[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-148437-105":59,"doc-detail-148437-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","multi-label-node-classification-with-label-influence-propagation-lip-conference-paper","Multi-Label Node Classification with Label Influence Propagation - LIP - Conference Paper","","Multi-label node classification (MLNC) on graphs is difficult because label interactions form complex, non-Euclidean dependencies that existing GNN-based or label-embedding-based methods fail to model. The work decomposes GNN message passing into propagation and transformation, quantifies positive and negative label influence correlations in each step, and builds a label influence graph from integrated correlations. High-order influences are propagated through this graph while dynamically amplifying labels with positive contributions and mitigating those with negative influence. Experiments on benchmark datasets consistently outperform state-of-the-art methods across multiple settings.",{"@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/multi-label-node-classification-with-label-influence-propagation-lip-conference-paper/148437/",{"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/multi-label-node-classification-with-label-influence-propagation-lip-conference-paper/148437.png","ImageObject",300,407,{"name":92,"@type":93},"Oliver","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-05","2026-08-26",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",13,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What problem does the paper address?","Question",{"text":113,"@type":114},"The paper addresses multi-label node classification on graphs (MLNC), where each node may belong to multiple labels and label interactions significantly affect prediction quality.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does Label Influence Propagation (LIP) model label interactions?",{"text":118,"@type":114},"LIP decomposes message passing into propagation and transformation, quantifies influence correlations between labels, builds a label influence graph, and propagates high-order influences through it.",{"name":120,"@type":111,"acceptedAnswer":121},"How does LIP use positive and negative influence during learning?",{"text":122,"@type":114},"During training, LIP dynamically amplifies labels that contribute positively to other labels and mitigates labels with negative influence, using the propagated high-order correlations.","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},148437,1787779801,{"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":130,"read_time":145},8796095461610,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","MULTI-LABEL NODE CLASSIFICATION WITH LABEL INFLUENCE PROPAGATION  \nYifei Sun 1 , Zemin Liu 1 ∗, Bryan Hooi2 , Yang Yang 1 ∗, Rizal Fathony3 , Jia Chen4 , Bingsheng He2 ∗  \n1Zhejiang University, 2National University of Singapore,  \n3 Capital One, 4 GrabTaxi Holdings Pte. Ltd.  \n{yifeisun, liu.zemin, [yangya](yangya}@zju.edu.cn)[}](yangya}@zju.edu.cn)[@zju.edu.cn](yangya}@zju.edu.cn) ,{bhooi, [hebs](hebs}@comp.nus.edu.sg)[}](hebs}@comp.nus.edu.sg)[@comp.nus.edu.sg](hebs}@comp.nus.edu.sg) ,  \n[rizal.fathony@capitalone.com](rizal.fathony@capitalone.com) , [jia.chen@grab.com](jia.chen@grab.com)  \nABSTRACT  \nGraphs are a complex and versatile data structure used across various domains, with possibly multi-label nodes playing a particularly crucial role. Examples include proteins in PPI networks with multiple functions and users in social ore-commerce networks exhibiting diverse interests. Tackling multi-label node classification (MLNC) on graphs has led to the development of various approaches. Some methods leverage graph neural networks (GNNs) to exploit label co-occurrence correlations, while others incorporate label embeddings to capture label proximity. However, these approaches fail to account for the intricate influences between labels in non-Euclidean graph data. To address this issue, we decompose the message passing process in GNNs into two operations: propagation and transformation. We then conduct a comprehensive analysis and quantification of the influence correlations between labels in each operation. Building on these insights, we propose a novel model, Label Influence Propagation (LIP) . Specifically, we construct a label influence graph based on the integrated label correlations. Then, we propagate high-order influences through this graph, dynamically adjusting the learning process by amplifying labels with positive contributions and mitigating those with negative influence. Finally, our framework is evaluated on comprehensive benchmark datasets, consistently outperforming SOTA methods across various settings, demonstrating its effectiveness on MLNC tasks 1.  \n1 INTRODUCTION  \nGraphs, as a complex data structure, are prevalent across various fields (Jiang et al., 2019; Kipf & Welling, 2016; Ying et al., 2018; Liu et al., 2023; Fang et al., 2024) . Among these, graphs with multi-label nodes are common and of great importance. For instance, proteins in ogbn-protein dataset have multiple functions (Hu et al., 2020) . Accurately identifying all the functions can assist with understanding biological processes and advancing biomedical research. Thus, we focus on this realistic but challenging problem named multi-label node classification on graphs, which we abbreviate as MLNC in the following paper.  \nPrior studies. Current methods typically adopt three strategies to address this problem. The first strategy is to neglect the multi-label information and predict the labels without mining label correlations (Shi et al., 2020b; Li et al., 2023) . The second strategy is to explicitly treat labels as anew type of node and incorporate them into the original graph, thereby enhancing task performance through propagation and aggregation information between nodes and label nodes (Gao et al., 2019; Shi et al., 2020a) . Since only incomplete connections between nodes and label nodes are available in the training set, the third strategy is to integrate label representations into the neighbor aggregation and classification processes, thereby improving the utilization of multi-label information (Zhou et al., 2021; Xiao et al., 2022) . However, these strategies underestimate the complex label correla-  \n∗ Corresponding authors.  \n1Our code is available at [https://github.com/Xtra-Computing/LIP_MLNC](https://github.com/Xtra-Computing/LIP_MLNC).  \n3 2 1 0  \n(a) AP Difference on DBLP  \n0 1 2 3  \n2  \n1  \n0  \n1  \n2  \n(b) AP Difference on BlogCat  \n9 8 7 6 5 4 3 2 1 0  \n0 1 2 3 4 5 6 7 8 9  \n0.2  \n0.0  \n~~ ~~0.2  \n~~ ~~0.4  \n~~ ~~0.6  \n9 8 7 6 5","cbCaid68ZIKd4knL","https://ap.wps.com/l/cbCaid68ZIKd4knL","pdf",2674594,25,"English","# Abstract\n# Introduction\n## Problem Setting: Multi-Label Node Classification on Graphs\n## Prior Studies and Limitations\n## Observations of Label Influence\n## Challenges and Contributions","[{\"question\":\"What problem does the paper address?\",\"answer\":\"The paper addresses multi-label node classification on graphs (MLNC), where each node may belong to multiple labels and label interactions significantly affect prediction quality.\"},{\"question\":\"How does Label Influence Propagation (LIP) model label interactions?\",\"answer\":\"LIP decomposes message passing into propagation and transformation, quantifies influence correlations between labels, builds a label influence graph, and propagates high-order influences through it.\"},{\"question\":\"How does LIP use positive and negative influence during learning?\",\"answer\":\"During training, LIP dynamically amplifies labels that contribute positively to other labels and mitigates labels with negative influence, using the propagated high-order correlations.\"}]","Multi-Label Node Classification with Label Influence Propagation - LIP - Conference Paper | PDF",63]