{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T19:54:53Z","timestamp":1788897293259,"version":"build-2803163510"},"reference-count":78,"publisher":"Association for Computing Machinery (ACM)","issue":"1","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["72174018 and 72442005"],"award-info":[{"award-number":["72174018 and 72442005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Inf. Syst."],"published-print":{"date-parts":[[2026,1,31]]},"abstract":"<jats:p>Online reviews play a critical role in influencing consumer\u2019s purchasing decision on e-commerce, making them a prime target for manipulation through fraudulent reviews. Although various Fraud Detection (FD) techniques have been presented, a crucial problem still remains unaddressed, i.e., the cold-start problem in FD, which refers to the difficulty in identifying fraudulent reviews due to limited historical data for new users and new products. Existing graph-based detection methods, while effective for well-connected nodes, are suffering Sparse Graph (SG) connections in cold-start FD. In this article, we propose a novel approach called SparseFraudNet to address the problem of cold-start FD with information aggregation. Specifically, the local information aggregation is proposed to dynamically optimize neighbor selection using Reinforcement Learning (RL) with Bernoulli Multi-armed Bandit (BMAB), with the goal to capture the five key types of relations among reviews. The global information aggregation is proposed to leverage Graph Coarsening (GC) with manifold learning and spectral clustering to mitigate adjacency matrix sparsity for new users under new products using Sparse Spectral Clustering (SSC). Experiments on the YelpZip-cold and YelpNYC-cold datasets demonstrate that the proposed SparseFraudNet approach significantly outperforms state-of-the-art methods in FD in terms of accuracy, precision, recall, F1 measure and AUC to identify fraudulent reviews of new users under new products.<\/jats:p>","DOI":"10.1145\/3748719","type":"journal-article","created":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T16:28:51Z","timestamp":1755880131000},"page":"1-45","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["SparseFraudNet: A Graph-based Approach for Cold-start Fraud Detection with Information Aggregation"],"prefix":"10.1145","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6216-2262","authenticated-orcid":false,"given":"Wen","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Economics and Management, Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1395-982X","authenticated-orcid":false,"given":"Rui","family":"Li","sequence":"additional","affiliation":[{"name":"College of Economics and Management, Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1214-6317","authenticated-orcid":false,"given":"Quan","family":"Bai","sequence":"additional","affiliation":[{"name":"School of Information and Communication Technology, University of Tasmania, Hobart,\u00a0Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0617-2877","authenticated-orcid":false,"given":"Song","family":"Wang","sequence":"additional","affiliation":[{"name":"Lassonde School of Engineering, York University, Toronto, Ontario, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,14]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2021.02612"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijinfomgt.2021.102416"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1287\/mksc.2022.1353"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbusres.2023.114200"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3443141"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474379"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112385"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-024-10702-9"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467364"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645706"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.107159"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.chb.2021.106972"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","unstructured":"Sailik Sengupta Ankur Chowdhary Abdulhakim Sabur Adel Alshamrani Dijiang Huang and Subbarao Kambhampati. 2020. A survey of moving target defenses for network security. IEEE Communications Surveys & Tutorials 22 3 (2020) 1909\u20131941. DOI: 10.1109\/COMST.2020.2982955","DOI":"10.1109\/COMST.2020.2982955"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/197"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411903"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512195"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127108"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.bushor.2023.08.002"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2021.02612"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.techfore.2023.122971"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","unstructured":"Saeedreza Shehnepoor Roberto Togneri Wei Liu and Mohammed Bennamoun. 2021. DFraud3: Multi-component fraud detection free of cold-start. IEEE Transactions on Information Forensics and Security 16 (2021) 3456\u20133468. DOI: 10.1109\/TIFS.2021.3081258","DOI":"10.1109\/TIFS.2021.3081258"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.116209"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-018-1333-x"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2023.114045"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117869"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1080\/03081079.2024.2384404"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2021.113728"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","unstructured":"Nan Jiang Fuxian Duan Honglong Chen Wei Huang and Ximeng Liu. 2022. MAFI: GNN-based multiple aggregators and feature interactions network for fraud detection over heterogeneous graph. IEEE Transactions on Big Data 8 4 (August 2022) 905\u2013919. DOI: 10.1109\/TBDATA.2021.3132672","DOI":"10.1109\/TBDATA.2021.3132672"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449989"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119153"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.120580"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.tele.2020.101560"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.04.027"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2019.113158"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113248"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121930"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3212001"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1080\/10864415.2024.2401949"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-022-04685-z"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","unstructured":"Shengchao Hu Li Shen Ya Zhang Yixin Chen and Dacheng Tao. 2024. On transforming reinforcement learning with transformers: The development trajectory. IEEE Transactions on Pattern Analysis and Machine Intelligence 46 12 (December 2024) 8580\u20138599. DOI: 10.1109\/TPAMI.2024.3408271","DOI":"10.1109\/TPAMI.2024.3408271"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403088"},{"key":"e_1_3_2_44_2","first-page":"21171","article-title":"Hierarchical graph transformer with adaptive node sampling","volume":"35","author":"Zhang Zaixi","year":"2022","unstructured":"Zaixi Zhang, Qi Liu, Qingyong Hu, and Chee-Kong Lee. 2022. Hierarchical graph transformer with adaptive node sampling. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 35, 21171\u201321183.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM58522.2023.00010"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290964"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121643"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467384"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512104"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","unstructured":"Sai Kiran Kadambari and Sundeep Prabhakar Chepuri. 2021. Product graph learning from multi-domain data with sparsity and rank constraints. IEEE Transactions on Signal Processing 69 (2021) 5665\u20135680. DOI: 10.1109\/TSP.2021.3115947","DOI":"10.1109\/TSP.2021.3115947"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3072345"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00888"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2022.103170"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2023.113977"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2021.3094233"},{"key":"e_1_3_2_56_2","first-page":"4","volume-title":"Pattern Recognition and Machine Learning","author":"Bishop Christopher M.","year":"2006","unstructured":"Christopher M. Bishop and Nasser M. Nasrabadi. 2006. Pattern Recognition and Machine Learning. Springer, New York, 4."},{"key":"e_1_3_2_57_2","doi-asserted-by":"crossref","unstructured":"Youshen Xia Jun Wang Zhenyu Lu and Liqing Huang. 2023. Two Recurrent Neural Networks With Reduced Model Complexity for Constrained l\u2081-Norm Optimization. IEEE Transactions on Neural Networks and Learning Systems 34 9 (September 2023) 6173\u20136185. DOI: 10.1109\/TNNLS.2021.3133836","DOI":"10.1109\/TNNLS.2021.3133836"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401253"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.08.018"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.5555\/3618408.3619802"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.12.004"},{"key":"e_1_3_2_62_2","first-page":"27294","article-title":"Canonical normalizing flows for manifold learning","volume":"36","author":"Flouris Kyriakos","year":"2023","unstructured":"Kyriakos Flouris and Ender Konukoglu. 2023. Canonical normalizing flows for manifold learning. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 36, 27294\u201327314.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_63_2","doi-asserted-by":"publisher","unstructured":"David L. Donoho. 2006. For most large underdetermined systems of linear equations the minimal \\(\\ell\\) 1 -norm solution is also the sparsest solution. Communications on Pure and Applied Mathematics 59 6 (June 2006) 797\u2013829. DOI: 10.1002\/cpa.20132","DOI":"10.1002\/cpa.20132"},{"key":"e_1_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.csda.2023.107902"},{"key":"e_1_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2013.12.027"},{"key":"e_1_3_2_66_2","first-page":"8247","article-title":"An efficient nonconvex reformulation of stagewise convex optimization problems","volume":"33","author":"Bunel Rudy","year":"2020","unstructured":"Rudy Bunel and Srinadh Bhojanapalli. 2020. An efficient nonconvex reformulation of stagewise convex optimization problems. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 33, 8247\u20138258.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10957-016-0869-2"},{"key":"e_1_3_2_68_2","first-page":"8271","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Oh Min-hwan","year":"2021","unstructured":"Min-hwan Oh, Garud Iyengar, and Assaf Zeevi. 2021. Sparsity-agnostic Lasso bandit. In Proceedings of the International Conference on Machine Learning, 8271\u20138280."},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.104743"},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118290"},{"key":"e_1_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"e_1_3_2_72_2","article-title":"Inductive representation learning on large graphs","volume":"30","author":"Hamilton Will","year":"2017","unstructured":"Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 30.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3114765"},{"key":"e_1_3_2_74_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2022.113765"},{"key":"e_1_3_2_75_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2020.113280"},{"key":"e_1_3_2_76_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.indmarman.2022.04.019"},{"key":"e_1_3_2_77_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3349397"},{"key":"e_1_3_2_78_2","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583237"},{"key":"e_1_3_2_79_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2015.10.004"}],"container-title":["ACM Transactions on Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3748719","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T18:31:35Z","timestamp":1760466695000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3748719"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,14]]},"references-count":78,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1,31]]}},"alternative-id":["10.1145\/3748719"],"URL":"https:\/\/doi.org\/10.1145\/3748719","relation":{},"ISSN":["1046-8188","1558-2868"],"issn-type":[{"value":"1046-8188","type":"print"},{"value":"1558-2868","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,14]]},"assertion":[{"value":"2024-12-10","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-09","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}