{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,11]],"date-time":"2026-11-11T13:27:48Z","timestamp":1794403668908,"version":"4.9.0"},"reference-count":113,"publisher":"Association for Computing Machinery (ACM)","issue":"4","funder":[{"name":"streams of Future Fellowship","award":["FT210100624"],"award-info":[{"award-number":["FT210100624"]}]},{"name":"Discovery Early Career Researcher","award":["DE230101033"],"award-info":[{"award-number":["DE230101033"]}]},{"name":"Discovery Project","award":["DP240101108 and DP240101814"],"award-info":[{"award-number":["DP240101108 and DP240101814"]}]},{"name":"Linkage Project","award":["LP230200892 and LP240200546"],"award-info":[{"award-number":["LP230200892 and LP240200546"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Inf. Syst."],"published-print":{"date-parts":[[2025,7,31]]},"abstract":"<jats:p>GNN-based recommender systems have become increasingly popular in academia and industry due to their ability to capture high-order information from user-item interaction graphs. However, as recommendation services scale rapidly and their deployment now commonly involves resource-constrained edge devices, GNN-based models face significant challenges, including high embedding storage costs and run-time latency from graph propagations. Our previous work, LEGCF, effectively reduced embedding storage costs but struggled to maintain recommendation performance under stricter storage limits. Additionally, LEGCF did not address the extensive run-time computation costs associated with graph propagation, which involves heavy multiplication and accumulation operations (MACs). These challenges consequently hinder effective training and inference on resource-constrained edge devices. To address these limitations, we propose Lightweight Embeddings with Rewired Graph (LERG) for Graph Collaborative Filtering, an improved extension of LEGCF. LERG retains LEGCF\u2019s compositional codebook structure but introduces quantization techniques to reduce the storage cost of embedding weights, enabling the inclusion of more meta-embeddings within the same storage constraints for improved model expressiveness. To optimize graph propagation for edge devices, we pretrain the quantized compositional embedding table using the full interaction graph on resource-rich servers, after which a fine-tuning stage is engaged to identify and prune low-contribution entities via a gradient-free binary integer programming approach, constructing a rewired graph that excludes these entities (i.e., user\/item nodes) from propagating signals. The quantized compositional embedding table with selective embedding participation and sparse rewired graph is transferred to edge devices which significantly reduce computation memory and inference time. Experiments on three public benchmark datasets, including an industry-scale dataset, demonstrate that LERG achieves superior recommendation performance while dramatically reducing storage and computation costs for graph-based recommendation services.<\/jats:p>","DOI":"10.1145\/3742424","type":"journal-article","created":{"date-parts":[[2025,6,2]],"date-time":"2025-06-02T11:48:00Z","timestamp":1748864880000},"page":"1-29","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Lightweight Embeddings with Graph Rewiring for Collaborative Filtering"],"prefix":"10.1145","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3458-3887","authenticated-orcid":false,"given":"Xurong","family":"Liang","sequence":"first","affiliation":[{"name":"The University of Queensland, Brisbane, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7269-146X","authenticated-orcid":false,"given":"Tong","family":"Chen","sequence":"additional","affiliation":[{"name":"The University of Queensland, Brisbane, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9400-842X","authenticated-orcid":false,"given":"Wei","family":"Yuan","sequence":"additional","affiliation":[{"name":"The University of Queensland, Brisbane, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1395-261X","authenticated-orcid":false,"given":"Hongzhi","family":"Yin","sequence":"additional","affiliation":[{"name":"The University of Queensland, Brisbane, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,7,10]]},"reference":[{"key":"e_1_3_3_2_2","unstructured":"Yoshua Bengio Nicholas L\u00e9onard and Aaron Courville. 2013. Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv:1308.3432. Retrieved from https:\/\/arxiv.org\/abs\/1308.3432"},{"key":"e_1_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/157485.165117"},{"key":"e_1_3_3_4_2","volume-title":"ICLR","author":"Chen Jie","year":"2018","unstructured":"Jie Chen, Tengfei Ma, and Cao Xiao. 2018. Fastgcn: Fast learning with graph convolutional networks via importance sampling. In ICLR."},{"key":"e_1_3_3_5_2","volume-title":"ICML","author":"Chen Jianfei","year":"2018","unstructured":"Jianfei Chen, Jun Zhu, and Le Song. 2018. Stochastic training of graph convolutional networks with variance reduction. In ICML."},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5330"},{"key":"e_1_3_3_7_2","unstructured":"Mengzhao Chen Wenqi Shao Peng Xu Jiahao Wang Peng Gao Kaipeng Zhang Yu Qiao and Ping Luo. 2024. EfficientQAT: Efficient quantization-aware training for large language models. arXiv:2407.11062. Retrieved from https:\/\/arxiv.org\/abs\/2407.11062"},{"key":"e_1_3_3_8_2","article-title":"Scalable graph neural networks via bidirectional propagation","author":"Chen Ming","year":"2020","unstructured":"Ming Chen, Zhewei Wei, Bolin Ding, Yaliang Li, Ye Yuan, Xiaoyong Du, and Ji-Rong Wen. 2020. Scalable graph neural networks via bidirectional propagation. In NeurIPS.","journal-title":"NeurIPS"},{"key":"e_1_3_3_9_2","volume-title":"ICML","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 ICML."},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467220"},{"key":"e_1_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330652"},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330925"},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/87252.88081"},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242610"},{"key":"e_1_3_3_16_2","unstructured":"Aditya Desai Yanzhou Pan Kuangyuan Sun Li Chou and Anshumali Shrivastava. 2021. Semantically constrained memory allocation (SCMA) for embedding in efficient recommendation systems. arXiv:2103.06124. Retrieved from https:\/\/arxiv.org\/abs\/2103.06124"},{"key":"e_1_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3575637.3575646"},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.7"},{"key":"e_1_3_3_19_2","volume-title":"ICLR","author":"Esser Steven K.","year":"2020","unstructured":"Steven K. Esser, Jeffrey L. McKinstry, Deepika Bablani, Rathinakumar Appuswamy, and Dharmendra S. Modha. 2020. Learned Step Size Quantization. In ICLR."},{"key":"e_1_3_3_20_2","volume-title":"WWW","author":"Fan Wenqi","year":"2019","unstructured":"Wenqi Fan, Yao Ma, Qing Li, Yuan He, Eric Zhao, Jiliang Tang, and Dawei Yin. 2019. Graph neural networks for social recommendation. In WWW."},{"key":"e_1_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3568022"},{"key":"e_1_3_3_22_2","unstructured":"Hui Guan Andrey Malevich Jiyan Yang Jongsoo Park and Hector Yuen. 2019. Post-training 4-bit quantization on embedding tables. arXiv:1911.02079. Retrieved from https:\/\/arxiv.org\/abs\/1911.02079"},{"key":"e_1_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3680021"},{"issue":"4","key":"e_1_3_3_24_2","first-page":"781","article-title":"MultiBiSage: A web-scale recommendation system using multiple bipartite graphs at pinterest","volume":"16","author":"Gurukar Saket","year":"2022","unstructured":"Saket Gurukar, Nikil Pancha, Andrew Zhai, Eric Kim, Samson Hu, Srinivasan Parthasarathy, Charles Rosenberg, and Jure Leskovec. 2022. MultiBiSage: A web-scale recommendation system using multiple bipartite graphs at pinterest. The International Journal on Very Large Data Bases 16, 4 (2022), 781\u2013789.","journal-title":"The International Journal on Very Large Data Bases"},{"key":"e_1_3_3_25_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 NeurIPS, Vol. 30.","journal-title":"NeurIPS"},{"key":"e_1_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401063"},{"key":"e_1_3_3_27_2","article-title":"Adaptive sampling towards fast graph representation learning","volume":"31","author":"Huang Wenbing","year":"2018","unstructured":"Wenbing Huang, Tong Zhang, Yu Rong, and Junzhou Huang. 2018. Adaptive sampling towards fast graph representation learning. In NeurIPS, Vol. 31.","journal-title":"NeurIPS"},{"key":"e_1_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403288"},{"key":"e_1_3_3_29_2","first-page":"219","volume-title":"Reducibility Among Combinatorial Problems","author":"Karp Richard M.","year":"2009","unstructured":"Richard M. Karp. 2009. Reducibility Among Combinatorial Problems. Springer, 219\u2013241 pages."},{"key":"e_1_3_3_30_2","unstructured":"George Karypis and Vipin Kumar. 1998. A software package for partitioning unstructured graphs partitioning meshes and computing fill-reducing orderings of sparse matrices. University of Minnesota Department of Computer Science and Engineering Army HPC Research Center Minneapolis MN."},{"key":"e_1_3_3_31_2","unstructured":"Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv:1412.6980. Retrieved from https:\/\/arxiv.org\/abs\/1412.6980"},{"key":"e_1_3_3_32_2","volume-title":"ICLR","author":"Kipf Thomas N.","year":"2017","unstructured":"Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In ICLR."},{"issue":"2","key":"e_1_3_3_33_2","first-page":"544","article-title":"Dual contrastive learning for efficient static feature representation in sequential recommendations","volume":"36","author":"Li Pan","year":"2023","unstructured":"Pan Li, Maofei Que, and Alexander Tuzhilin. 2023. Dual contrastive learning for efficient static feature representation in sequential recommendations. IEEE Transactions on Knowledge and Data Engineering 36, 2 (2023), 544\u2013555.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25564"},{"key":"e_1_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3637841"},{"key":"e_1_3_3_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482448"},{"key":"e_1_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380151"},{"key":"e_1_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2964232"},{"key":"e_1_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657820"},{"key":"e_1_3_3_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM58522.2023.00047"},{"key":"e_1_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421281"},{"key":"e_1_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/MIC.2003.1167344"},{"key":"e_1_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM50108.2020.00045"},{"key":"e_1_3_3_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401436"},{"key":"e_1_3_3_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467441"},{"key":"e_1_3_3_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599889"},{"key":"e_1_3_3_47_2","volume-title":"ICLR","author":"Liu Siyi","year":"2021","unstructured":"Siyi Liu, Chen Gao, Yihong Chen, Depeng Jin, and Yong Li. 2021. Learnable embedding sizes for recommender systems. In ICLR."},{"key":"e_1_3_3_48_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/245"},{"key":"e_1_3_3_49_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/772"},{"key":"e_1_3_3_50_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.26"},{"key":"e_1_3_3_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"e_1_3_3_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3555374"},{"key":"e_1_3_3_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671743"},{"key":"e_1_3_3_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557411"},{"key":"e_1_3_3_55_2","unstructured":"Shuming Ma Hongyu Wang Lingxiao Ma Lei Wang Wenhui Wang Shaohan Huang Li Dong Ruiping Wang Jilong Xue and Furu Wei. 2024. The era of 1-bit llms: All large language models are in 1.58 bits. arXiv:2402.17764. Retrieved from https:\/\/arxiv.org\/abs\/2402.17764"},{"key":"e_1_3_3_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3410530.3414370"},{"key":"e_1_3_3_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482291"},{"key":"e_1_3_3_58_2","unstructured":"Markus Nagel Marios Fournarakis Rana Ali Amjad Yelysei Bondarenko Mart Van Baalen and Tijmen Blankevoort. 2021. A white paper on neural network quantization. arXiv:2106.08295. Retrieved from https:\/\/arxiv.org\/abs\/2106.08295"},{"key":"e_1_3_3_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403280"},{"key":"e_1_3_3_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532060"},{"key":"e_1_3_3_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635778"},{"key":"e_1_3_3_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591653"},{"key":"e_1_3_3_63_2","unstructured":"Yunke Qu Liang Qu Tong Chen Xiangyu Zhao Jianxin Li and Hongzhi Yin. 2024. Sparser training for on-device recommendation systems. arXiv:2411.12205. Retrieved from https:\/\/arxiv.org\/abs\/2411.12205"},{"key":"e_1_3_3_64_2","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679638"},{"key":"e_1_3_3_65_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3614305"},{"key":"e_1_3_3_66_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.127"},{"key":"e_1_3_3_67_2","first-page":"452","volume-title":"UAI","author":"Rendle Steffen","year":"2009","unstructured":"Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme. 2009. BPR: Bayesian personalized ranking from implicit feedback. In UAI, 452\u2013461."},{"key":"e_1_3_3_68_2","volume-title":"ICLR","author":"Rong Yu","year":"2020","unstructured":"Yu Rong, Wenbing Huang, Tingyang Xu, and Junzhou Huang. 2020. Dropedge: Towards deep graph convolutional networks on node classification. In ICLR."},{"key":"e_1_3_3_69_2","volume-title":"Theory of Linear and Integer Programming","author":"Schrijver A.","year":"1998","unstructured":"A. Schrijver. 1998. Theory of Linear and Integer Programming. John Wiley & Sons."},{"key":"e_1_3_3_70_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403059"},{"key":"e_1_3_3_71_2","volume-title":"WWW","author":"Sun Jianing","year":"2021","unstructured":"Jianing Sun, Zhaoyue Cheng, Saba Zuberi, Felipe P\u00e9rez, and Maksims Volkovs. 2021. Hgcf: Hyperbolic graph convolution networks for collaborative filtering. In WWW."},{"key":"e_1_3_3_72_2","article-title":"Ultra-low precision 4-bit training of deep neural networks","volume":"33","author":"Sun Xiao","year":"2020","unstructured":"Xiao Sun, Naigang Wang, Chia-Yu Chen, Jiamin Ni, Ankur Agrawal, Xiaodong Cui, Swagath Venkataramani, Kaoutar El Maghraoui, Vijayalakshmi Viji Srinivasan, and Kailash Gopalakrishnan. 2020. Ultra-low precision 4-bit training of deep neural networks. In NeurIPS, Vol. 33.","journal-title":"NeurIPS"},{"key":"e_1_3_3_73_2","volume-title":"ICLR","author":"Topping Jake","year":"2022","unstructured":"Jake Topping, Francesco Di Giovanni, Benjamin Paul Chamberlain, Xiaowen Dong, and Michael M. Bronstein. 2022. Understanding over-squashing and bottlenecks on graphs via curvature. In ICLR."},{"key":"e_1_3_3_74_2","first-page":"1","volume-title":"ACM Transactions on Information Systems","author":"Vinh Tran Hung","year":"2025","unstructured":"Hung Vinh Tran, Tong Chen, Nguyen Quoc Viet Hung, Zi Huang, Lizhen Cui, and Hongzhi Yin. 2025. A thorough performance benchmarking on lightweight embedding-based recommender systems. ACM Transactions on Information Systems 43, 3 (2025), 1\u201332."},{"key":"e_1_3_3_75_2","first-page":"772","volume-title":"WWW","author":"Vinh Tran Hung","year":"2025","unstructured":"Hung Vinh Tran, Tong Chen, Guanhua Ye, Quoc Viet Hung Nguyen, Kai Zheng, and Hongzhi Yin. 2025. On-device content-based recommendation with single-shot embedding pruning: A cooperative game perspective. In WWW, 772\u2013785."},{"key":"e_1_3_3_76_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-007-9033-z"},{"key":"e_1_3_3_77_2","unstructured":"Zhongwei Wan Xin Wang Che Liu Samiul Alam Yu Zheng Jiachen Liu Zhongnan Qu Shen Yan Yi Zhu Quanlu Zhang et al. 2023. Efficient large language models: A survey. arXiv:2312.03863. Retrieved from https:\/\/arxiv.org\/abs\/2312.03863"},{"key":"e_1_3_3_78_2","unstructured":"Hongyu Wang Shuming Ma Li Dong Shaohan Huang Huaijie Wang Lingxiao Ma Fan Yang Ruiping Wang Yi Wu and Furu Wei. 2023. BitNet: Scaling 1-bit transformers for large language models."},{"key":"e_1_3_3_79_2","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219869"},{"key":"e_1_3_3_80_2","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380170"},{"key":"e_1_3_3_81_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-021-00700-6"},{"key":"e_1_3_3_82_2","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331267"},{"issue":"6","key":"e_1_3_3_83_2","article-title":"A theoretical analysis of NDCG ranking measures","volume":"8","author":"Wang Yining","year":"2013","unstructured":"Yining Wang, Liwei Wang, Yuanzhi Li, Di He, Wei Chen, and Tie-Yan Liu. 2013. A theoretical analysis of NDCG ranking measures. In COLT, Vol. 8, 6.","journal-title":"COLT"},{"key":"e_1_3_3_84_2","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2024.3393230"},{"key":"e_1_3_3_85_2","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553516"},{"key":"e_1_3_3_86_2","volume-title":"ICML","author":"Wu Felix","year":"2019","unstructured":"Felix Wu, Amauri Souza, Tianyi Zhang, Christopher Fifty, Tao Yu, and Kilian Weinberger. 2019. Simplifying graph convolutional networks. In ICML."},{"key":"e_1_3_3_87_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462862"},{"key":"e_1_3_3_88_2","doi-asserted-by":"publisher","DOI":"10.1145\/3535101"},{"key":"e_1_3_3_89_2","first-page":"37524","volume-title":"ICML","author":"Wu Xiaoxia","year":"2023","unstructured":"Xiaoxia Wu, Cheng Li, Reza Yazdani Aminabadi, Zhewei Yao, and Yuxiong He. 2023. Understanding int4 quantization for language models: latency speedup, composability, and failure cases. In ICML, 37524\u201337539."},{"key":"e_1_3_3_90_2","article-title":"Training transformers with 4-bit integers","volume":"36","author":"Xi Haocheng","year":"2023","unstructured":"Haocheng Xi, Changhao Li, Jianfei Chen, and Jun Zhu. 2023. Training transformers with 4-bit integers. In NeurIPS 36 (2023).","journal-title":"NeurIPS"},{"key":"e_1_3_3_91_2","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531775"},{"issue":"4","key":"e_1_3_3_92_2","article-title":"Efficient on-device session-based recommendation","volume":"41","author":"Xia Xin","year":"2023","unstructured":"Xin Xia, Junliang Yu, Qinyong Wang, Chaoqun Yang, Nguyen Quoc Viet Hung, and Hongzhi Yin. 2023. Efficient on-device session-based recommendation. ACM Transactions on Information Systems 41, 4 (2023).","journal-title":"ACM Transactions on Information Systems"},{"key":"e_1_3_3_93_2","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615088"},{"key":"e_1_3_3_94_2","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457236"},{"key":"e_1_3_3_95_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539263"},{"key":"e_1_3_3_96_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/563"},{"key":"e_1_3_3_97_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467097"},{"key":"e_1_3_3_98_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3332671"},{"key":"e_1_3_3_99_2","volume-title":"ICML","author":"Yao Zhewei","year":"2021","unstructured":"Zhewei Yao, Zhen Dong, Zhangcheng Zheng, Amir Gholami, Jiali Yu, Eric Tan, Leyuan Wang, Qijing Huang, Yida Wang, Michael Mahoney, et al. 2021. Hawq-v3: Dyadic neural network quantization. In ICML."},{"issue":"2021","key":"e_1_3_3_100_2","first-page":"448","article-title":"TT-REC: Tensor train compression for deep learning recommendation model embeddings","volume":"3","author":"Yin Chunxing","year":"2021","unstructured":"Chunxing Yin, Bilge Acun, Carole-Jean Wu, and Xing Liu. 2021. TT-REC: Tensor train compression for deep learning recommendation model embeddings. Proceedings of Machine Learning and Systems 3 (2021), 448\u2013462.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_3_101_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539423"},{"key":"e_1_3_3_102_2","unstructured":"Hongzhi Yin Liang Qu Tong Chen Wei Yuan Ruiqi Zheng Jing Long Xin Xia Yuhui Shi and Chengqi Zhang. 2024. On-device recommender systems: A comprehensive survey."},{"key":"e_1_3_3_103_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3288135"},{"key":"e_1_3_3_104_2","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531937"},{"key":"e_1_3_3_105_2","volume-title":"ICLR","author":"Zeng Hanqing","year":"2020","unstructured":"Hanqing Zeng, Hongkuan Zhou, Ajitesh Srivastava, Rajgopal Kannan, and Viktor Prasanna. 2020. Graphsaint: Graph sampling based inductive learning method. In ICLR."},{"key":"e_1_3_3_106_2","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412227"},{"issue":"2","key":"e_1_3_3_107_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3466641","article-title":"Multi-graph heterogeneous interaction fusion for social recommendation","volume":"40","author":"Zhang Chengyuan","year":"2021","unstructured":"Chengyuan Zhang, Yang Wang, Lei Zhu, Jiayu Song, and Hongzhi Yin. 2021. Multi-graph heterogeneous interaction fusion for social recommendation. ACM Transactions on Information Systems 40, 2 (2021), 1\u201326.","journal-title":"ACM Transactions on Information Systems"},{"key":"e_1_3_3_108_2","doi-asserted-by":"publisher","DOI":"10.1145\/3578361"},{"key":"e_1_3_3_109_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20356"},{"key":"e_1_3_3_110_2","first-page":"896","volume-title":"ICDM","author":"Zhao Xiangyu","year":"2021","unstructured":"Xiangyu Zhao, Haochen Liu, Wenqi Fan, Hui Liu, Jiliang Tang, Chong Wang, Ming Chen, Xudong Zheng, Xiaobing Liu, and Xiwang Yang. 2021. Autoemb: Automated embedding dimensionality search in streaming recommendations. In ICDM, 896\u2013905."},{"key":"e_1_3_3_111_2","volume-title":"ICML","author":"Zheng Cheng","year":"2020","unstructured":"Cheng Zheng, Bo Zong, Wei Cheng, Dongjin Song, Jingchao Ni, Wenchao Yu, Haifeng Chen, and Wei Wang. 2020. Robust graph representation learning via neural sparsification. In ICML."},{"key":"e_1_3_3_112_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3361562"},{"key":"e_1_3_3_113_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2025.3546686"},{"key":"e_1_3_3_114_2","article-title":"Layer-dependent importance sampling for training deep and large graph convolutional networks","volume":"32","author":"Zou Difan","year":"2019","unstructured":"Difan Zou, Ziniu Hu, Yewen Wang, Song Jiang, Yizhou Sun, and Quanquan Gu. 2019. Layer-dependent importance sampling for training deep and large graph convolutional networks. In NeurIPS, Vol. 32.","journal-title":"NeurIPS"}],"container-title":["ACM Transactions on Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3742424","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T21:55:52Z","timestamp":1767909352000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3742424"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,10]]},"references-count":113,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,7,31]]}},"alternative-id":["10.1145\/3742424"],"URL":"https:\/\/doi.org\/10.1145\/3742424","relation":{},"ISSN":["1046-8188","1558-2868"],"issn-type":[{"value":"1046-8188","type":"print"},{"value":"1558-2868","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,10]]},"assertion":[{"value":"2025-01-21","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-23","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}