{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T16:26:46Z","timestamp":1784305606463,"version":"3.55.0"},"reference-count":63,"publisher":"Association for Computing Machinery (ACM)","issue":"1","funder":[{"name":"National Science and Technology","award":["2023ZD0121104"],"award-info":[{"award-number":["2023ZD0121104"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62222213 and 62072423"],"award-info":[{"award-number":["62222213 and 62072423"]}],"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>Recent years have witnessed the prosperity of Knowledge Graph-Based Recommendation System (KGRS), which enriches the representation of users, items, and entities by structural knowledge with striking improvement. Nevertheless, its unaffordable computational cost still limits researchers from exploring more sophisticated models. We observe that the bottleneck for training efficiency arises from the knowledge graph, which is plagued by the well-known issue of knowledge explosion. Recently, some works have attempted to slim the inflated KG via summarization techniques, which summarize multiple real nodes into the single virtual one. However, these summarized virtual nodes may ignore collaborative signals and thus fail to figure out the redundant nodes related to recommendation task. To this end, in this article, we propose a novel approach called KGTrimmer for knowledge graph pruning tailored for recommendation, to remove the unessential nodes while minimizing performance degradation. Specifically, we design an importance evaluator from a dual-view perspective. For the collective view, we embrace the idea of collective intelligence by extracting community consensus based on abundant collaborative signals, i.e., nodes are considered important if they attract attention of numerous users. For the holistic view, we learn a global mask to identify the valueless nodes from their inherent properties or overall popularity. With the collective and holistic importance scores, we build an end-to-end importance-aware graph neural network, which injects filtered knowledge to enhance the distillation of valuable user-item collaborative signals. Ultimately, we generate a pruned knowledge graph with lightweight, stable, and robust properties to facilitate the following-up recommendation task. Extensive experiments are conducted on three publicly available datasets to prove the effectiveness and generalizability of KGTrimmer, where it can reduce the number of triplets in KG by up to 90% without compromising performance.<\/jats:p>","DOI":"10.1145\/3769107","type":"journal-article","created":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T13:17:42Z","timestamp":1758633462000},"page":"1-28","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Knowledge Graph Pruning for Recommendation"],"prefix":"10.1145","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1402-2358","authenticated-orcid":false,"given":"Fake","family":"Lin","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3621-8493","authenticated-orcid":false,"given":"Xi","family":"Zhu","sequence":"additional","affiliation":[{"name":"Rutgers, The State University of New Jersey, New Brunswick, New Jersey, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0814-7313","authenticated-orcid":false,"given":"Ziwei","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7154-9978","authenticated-orcid":false,"given":"Deqiang","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3109-7859","authenticated-orcid":false,"given":"Yu","family":"Yu","sequence":"additional","affiliation":[{"name":"Advanced Algorithms Research Shanghai, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3699-0697","authenticated-orcid":false,"given":"Xueying","family":"Li","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7758-8904","authenticated-orcid":false,"given":"Zhi","family":"Zheng","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4246-5386","authenticated-orcid":false,"given":"Tong","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4835-4102","authenticated-orcid":false,"given":"Enhong","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,11,14]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.3390\/a11090137"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-52846-6_75"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/2492007.2492029"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380189"},{"key":"e_1_3_2_6_2","volume-title":"Proceedings of the 10th International Conference on Learning Representations (ICLR \u201922), Virtual Event","author":"Brody Shaked","year":"2022","unstructured":"Shaked Brody, Uri Alon, and Eran Yahav. 2022. How attentive are graph attention networks? In Proceedings of the 10th International Conference on Learning Representations (ICLR \u201922), Virtual Event. OpenReview.net. Retrieved from https:\/\/openreview.net\/forum?id=F72ximsx7C1"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313705"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959131"},{"key":"e_1_3_2_9_2","first-page":"1695","volume-title":"Proceedings of the 38th International Conference on Machine Learning (ICML \u201921), Virtual Event","volume":"139","author":"Chen Tianlong","year":"2021","unstructured":"Tianlong Chen, Yongduo Sui, Xuxi Chen, Aston Zhang, and Zhangyang Wang. 2021. A unified lottery ticket hypothesis for graph neural networks. In Proceedings of the 38th International Conference on Machine Learning (ICML \u201921), Virtual Event. Marina Meila and Tong Zhang (Eds.), Proceedings of Machine Learning Research, Vol. 139, PMLR, 1695\u20131706. Retrieved from http:\/\/proceedings.mlr.press\/v139\/chen21p.html"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/2491159.2491168"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531987"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/564"},{"key":"e_1_3_2_13_2","volume-title":"Proceedings of the 7th International Conference on Learning Representations (ICLR \u201919)","author":"Frankle Jonathan","year":"2019","unstructured":"Jonathan Frankle and Michael Carbin. 2019. The lottery ticket hypothesis: Finding sparse, trainable neural networks. In Proceedings of the 7th International Conference on Learning Representations (ICLR \u201919). OpenReview.net. Retrieved from https:\/\/openreview.net\/forum?id=rJl-b3RcF7"},{"key":"e_1_3_2_14_2","first-page":"249","volume-title":"Proceedings of the 13th International Conference on Artificial Intelligence and Statistics (AISTATS \u201910)","volume":"9","author":"Glorot Xavier","year":"2010","unstructured":"Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the 13th International Conference on Artificial Intelligence and Statistics (AISTATS \u201910). Yee Whye Teh and D. Mike Titterington (Eds.), JMLR Proceedings, Vol. 9, JMLR.org, 249\u2013256. Retrieved from http:\/\/proceedings.mlr.press\/v9\/glorot10a.html"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.06.024"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219965"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210017"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1162\/NECO.1991.3.1.79"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313586"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403050"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380043"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00219"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1007\/S41060-021-00288-8"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3186727"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313607"},{"key":"e_1_3_2_26_2","unstructured":"Steffen Rendle Christoph Freudenthaler Zeno Gantner and Lars Schmidt-Thieme. 2012. BPR: Bayesian personalized ranking from implicit feedback. arXiv:1205.2618. Retrieved from http:\/\/arxiv.org\/abs\/1205.2618"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10844-021-00650-z"},{"key":"e_1_3_2_28_2","unstructured":"Nasrin Shabani Jia Wu Amin Beheshti Jin Foo Ambreen Hanif and Maryam Shahabikargar. 2023. A survey on graph neural networks for graph summarization. arXiv:2302.06114. Retrieved from https:\/\/arxiv.org\/abs\/2302.06114"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.5555\/2627435.2670313"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240361"},{"key":"e_1_3_2_31_2","first-page":"9448","volume-title":"Proceedings of the 37th International Conference on Machine Learning (ICML \u201920), Virtual Event","volume":"119","author":"Teru Komal K.","year":"2020","unstructured":"Komal K. Teru, Etienne G. Denis, and William L. Hamilton. 2020. Inductive relation prediction by subgraph reasoning. In Proceedings of the 37th International Conference on Machine Learning (ICML \u201920), Virtual Event. Proceedings of Machine Learning Research, Vol. 119, PMLR, 9448\u20139457. Retrieved from http:\/\/proceedings.mlr.press\/v119\/teru20a.html"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462912"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401131"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271739"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330836"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3047086"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482470"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330989"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450133"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015329"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482092"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1609\/AAAI.V28I1.8870"},{"key":"e_1_3_2_43_2","unstructured":"Yinwei Wei Xiang Wang Liqiang Nie Shaoyu Li Dingxian Wang and Tat-Seng Chua. 2022. Causal inference for knowledge graph based recommendation. arXiv:2212.10046. Retrieved from https:\/\/arxiv.org\/abs\/2212.10046"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1609\/AAAI.V32I1.11924"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645351"},{"key":"e_1_3_2_46_2","volume-title":"Proceedings of the 8th International Conference on Learning Representations (ICLR \u201920)","author":"Xu Xiaoran","year":"2020","unstructured":"Xiaoran Xu, Wei Feng, Yunsheng Jiang, Xiaohui Xie, Zhiqing Sun, and Zhi-Hong Deng. 2020. Dynamically pruned message passing networks for large-scale knowledge graph reasoning. In Proceedings of the 8th International Conference on Learning Representations (ICLR \u201920). OpenReview.net. Retrieved from https:\/\/openreview.net\/forum?id=rkeuAhVKvB"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512180"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599400"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532009"},{"key":"e_1_3_2_50_2","first-page":"2331","volume-title":"Uncertainty in Artificial Intelligence, Proceedings of the 38th Conference on Uncertainty in Artificial Intelligence (UAI \u201922)","volume":"180","author":"Yu Shujian","year":"2022","unstructured":"Shujian Yu, Francesco Alesiani, Wenzhe Yin, Robert Jenssen, and Jos\u00e9 C. Pr\u00edncipe. 2022. Principle of relevant information for graph sparsification. In Uncertainty in Artificial Intelligence, Proceedings of the 38th Conference on Uncertainty in Artificial Intelligence (UAI \u201922). James Cussens and Kun Zhang (Eds.), Proceedings of Machine Learning Research, Vol. 180, PMLR, 2331\u20132341. Retrieved from https:\/\/proceedings.mlr.press\/v180\/yu22c.html"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939673"},{"key":"e_1_3_2_52_2","unstructured":"Guibin Zhang Xiangguo Sun Yanwei Yue Kun Wang Tianlong Chen and Shirui Pan. 2024. Graph sparsification via mixture of graphs. arXiv:2405.14260. Retrieved from https:\/\/arxiv.org\/abs\/2405.14260"},{"key":"e_1_3_2_53_2","volume-title":"Proceedings of the 12th International Conference on Learning Representations","author":"Zhang Guibin","year":"2024","unstructured":"Guibin Zhang, Kun Wang, Wei Huang, Yanwei Yue, Yang Wang, Roger Zimmermann, Aojun Zhou, Dawei Cheng, Jin Zeng, and Yuxuan Liang. 2024. Graph lottery ticket automated. In Proceedings of the 12th International Conference on Learning Representations."},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557264"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.120871"},{"key":"e_1_3_2_56_2","volume-title":"Proceedings of the CIKM 2018 Workshops Co-Located with 27th ACM International Conference on Information and Knowledge Management (CIKM \u201918)","volume":"2482","author":"Zhao Wayne Xin","year":"2018","unstructured":"Wayne Xin Zhao, Gaole He, Hongjian Dou, Jin Huang, Siqi Ouyang, and Ji-Rong Wen. 2018. KB4Rec: A dataset for linking knowledge bases with recommender systems. In Proceedings of the CIKM 2018 Workshops Co-Located with 27th ACM International Conference on Information and Knowledge Management (CIKM \u201918). Alfredo Cuzzocrea, Francesco Bonchi, and Dimitrios Gunopulos (Eds.), CEUR Workshop Proceedings, Vol. 2482, CEUR-WS.org. Retrieved from https:\/\/ceur-ws.org\/Vol-2482\/paper25.pdf"},{"key":"e_1_3_2_57_2","unstructured":"Ziwei Zhao Fake Lin Xi Zhu Zhi Zheng Tong Xu Shitian Shen Xueying Li Zikai Yin and Enhong Chen. 2024. DynLLM: When large language models meet dynamic graph recommendation. arXiv:2405.07580. Retrieved from https:\/\/arxiv.org\/abs\/2405.07580"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645358"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512099"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449962"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.01.001"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591707"},{"issue":"4","key":"e_1_3_2_63_2","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1561\/3300000050","article-title":"Recommender systems meet large language model agents: A survey","volume":"7","author":"Zhu Xi","year":"2025","unstructured":"Xi Zhu, Yu Wang, Hang Gao, Wujiang Xu, Chen Wang, Zhiwei Liu, Kun Wang, Mingyu Jin, Linsey Pang, Qingsong Weng, et al. 2025. Recommender systems meet large language model agents: A survey. Foundations and Trends\u00ae in Privacy and Security 7, 4 (2025), 247\u2013396.","journal-title":"Foundations and Trends\u00ae in Privacy and Security"},{"key":"e_1_3_2_64_2","doi-asserted-by":"crossref","unstructured":"Xi Zhu Haochen Xue Ziwei Zhao Wujiang Xu Jingyuan Huang Minghao Guo Qifan Wang Kaixiong Zhou and Yongfeng Zhang. 2025. LLM as GNN: Graph vocabulary learning for text-attributed graph foundation models. arXiv:2503.03313. Retrieved from https:\/\/arxiv.org\/abs\/2503.03313","DOI":"10.2139\/ssrn.5162133"}],"container-title":["ACM Transactions on Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3769107","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T14:11:30Z","timestamp":1763129490000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3769107"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,14]]},"references-count":63,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1,31]]}},"alternative-id":["10.1145\/3769107"],"URL":"https:\/\/doi.org\/10.1145\/3769107","relation":{},"ISSN":["1046-8188","1558-2868"],"issn-type":[{"value":"1046-8188","type":"print"},{"value":"1558-2868","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,14]]},"assertion":[{"value":"2024-07-10","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-05","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}