[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84866-en":3,"doc-seo-84866-105":30,"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},84866,8796095461564,"Liam","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Signed-Graph Recommendation as Structural Consistency Maximization","Signed social recommendation can be limited by structural noise and data sparsity, which causes biased representations learned from sparse or unreliable signed graphs. The study identifies a core inconsistency spanning structural, propagation, and semantic layers, where noisy topologies do not match reliable social semantics. A unified framework, SSC-Loop, maximizes structural consistency through ESA-DA for structural refinement, a P/N/O polarity-aware propagation mechanism, and a contrastive semantic consistency objective. Experiments on Epinions and auxiliary Slashdot settings support strong prediction performance and structural exploitation.","arXiv :2607 .05952v 1 [ cs . SI ] 7 Jul 2026  \nSigned-Graph Recommendation as Structural Consistency Maximization  \nZifan Wang, Siyu Chen, and Wenzhuo Song⋆ Northeast Normal University, Changchun, Jilin, China  \nAbstract. While signed social recommendation has shown great potential by modeling both trust and distrust relations, its effectiveness is often hindered by structural noise and data sparsity. In this work, we first identify a fundamental inconsistency across the structural, propagation, and semantic layers of existing models, which leads to biased representations learned from sparse or noisy datasets. Furthermore, we observe that most existing methods treat the observed graph as fixed, failing to bridge the gap between noisy topologies and reliable social semantics. To address these issues, we propose a unified framework named SSC-Loop that treats signed social recommendation as the maximization of structural consistency. SSC-Loop includes three dedicated modules: ESA-DA for structural consistency, a P/N/O propagation mechanism for propagation consistency, and a contrastive learning objective for semantic consistency. Experiments on Epinions demonstrate that SSC-Loop achieves strong performance on explicit signed social rating prediction, while auxiliary results on Slashdot under a derived link-existence setting further suggest its ability to exploit signed social structures. Source code is available at [https://github.com/Refrainwww/SSC-Loop](https://github.com/Refrainwww/SSC-Loop).  \nKeywords: Recommender Systems · Signed Networks · Graph Neural Networks  \n1 Introduction  \nSocial recommendation leverages user–item interactions and social relations to improve personalized recommendation [1, 2] . Most existing methods assume that social relations are homogeneous and positive, such as friendship or trust [3] . However, real-world social networks often contain both trust and distrust relations [4] . Signed social recommendation is therefore important, as it can incorporate both trust and distrust relations into user preference modeling [5, 6] .  \nDespite this potential, signed social recommendation remains challenging because observed signed graphs are often sparse, noisy, and structurally imbalanced. Recent works commonly adopt Graph Neural Networks (GNNs), which model social relationships via message passing over observed links [3] . However, unreliable topology can distort information propagation and induce biased representations. In benchmark signed networks such as Epinions and Slashdot,  \n⋆ Corresponding [author. Email: wzsong@nenu.edu.cn](author. Email: wzsong@nenu.edu.cn)  \n2 Zifan Wang, Siyu Chen, and Wenzhuo Song  \nsocial links are highly sparse [7], and many signed triangles may violate structural balance theory [8] . These issues reveal a key limitation of existing methods, i.e., graph structure, propagation dynamics, and learned representations may be mutually inconsistent.  \nIn this work, we characterize this problem as a mismatch among three coupled layers: observed signed topology, polarity-aware propagation dynamics, and learned representation geometry. Structural inconsistency indicates that the observed topology may not reflect reliable social semantics. Propagation inconsistency indicates that positive and negative signals may be weakened, mixed, or distorted during multi-hop message passing. Semantic inconsistency indicates that the learned embedding space may fail to place trusted users close to eachother and distrusted users far apart.  \nBased on this perspective, we formulate signed social recommendation as a structural consistency maximization problem. Rather than treating the observed graph as a fixed input, we argue that graph structure and user representations should co-evolve within a closed loop. To this end, we propose the Signed Structural Consistency Loop (SSC-Loop), which integrates a module named ESADA for adaptive signed graph refinement, a polarity-aware P/N/O aggregation scheme for ","cbCaisCMjDAwyors","https://ap.wps.com/l/cbCaisCMjDAwyors","pdf",1157806,2,1,13,"English","en",105,"# Introduction\n## Problem: three-level inconsistency\n## Proposed framework: SSC-Loop\n## Contributions\n# Related Work","[{\"question\":\"What challenges limit signed social recommendation in practice?\",\"answer\":\"Observed signed graphs are often sparse, noisy, and structurally imbalanced, which can distort message passing and lead to biased learned representations.\"},{\"question\":\"What inconsistency does the paper claim exists across existing models?\",\"answer\":\"The work identifies a mismatch among structural, propagation, and semantic layers, where noisy topology, polarity-aware propagation, and representation geometry become mutually inconsistent.\"},{\"question\":\"How does SSC-Loop address structural, propagation, and semantic issues?\",\"answer\":\"SSC-Loop uses ESA-DA for adaptive signed graph refinement, a polarity-preserving P/N/O propagation mechanism for propagation consistency, and a contrastive objective to align signed semantics.\"}]",1784198912,33,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"signed-graph-recommendation-as-structural-consistency-maximization","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/signed-graph-recommendation-as-structural-consistency-maximization/84866/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-21","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 challenges limit signed social recommendation in practice?","Question",{"text":75,"@type":76},"Observed signed graphs are often sparse, noisy, and structurally imbalanced, which can distort message passing and lead to biased learned representations.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What inconsistency does the paper claim exists across existing models?",{"text":80,"@type":76},"The work identifies a mismatch among structural, propagation, and semantic layers, where noisy topology, polarity-aware propagation, and representation geometry become mutually inconsistent.",{"name":82,"@type":73,"acceptedAnswer":83},"How does SSC-Loop address structural, propagation, and semantic issues?",{"text":84,"@type":76},"SSC-Loop uses ESA-DA for adaptive signed graph refinement, a polarity-preserving P/N/O propagation mechanism for propagation consistency, and a contrastive objective to align signed semantics.","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":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]