StructCL to refine representations using intra-batch structural similarity.\"},{\"question\":\"How was SCISE evaluated and validated?\",\"answer\":\"The method was tested on six mainstream benchmark datasets, and ablation studies plus robustness analyses confirm its effectiveness and reliability for large-scale graphs.\"}]","Breaking Structural Isolation - Scalable Graph Clustering via Community-Aware Sampling and Structural Entropy | PDF",1789978576,45]