Behavior-Aware Aggregation and Graph Attention Fusion Network for Multi-Behavior Recommendation | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Behavior-Aware Aggregation and Graph Attention Fusion Network for Multi-Behavior Recommendation Chuang Shi, Yong Xu, Cheng Li, Jianfeng Sun, Qun Fang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8033010/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract In real world recommender systems, users interact with the same item through multiple behaviors—click, favorite, add-to-cart, and purchase that are heterogeneous and time dependent. Existing multi-behavior approaches suffer from three gaps: (i) static behavior categorization that ignores how frequency, intensity, and anomalies dynamically affect preference; (ii) shallow or fixed graph propagation that misses higher-order preferences and cross-graph semantics; and (iii) weak handling of temporal dependencies, which obscures interest evolution. We propose the Behavior-Aware Aggregation and Graph-Attention Fusion Network (BAGAR) to jointly model behavior differences, temporal dynamics, and semantic relations. BAGAR includes: a behavior-aware aggregation module combining behavior-intensity pooling, core-preference pooling, and anomaly filtering, fused by an adaptive graph multilayer perceptron; a multi-hop graph-attention module that forms hierarchical channels for first-order direct interests, higher-order latent preferences, and global semantic paths, reconciled by gating and a joint behavior-time dependency mechanism that embeds behavior relations and inter-event time gaps within a unified attention framework to track preference evolution. Experiments on Taobao, Tmall, and Yelp show that BAGAR outperforms strong baselines on hit rate and normalized discounted cumulative gain, validating its effectiveness for complex behavior modeling. Recommender systems Multi-behavior recommendation Graph attention network Knowledge graph Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-8033010","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":554321258,"identity":"0ed15a2b-5197-4e71-9cfd-bc515a4d4deb","order_by":0,"name":"Chuang Shi","email":"","orcid":"","institution":"Anhui Normal University","correspondingAuthor":false,"prefix":"","firstName":"Chuang","middleName":"","lastName":"Shi","suffix":""},{"id":554321259,"identity":"3b45e3e3-6abc-488b-a7ba-3b8a609de4b1","order_by":1,"name":"Yong Xu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAvUlEQVRIiWNgGAWjYHACxgMPKhgSwEweYvUcSDhDspbENlK0GNzIMTiQOM8uz1wigfHB2zYGeXOCWs6cAWrZllxsOSOB2XBuG4PhzgZCWo73gLQwJ264kcAmzQt0ocEBQloO8wC1zKkHaWH/TZwWsC0Nh8G2MBOlRfLMsYIDCceOJ24487BZcs45CcMNhLTw3Uje+OBDTXXihuPJBz+8KbORJ2iLAkIBYwOQkCCgHgjkGwirGQWjYBSMgpEOAPh+SGZ9+EfKAAAAAElFTkSuQmCC","orcid":"","institution":"Anhui Normal University","correspondingAuthor":true,"prefix":"","firstName":"Yong","middleName":"","lastName":"Xu","suffix":""},{"id":554321260,"identity":"774ec5d9-241b-478c-ae29-5d68b2a96ba8","order_by":2,"name":"Cheng Li","email":"","orcid":"","institution":"Anhui Normal University","correspondingAuthor":false,"prefix":"","firstName":"Cheng","middleName":"","lastName":"Li","suffix":""},{"id":554321261,"identity":"5a728382-9489-44e0-9501-72f96a6c268f","order_by":3,"name":"Jianfeng Sun","email":"","orcid":"","institution":"Anhui Normal University","correspondingAuthor":false,"prefix":"","firstName":"Jianfeng","middleName":"","lastName":"Sun","suffix":""},{"id":554321262,"identity":"77fcd764-8ecb-47a3-aada-1db5af115ec9","order_by":4,"name":"Qun Fang","email":"","orcid":"","institution":"Anhui Normal University","correspondingAuthor":false,"prefix":"","firstName":"Qun","middleName":"","lastName":"Fang","suffix":""}],"badges":[],"createdAt":"2025-11-05 01:23:16","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8033010/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8033010/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":97409664,"identity":"08c3b9ce-3f36-46da-aace-2ab4e73e26ad","added_by":"auto","created_at":"2025-12-04 05:00:16","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6176,"visible":true,"origin":"","legend":"","description":"","filename":"fe85c40ada4649c787286baf5330d6d5.json","url":"https://assets-eu.researchsquare.com/files/rs-8033010/v1/507b58360d59d6a95da5ea6c.json"},{"id":97409684,"identity":"c540b458-e987-4a0c-ac40-fc42039fdff7","added_by":"auto","created_at":"2025-12-04 05:00:16","extension":"xml","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":101627,"visible":true,"origin":"","legend":"","description":"","filename":"fe85c40ada4649c787286baf5330d6d51enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8033010/v1/e1603f6752f44158775313cc.xml"},{"id":97409669,"identity":"9c9dfdc2-bee6-4024-abf4-c0e092c9094b","added_by":"auto","created_at":"2025-12-04 05:00:16","extension":"pdf","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2257435,"visible":true,"origin":"","legend":"","description":"","filename":"BAGAR.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8033010/v1/4884937853e768316d64e063.pdf"},{"id":97667052,"identity":"b25b2122-d95c-442e-ae2a-c513e90549c1","added_by":"auto","created_at":"2025-12-08 09:22:41","extension":"eps","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2890,"visible":true,"origin":"","legend":"","description":"","filename":"empty.eps","url":"https://assets-eu.researchsquare.com/files/rs-8033010/v1/a4275776b8e54af87813cbb5.eps"},{"id":97409687,"identity":"5f06b944-b09e-486a-9510-61cc2e0b3f2a","added_by":"auto","created_at":"2025-12-04 05:00:16","extension":"eps","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":91593,"visible":true,"origin":"","legend":"","description":"","filename":"fig.eps","url":"https://assets-eu.researchsquare.com/files/rs-8033010/v1/97a9786a0b46c4e044679727.eps"},{"id":97667880,"identity":"e45cb529-899c-4328-bda7-8028a85886ed","added_by":"auto","created_at":"2025-12-08 09:24:26","extension":"bst","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":146013,"visible":true,"origin":"","legend":"","description":"","filename":"snapacite.bst","url":"https://assets-eu.researchsquare.com/files/rs-8033010/v1/14eb29c580587d5eed8b0d5d.bst"},{"id":97409667,"identity":"01850b82-c29a-4499-9410-e338cd03fc9d","added_by":"auto","created_at":"2025-12-04 05:00:16","extension":"bst","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":29828,"visible":true,"origin":"","legend":"","description":"","filename":"snaps.bst","url":"https://assets-eu.researchsquare.com/files/rs-8033010/v1/1440fcc10f7441c420deb779.bst"},{"id":97409678,"identity":"7d48bb54-5b39-4d63-a3cb-c9d2cc1b2e46","added_by":"auto","created_at":"2025-12-04 05:00:16","extension":"bst","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":35515,"visible":true,"origin":"","legend":"","description":"","filename":"snbasic.bst","url":"https://assets-eu.researchsquare.com/files/rs-8033010/v1/758b608afc686039bd5592c8.bst"},{"id":97409670,"identity":"c8233a68-8837-4dc3-92f3-e68367725f11","added_by":"auto","created_at":"2025-12-04 05:00:16","extension":"bst","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":33968,"visible":true,"origin":"","legend":"","description":"","filename":"snchicago.bst","url":"https://assets-eu.researchsquare.com/files/rs-8033010/v1/476b5bff6934e2ee28bfb5c0.bst"},{"id":97409675,"identity":"e65e0ec7-54c0-46a6-b77f-554d45883de6","added_by":"auto","created_at":"2025-12-04 05:00:16","extension":"cls","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":55861,"visible":true,"origin":"","legend":"","description":"","filename":"snjnl.cls","url":"https://assets-eu.researchsquare.com/files/rs-8033010/v1/3c21fdc66915ae13ea1c8402.cls"},{"id":97665581,"identity":"c44abbfe-9257-4a70-bcbf-933761d26a36","added_by":"auto","created_at":"2025-12-08 09:19:05","extension":"bst","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64023,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysay.bst","url":"https://assets-eu.researchsquare.com/files/rs-8033010/v1/6661bc83d3797fabb58974bf.bst"},{"id":97666088,"identity":"6dcba218-564e-4ec2-b037-c5a63416f0fb","added_by":"auto","created_at":"2025-12-08 09:20:23","extension":"bst","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64166,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysnum.bst","url":"https://assets-eu.researchsquare.com/files/rs-8033010/v1/0387e4ac2b2cc2b614280e5d.bst"},{"id":97409690,"identity":"f455a9c9-12b6-47f4-8ae1-f92e48017bef","added_by":"auto","created_at":"2025-12-04 05:00:16","extension":"bst","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":37333,"visible":true,"origin":"","legend":"","description":"","filename":"snnature.bst","url":"https://assets-eu.researchsquare.com/files/rs-8033010/v1/d8d14593a2b524a45a31d2c5.bst"},{"id":97409692,"identity":"3378060f-433b-4b50-b58b-52e2cc88d954","added_by":"auto","created_at":"2025-12-04 05:00:16","extension":"bst","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":39951,"visible":true,"origin":"","legend":"","description":"","filename":"snvancouveray.bst","url":"https://assets-eu.researchsquare.com/files/rs-8033010/v1/60f4be2a464ce46e9ecc8310.bst"},{"id":97665302,"identity":"45a87413-4dc7-4cef-a651-c032b93c8b6f","added_by":"auto","created_at":"2025-12-08 09:17:45","extension":"bst","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":40758,"visible":true,"origin":"","legend":"","description":"","filename":"snvancouvernum.bst","url":"https://assets-eu.researchsquare.com/files/rs-8033010/v1/c4f6b06901cc737a297d0037.bst"},{"id":97409696,"identity":"862a1020-410a-44e4-8f41-e8373173f4fe","added_by":"auto","created_at":"2025-12-04 05:00:16","extension":"xml","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":110030,"visible":true,"origin":"","legend":"","description":"","filename":"fe85c40ada4649c787286baf5330d6d51structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8033010/v1/3612098fdf7ff725c20a6d02.xml"},{"id":97409694,"identity":"889a8075-f1d0-41bc-88dd-2426e9e88efa","added_by":"auto","created_at":"2025-12-04 05:00:16","extension":"html","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":121935,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8033010/v1/bdfccf2e5de6f47bc633637d.html"},{"id":104950674,"identity":"fa15f8ce-aa2f-4ef4-b6ec-abbec485c308","added_by":"auto","created_at":"2026-03-19 06:41:54","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2172664,"visible":true,"origin":"","legend":"","description":"","filename":"BAGAR.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8033010/v1_covered_81212e93-8fb8-4bba-8564-4a910678eb58.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Behavior-Aware Aggregation and Graph Attention Fusion Network for Multi-Behavior Recommendation","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"
[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Recommender systems, Multi-behavior recommendation, Graph attention network, Knowledge graph","lastPublishedDoi":"10.21203/rs.3.rs-8033010/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8033010/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eIn real world recommender systems, users interact with the same item through multiple behaviors\u0026mdash;click, favorite, add-to-cart, and purchase that are heterogeneous and time dependent. Existing multi-behavior approaches suffer from three gaps: (i) static behavior categorization that ignores how frequency, intensity, and anomalies dynamically affect preference; (ii) shallow or fixed graph propagation that misses higher-order preferences and cross-graph semantics; and (iii) weak handling of temporal dependencies, which obscures interest evolution. We propose the Behavior-Aware Aggregation and Graph-Attention Fusion Network (BAGAR) to jointly model behavior differences, temporal dynamics, and semantic relations. BAGAR includes: a behavior-aware aggregation module combining behavior-intensity pooling, core-preference pooling, and anomaly filtering, fused by an adaptive graph multilayer perceptron; a multi-hop graph-attention module that forms hierarchical channels for first-order direct interests, higher-order latent preferences, and global semantic paths, reconciled by gating and a joint behavior-time dependency mechanism that embeds behavior relations and inter-event time gaps within a unified attention framework to track preference evolution. Experiments on Taobao, Tmall, and Yelp show that BAGAR outperforms strong baselines on hit rate and normalized discounted cumulative gain, validating its effectiveness for complex behavior modeling.\u003c/p\u003e","manuscriptTitle":"Behavior-Aware Aggregation and Graph Attention Fusion Network for Multi-Behavior Recommendation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-04 05:00:11","doi":"10.21203/rs.3.rs-8033010/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"
[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"24eb5941-06f8-4fa9-814b-5cdd0c095834","owner":[],"postedDate":"December 4th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-03-19T06:40:48+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-04 05:00:11","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8033010","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8033010","identity":"rs-8033010","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}
Text is read by the "Ask this paper" AI Q&A widget below.
Extraction quality varies by source — PMC NXML preserves structure
cleanly, OA-HTML may include some navigation residue, and OA-PDF can
have broken hyphenation. The publisher copy
(via DOI)
is the canonical version.