{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T10:14:43Z","timestamp":1775470483254,"version":"3.50.1"},"reference-count":188,"publisher":"Association for Computing Machinery (ACM)","issue":"9","license":[{"start":{"date-parts":[[2021,10,8]],"date-time":"2021-10-08T00:00:00Z","timestamp":1633651200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"European Union\u2019s Horizon 2020 Research and Innovation Programme","award":["863337 (WiPLASH project)"],"award-info":[{"award-number":["863337 (WiPLASH project)"]}]},{"name":"Spanish Ministry of Economy and Competitiveness","award":["TEC2017-90034-C2-1-R (ALLIANCE project)"],"award-info":[{"award-number":["TEC2017-90034-C2-1-R (ALLIANCE project)"]}]},{"DOI":"10.13039\/501100008530","name":"FEDER","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100008530","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Comput. Surv."],"published-print":{"date-parts":[[2022,12,31]]},"abstract":"<jats:p>Graph Neural Networks (GNNs) have exploded onto the machine learning scene in recent years owing to their capability to model and learn from graph-structured data. Such an ability has strong implications in a wide variety of fields whose data are inherently relational, for which conventional neural networks do not perform well. Indeed, as recent reviews can attest, research in the area of GNNs has grown rapidly and has lead to the development of a variety of GNN algorithm variants as well as to the exploration of ground-breaking applications in chemistry, neurology, electronics, or communication networks, among others. At the current stage research, however, the efficient processing of GNNs is still an open challenge for several reasons. Besides of their novelty, GNNs are hard to compute due to their dependence on the input graph, their combination of dense and very sparse operations, or the need to scale to huge graphs in some applications. In this context, this article aims to make two main contributions. On the one hand, a review of the field of GNNs is presented from the perspective of computing. This includes a brief tutorial on the GNN fundamentals, an overview of the evolution of the field in the last decade, and a summary of operations carried out in the multiple phases of different GNN algorithm variants. On the other hand, an in-depth analysis of current software and hardware acceleration schemes is provided, from which a hardware-software, graph-aware, and communication-centric vision for GNN accelerators is distilled.<\/jats:p>","DOI":"10.1145\/3477141","type":"journal-article","created":{"date-parts":[[2021,10,8]],"date-time":"2021-10-08T22:02:57Z","timestamp":1633730577000},"page":"1-38","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":223,"title":["Computing Graph Neural Networks: A Survey from Algorithms to Accelerators"],"prefix":"10.1145","volume":"54","author":[{"given":"Sergi","family":"Abadal","sequence":"first","affiliation":[{"name":"Universitat Polit\u00e8cnica de Catalunya, Spain"}]},{"given":"Akshay","family":"Jain","sequence":"additional","affiliation":[{"name":"Universitat Polit\u00e8cnica de Catalunya, Spain"}]},{"given":"Robert","family":"Guirado","sequence":"additional","affiliation":[{"name":"Universitat Polit\u00e8cnica de Catalunya, Spain"}]},{"given":"Jorge","family":"L\u00f3pez-Alonso","sequence":"additional","affiliation":[{"name":"Universitat Polit\u00e8cnica de Catalunya, Spain"}]},{"given":"Eduard","family":"Alarc\u00f3n","sequence":"additional","affiliation":[{"name":"Universitat Polit\u00e8cnica de Catalunya, Spain"}]}],"member":"320","published-online":{"date-parts":[[2021,10,8]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"2019. Build Graph Nets in Tensorflow. Retrieved from https:\/\/github.com\/deepmind\/graph_nets.  2019. Build Graph Nets in Tensorflow. Retrieved from https:\/\/github.com\/deepmind\/graph_nets."},{"key":"e_1_2_1_2_1","unstructured":"2019. Food Discovery with Uber Eats: Using Graph Learning to Power Recommendations. Retrieved from https:\/\/eng.uber.com\/uber-eats-graph-learning.  2019. Food Discovery with Uber Eats: Using Graph Learning to Power Recommendations. Retrieved from https:\/\/eng.uber.com\/uber-eats-graph-learning."},{"key":"e_1_2_1_3_1","unstructured":"2020. PaddlePaddle\/PGL. Retrieved from https:\/\/github.com\/PaddlePaddle\/PGL.  2020. PaddlePaddle\/PGL. Retrieved from https:\/\/github.com\/PaddlePaddle\/PGL."},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00023"},{"key":"e_1_2_1_5_1","unstructured":"Luis B. Almeida. 1990. A learning rule for asynchronous perceptrons with feedback in a combinatorial environment. In Artificial Neural Networks: Concept Learning. 102\u2013111.  Luis B. Almeida. 1990. A learning rule for asynchronous perceptrons with feedback in a combinatorial environment. In Artificial Neural Networks: Concept Learning. 102\u2013111."},{"key":"e_1_2_1_6_1","unstructured":"James Atwood and Don Towsley. 2016. Diffusion-convolutional neural networks. In Advances in Neural Information Processing Systems. 1993\u20132001.  James Atwood and Don Towsley. 2016. Diffusion-convolutional neural networks. In Advances in Neural Information Processing Systems. 1993\u20132001."},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218751"},{"key":"e_1_2_1_8_1","unstructured":"Matej Balog Bart van Merri\u00ebnboer Subhodeep Moitra Yujia Li and Daniel Tarlow. 2019. Fast training of sparse graph neural networks on dense hardware. arXiv:1906.11786. Retrieved from https:\/\/arxiv.org\/abs\/1906.11786.  Matej Balog Bart van Merri\u00ebnboer Subhodeep Moitra Yujia Li and Daniel Tarlow. 2019. Fast training of sparse graph neural networks on dense hardware. arXiv:1906.11786. Retrieved from https:\/\/arxiv.org\/abs\/1906.11786."},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2010.5596634"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS51385.2021.00013"},{"key":"e_1_2_1_11_1","volume-title":"et\u00a0al","author":"Battaglia Peter W.","year":"2018"},{"key":"e_1_2_1_12_1","unstructured":"Peter W. Battaglia Razvan Pascanu Matthew Lai Danilo Rezende and Koray Kavukcuoglu. 2016. Interaction networks for learning about objects relations and physics. In Advances in Neural Information Processing Systems 4502\u20134510.  Peter W. Battaglia Razvan Pascanu Matthew Lai Danilo Rezende and Koray Kavukcuoglu. 2016. Interaction networks for learning about objects relations and physics. In Advances in Neural Information Processing Systems 4502\u20134510."},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.07.003"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2019.02.006"},{"key":"e_1_2_1_15_1","unstructured":"Xavier Bresson and Thomas Laurent. 2017. Residual gated graph convnets. arXiv:1711.07553. Retrieved from https:\/\/arxiv.org\/abs\/1711.07553.  Xavier Bresson and Thomas Laurent. 2017. Residual gated graph convnets. arXiv:1711.07553. Retrieved from https:\/\/arxiv.org\/abs\/1711.07553."},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2693418"},{"key":"e_1_2_1_17_1","volume-title":"Berger-Wolf","author":"Brugere Ivan","year":"2018"},{"key":"e_1_2_1_18_1","volume-title":"Proceedings of the 2nd International Conference on Learning Representations (ICLR\u201914)","author":"Bruna Joan","year":"2014"},{"key":"e_1_2_1_19_1","unstructured":"Ines Chami Sami Abu-El-Haija Bryan Perozzi Christopher R\u00e9 and Kevin Murphy. 2020. Machine learning on graphs: A model and comprehensive taxonomy. arXiv:2005.03675. Retrieved from https:\/\/arxiv.org\/abs\/2005.03675.  Ines Chami Sami Abu-El-Haija Bryan Perozzi Christopher R\u00e9 and Kevin Murphy. 2020. Machine learning on graphs: A model and comprehensive taxonomy. arXiv:2005.03675. Retrieved from https:\/\/arxiv.org\/abs\/2005.03675."},{"key":"e_1_2_1_20_1","volume-title":"Proceedings of the 6th International Conference on Learning Representations (ICLR\u201918)","author":"Chen Jie","year":"2018"},{"key":"e_1_2_1_21_1","volume-title":"Proceedings of the 35th International Conference on Machine Learning (ICML\u201918)","author":"Chen Jianfei","year":"2018"},{"key":"e_1_2_1_22_1","volume-title":"Proceedings of the International Conference on Machine Learning. 1725\u20131735","author":"Chen Ming","year":"2020"},{"key":"e_1_2_1_23_1","volume-title":"Rubik: A hierarchical architecture for efficient graph neural network training","author":"Chen Xiaobing","year":"2021"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2616357"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2019.2910232"},{"key":"e_1_2_1_26_1","volume-title":"Proceedings of the 7th International Conference on Learning Representations (ICLR\u201919)","author":"Chen Zhengdao","year":"2019"},{"key":"e_1_2_1_27_1","unstructured":"Zhiqian Chen Fanglan Chen Lei Zhang Taoran Ji Kaiqun Fu Liang Zhao Feng Chen and Chang-Tien Lu. 2020. Bridging the gap between spatial and spectral domains: A survey on graph neural networks. arXiv:2002.11867. Retrieved from https:\/\/arxiv.org\/abs\/2002.11867.  Zhiqian Chen Fanglan Chen Lei Zhang Taoran Ji Kaiqun Fu Liang Zhao Feng Chen and Chang-Tien Lu. 2020. Bridging the gap between spatial and spectral domains: A survey on graph neural networks. arXiv:2002.11867. Retrieved from https:\/\/arxiv.org\/abs\/2002.11867."},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330925"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330925"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2018.2849727"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2950416"},{"key":"e_1_2_1_33_1","volume-title":"Proceedings of the 7th International Conference on Learning Representations.","author":"Das Rajarshi","year":"2018"},{"key":"e_1_2_1_34_1","unstructured":"Shail Dave Riyadh Baghdadi Tony Nowatzki Sasikanth Avancha Aviral Shrivastava and Baoxin Li. 2020. Hardware acceleration of sparse and irregular tensor computations of ML models: A survey and insights. arXiv:2007.00864. https:\/\/arxiv.org\/abs\/2007.00864.  Shail Dave Riyadh Baghdadi Tony Nowatzki Sasikanth Avancha Aviral Shrivastava and Baoxin Li. 2020. Hardware acceleration of sparse and irregular tensor computations of ML models: A survey and insights. arXiv:2007.00864. https:\/\/arxiv.org\/abs\/2007.00864."},{"key":"e_1_2_1_35_1","volume-title":"Proceedings of the ICML Workshop on Theoretical Foundations and Applications of Deep Generative Models.","author":"Cao Nicola De","year":"2018"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/1327452.1327492"},{"key":"e_1_2_1_37_1","unstructured":"Micha\u00ebl Defferrard Xavier Bresson and Pierre Vandergheynst. 2016. Convolutional neural networks on graphs with fast localized spectral filtering. In Advances in Neural Information Processing Systems. 3844\u20133852.  Micha\u00ebl Defferrard Xavier Bresson and Pierre Vandergheynst. 2016. Convolutional neural networks on graphs with fast localized spectral filtering. In Advances in Neural Information Processing Systems. 3844\u20133852."},{"key":"e_1_2_1_38_1","volume-title":"Proceedings of the IEEE International Conference on Neural Networks, 778\u2013785","author":"Massa Vincenzo Di","year":"2006"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750389"},{"key":"e_1_2_1_40_1","unstructured":"Alberto Garcia Duran and Mathias Niepert. 2017. Learning graph representations with embedding propagation. In Advances in Neural Information Processing Systems. 5119\u20135130.  Alberto Garcia Duran and Mathias Niepert. 2017. Learning graph representations with embedding propagation. In Advances in Neural Information Processing Systems. 5119\u20135130."},{"key":"e_1_2_1_41_1","volume-title":"Adams","author":"Duvenaud David","year":"2015"},{"key":"e_1_2_1_42_1","volume-title":"Proceedings of the ICML Workshop on Graph Representation Learning and Beyond.","author":"Dwivedi Vijay Prakash","year":"2020"},{"key":"e_1_2_1_43_1","volume-title":"Dermatologist-level classification of skin cancer with deep neural networks.Nature 542, 7639","author":"Esteva Andre","year":"2017"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313488"},{"key":"e_1_2_1_45_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR\u201919)","author":"Fey Matthias","year":"2019"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.physrep.2009.11.002"},{"key":"e_1_2_1_47_1","unstructured":"Alex Fout Jonathon Byrd Basir Shariat and Asa Ben-Hur. 2017. Protein interface prediction using graph convolutional networks. Adv. Neural Inf. Process. Syst.6531\u20136540.  Alex Fout Jonathon Byrd Basir Shariat and Asa Ben-Hur. 2017. Protein interface prediction using graph convolutional networks. Adv. Neural Inf. Process. Syst.6531\u20136540."},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219947"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01154"},{"key":"e_1_2_1_50_1","volume-title":"Proceedings of the International Conference on Learning Representations.","author":"Garcia Victor","year":"2018"},{"key":"e_1_2_1_51_1","volume-title":"Robert Guirado, Akshay Jain, Sergi Abadal, Jos\u00e9 L. Abell\u00e1n, Manuel E. Acacio, Eduard Alarc\u00f3n, Sivasankaran Rajamanickam, and Tushar Krishna.","author":"Garg Raveesh","year":"2021"},{"key":"e_1_2_1_52_1","volume-title":"On graph kernels: Hardness results and efficient alternatives","author":"G\u00e4rtner Thomas"},{"key":"e_1_2_1_53_1","volume-title":"Proceedings of the 53rd Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO\u201920)","author":"Geng Tong"},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013656"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2017.11.002"},{"key":"e_1_2_1_56_1","volume-title":"Proceedings of the 34th International Conference on Machine Learning. 2053\u20132070","author":"Gilmer Justin"},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2005.1555942"},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2020.3039072"},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-019-1914-z"},{"key":"e_1_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS51556.2021.9401612"},{"key":"e_1_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301922"},{"key":"e_1_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2011.02.068"},{"key":"e_1_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783759"},{"key":"e_1_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/250"},{"key":"e_1_2_1_65_1","unstructured":"William L. Hamilton Rex Ying and Jure Leskovec. 2017. Inductive representation learning on large graphs. In Advances in Neural Information Processing Systems. 1025\u20131035.  William L. Hamilton Rex Ying and Jure Leskovec. 2017. Inductive representation learning on large graphs. In Advances in Neural Information Processing Systems. 1025\u20131035."},{"key":"e_1_2_1_66_1","first-page":"52","article-title":"Representation learning on graphs: Methods and applications","volume":"40","author":"Hamilton William L.","year":"2017","journal-title":"IEEE Data Eng. Bull."},{"key":"e_1_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00062"},{"key":"e_1_2_1_69_1","unstructured":"Mikael Henaff Joan Bruna and Yann LeCun. 2015. Deep convolutional networks on graph-structured data. arXiv:1506.05163. Retrieved from https:\/\/arxiv.org\/abs\/1506.05163.  Mikael Henaff Joan Bruna and Yann LeCun. 2015. Deep convolutional networks on graph-structured data. arXiv:1506.05163. Retrieved from https:\/\/arxiv.org\/abs\/1506.05163."},{"key":"e_1_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/1014052.1014072"},{"key":"e_1_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/630"},{"key":"e_1_2_1_72_1","first-page":"22118","article-title":"Open graph benchmark: Datasets for machine learning on graphs","volume":"33","author":"Hu Weihua","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_73_1","volume-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis.","author":"Hu Yuwei","year":"2020"},{"key":"e_1_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00076"},{"key":"e_1_2_1_75_1","volume-title":"Proceedings of the International Symposium on Physical Design. 145\u2013149","author":"James Michael","year":"2020"},{"key":"e_1_2_1_76_1","volume-title":"Proceedings of the Conference on Machine Learning and Systems (MLSys\u201920)","author":"Jia Zhihao","year":"2020"},{"key":"e_1_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403142"},{"key":"e_1_2_1_78_1","volume-title":"Proceedings of the Conference on Machine Learning and Systems (SysML\u201919)","author":"Jia Zhihao","year":"2019"},{"key":"e_1_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/369"},{"key":"e_1_2_1_80_1","volume-title":"Proceedings of the 2nd Workshop on Machine Learning and the Physical Sciences (NeurIPS\u201919)","author":"Ju Xiangyang","year":"2019"},{"key":"e_1_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1137\/S1064827595287997"},{"key":"e_1_2_1_82_1","unstructured":"Tatsuro Kawamoto Masashi Tsubaki and Tomoyuki Obuchi. 2018. Mean-field theory of graph neural networks in graph partitioning. In Advances in Neural Information Processing Systems. 4361\u20134371.  Tatsuro Kawamoto Masashi Tsubaki and Tomoyuki Obuchi. 2018. Mean-field theory of graph neural networks in graph partitioning. In Advances in Neural Information Processing Systems. 4361\u20134371."},{"key":"e_1_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2020.00630"},{"key":"e_1_2_1_84_1","volume-title":"Proceedings of the Workshop on Resource-Constrained Machine Learning (ReCoML\u201920)","author":"Kiningham Kevin","year":"2020"},{"key":"e_1_2_1_85_1","volume-title":"GRIP: A graph neural network accelerator architecture. arXiv:2007.13828.","author":"Kiningham Kevin","year":"2020"},{"key":"e_1_2_1_86_1","volume-title":"Proceedings of the Bayesian Deep Learning Workshop (NIPS\u201916)","author":"Thomas"},{"key":"e_1_2_1_87_1","volume-title":"Proceedings of the 5th International Conference on Learning Representations.","author":"Kipf Thomas N","year":"2017"},{"key":"e_1_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1145\/3130218.3130230"},{"key":"e_1_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2018.2877289"},{"key":"e_1_2_1_90_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173176"},{"key":"e_1_2_1_91_1","volume-title":"Vardi","author":"Lamb Luis C.","year":"2020"},{"key":"e_1_2_1_92_1","volume-title":"Deep learning. Nature 521, 7553","author":"Lecun Yann","year":"2015"},{"key":"e_1_2_1_93_1","doi-asserted-by":"publisher","DOI":"10.1145\/3363574"},{"key":"e_1_2_1_94_1","volume-title":"Proceedings of the Conference on Machine Learning and Systems (MLSys\u201919)","author":"Lerer Adam","year":"2019"},{"key":"e_1_2_1_95_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00936"},{"key":"e_1_2_1_96_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00070"},{"key":"e_1_2_1_97_1","volume-title":"Proceedings of the 32nd AAAI Conference on Artificial Intelligence. 3538\u20133545","author":"Li Qimai","year":"2018"},{"key":"e_1_2_1_98_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.448"},{"key":"e_1_2_1_99_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence.","author":"Li Ruoyu","year":"2018"},{"key":"e_1_2_1_100_1","volume-title":"Proceedings of the Medical Image Computing and Computer Assisted Intervention (MICCAI\u201920)","author":"Li Xiaoxiao"},{"key":"e_1_2_1_101_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR\u201918)","author":"Li Yujia","year":"2018"},{"key":"e_1_2_1_102_1","volume-title":"Proceedings of the 4th International Conference on Learning Representation.","author":"Li Yujia","year":"2016"},{"key":"e_1_2_1_103_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.3014632"},{"key":"e_1_2_1_104_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR\u201918)","author":"Liao Renjie"},{"key":"e_1_2_1_105_1","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415482"},{"key":"e_1_2_1_106_1","volume-title":"Proceedings of the USENIX Annual Technical Conference (USENIX ATC\u201919)","author":"Ma Lingxiao","year":"2019"},{"key":"e_1_2_1_107_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33011069"},{"key":"e_1_2_1_108_1","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3317838"},{"key":"e_1_2_1_109_1","first-page":"105","article-title":"PaddlePaddle: An open-source deep learning platform from industrial practice","volume":"1","author":"Ma Yanjun","year":"2019","journal-title":"Front. Data Comput."},{"key":"e_1_2_1_110_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.physrep.2013.08.002"},{"key":"e_1_2_1_111_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-018-3761-1"},{"key":"e_1_2_1_112_1","first-page":"665","article-title":"Graph neural networks for object localization","volume":"141","author":"Monfardini Gabriele","year":"2006","journal-title":"Front. Artif. Intell. Appl."},{"key":"e_1_2_1_113_1","unstructured":"Federico Monti Michael M. Bronstein and Xavier Bresson. 2017. Geometric matrix completion with recurrent multi-graph neural networks. In Advances in Neural Information Processing Systems. 3698\u20133708.  Federico Monti Michael M. Bronstein and Xavier Bresson. 2017. Geometric matrix completion with recurrent multi-graph neural networks. In Advances in Neural Information Processing Systems. 3698\u20133708."},{"key":"e_1_2_1_114_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.8769036"},{"key":"e_1_2_1_115_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2019.00037"},{"key":"e_1_2_1_116_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2012.12.001"},{"key":"e_1_2_1_117_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2483592"},{"key":"e_1_2_1_118_1","volume-title":"Proceedings of the 33rd International Conference on Machine Learning. 2958\u20132967","author":"Niepert Mathias","year":"2016"},{"key":"e_1_2_1_119_1","volume-title":"Proceedings of the Annual Conference on Automated Knowledge Base Construction (AKBC\u201917)","author":"O\u00f1oro-Rubio Daniel"},{"key":"e_1_2_1_120_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5984"},{"key":"e_1_2_1_121_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/447"},{"key":"e_1_2_1_122_1","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.59.2229"},{"key":"e_1_2_1_123_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220077"},{"key":"e_1_2_1_124_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1187"},{"key":"e_1_2_1_125_1","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2018.2886259"},{"key":"e_1_2_1_126_1","doi-asserted-by":"publisher","DOI":"10.1145\/3314148.3314357"},{"key":"e_1_2_1_127_1","volume-title":"Proceedings of the NeurIPS\u201919 Graph Representation Learning Workshop.","author":"Salha Guillaume","year":"2019"},{"key":"e_1_2_1_128_1","volume-title":"Proceedings of the 35th International Conference on Machine Learning. 7097\u20137117","author":"Sanchez-Gonzalez Alvaro","year":"2018"},{"key":"e_1_2_1_129_1","volume-title":"Wiltschko","author":"Sanchez-Lengeling Benjamin","year":"2019"},{"key":"e_1_2_1_130_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"e_1_2_1_131_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005141"},{"key":"e_1_2_1_132_1","doi-asserted-by":"publisher","DOI":"10.1109\/WI.2005.67"},{"key":"e_1_2_1_133_1","series-title":"Lecture Notes in Computer Science","volume-title":"Modeling Relational Data with Graph Convolutional Networks","author":"Schlichtkrull Michael","year":"2018"},{"key":"e_1_2_1_134_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00178"},{"key":"e_1_2_1_135_1","unstructured":"Hy Truong Son and Chris Jones. 2019. Graph neural networks with efficient tensor operations in CUDA\/GPU and Graphflow deep learning framework in C++ for quantum chemistry. Retrieved from http:\/\/people.cs.uchicago.edu\/ hytruongson\/CCN-GraphFlow.pdf.  Hy Truong Son and Chris Jones. 2019. Graph neural networks with efficient tensor operations in CUDA\/GPU and Graphflow deep learning framework in C++ for quantum chemistry. Retrieved from http:\/\/people.cs.uchicago.edu\/ hytruongson\/CCN-GraphFlow.pdf."},{"key":"e_1_2_1_136_1","article-title":"Message-passing neural networks for high-throughput polymer screening","volume":"150","author":"John Peter C. St.","year":"2019","journal-title":"J. Chem. Phys."},{"key":"e_1_2_1_137_1","unstructured":"Sainbayar Sukhbaatar Arthur Szlam and Rob Fergus. 2016. Learning multiagent communication with backpropagation. In Advances in Neural Information Processing Systems. 2244\u20132252.  Sainbayar Sukhbaatar Arthur Szlam and Rob Fergus. 2016. Learning multiagent communication with backpropagation. In Advances in Neural Information Processing Systems. 2244\u20132252."},{"key":"e_1_2_1_138_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"e_1_2_1_139_1","unstructured":"Zhenheng Tang Shaohuai Shi Xiaowen Chu Wei Wang and Bo Li. 2020. Communication-efficient distributed deep learning: A comprehensive survey. arXiv:2003.06307v1. Retrieved from https:\/\/arxiv.org\/abs\/2003.06307v1.  Zhenheng Tang Shaohuai Shi Xiaowen Chu Wei Wang and Bo Li. 2020. Communication-efficient distributed deep learning: A comprehensive survey. arXiv:2003.06307v1. Retrieved from https:\/\/arxiv.org\/abs\/2003.06307v1."},{"key":"e_1_2_1_140_1","unstructured":"Kiran K. Thekumparampil Chong Wang Sewoong Oh and Li-Jia Li. 2018. Attention-based graph neural network for semi-supervised learning. arXiv:1803.03735. Retrieved from https:\/\/arxiv.org\/abs\/1803.03735.  Kiran K. Thekumparampil Chong Wang Sewoong Oh and Li-Jia Li. 2018. Attention-based graph neural network for semi-supervised learning. arXiv:1803.03735. Retrieved from https:\/\/arxiv.org\/abs\/1803.03735."},{"key":"e_1_2_1_141_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS47924.2020.00100"},{"key":"e_1_2_1_142_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-015-0249-8"},{"key":"e_1_2_1_143_1","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2018.8628758"},{"key":"e_1_2_1_144_1","volume-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC). 987\u20131000","author":"Tripathy Alok"},{"key":"e_1_2_1_145_1","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems. 6000\u20136010","author":"Vaswani Ashish","year":"2017"},{"key":"e_1_2_1_146_1","volume-title":"Proceedings of the 6th International Conference on Learning Representations.","author":"Veli\u010dkovi\u0107 Petar","year":"2018"},{"key":"e_1_2_1_147_1","volume-title":"Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval. 1281\u20131284","author":"Verma Manisha","year":"2019"},{"key":"e_1_2_1_148_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330956"},{"key":"e_1_2_1_149_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.251"},{"key":"e_1_2_1_150_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447786.3456229"},{"key":"e_1_2_1_151_1","volume-title":"et\u00a0al","author":"Wang Minjie","year":"2019"},{"key":"e_1_2_1_152_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"e_1_2_1_153_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457564"},{"key":"e_1_2_1_154_1","doi-asserted-by":"publisher","DOI":"10.1145\/2851141.2851145"},{"key":"e_1_2_1_155_1","volume-title":"Proceedings of the USENIX Symposium on Operating Systems Design and Implementation (OSDI\u201921)","author":"Wang Yuke","year":"2021"},{"key":"e_1_2_1_156_1","doi-asserted-by":"publisher","DOI":"10.1145\/2384716.2384777"},{"key":"e_1_2_1_157_1","unstructured":"Boris Weisfeiler and Andrei Leman. 1968. A reduction of a graph to a canonical form and an algebra arising during this reduction.Nauchno-Techn. Inf. (1968) 2\u201316.  Boris Weisfeiler and Andrei Leman. 1968. A reduction of a graph to a canonical form and an algebra arising during this reduction.Nauchno-Techn. Inf. (1968) 2\u201316."},{"key":"e_1_2_1_158_1","volume-title":"Proceedings of the International Conference on Machine Learning. 6861\u20136871","author":"Wu Felix","year":"2019"},{"key":"e_1_2_1_159_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330950"},{"key":"e_1_2_1_160_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"e_1_2_1_161_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2915364"},{"key":"e_1_2_1_162_1","volume-title":"How powerful are graph neural networks?Proceedings of the 7th International Conference on Learning Representations","author":"Xu Keyulu","year":"2019"},{"key":"e_1_2_1_163_1","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2020.2970395"},{"key":"e_1_2_1_164_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00012"},{"key":"e_1_2_1_165_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"e_1_2_1_166_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/569"},{"key":"e_1_2_1_167_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219890"},{"key":"e_1_2_1_168_1","volume-title":"Proceedings of the 32nd International Conference on Neural Information Processing Systems. 4805\u20134815","author":"Ying Rex","year":"2018"},{"key":"e_1_2_1_169_1","volume-title":"Gnnexplainer: Generating explanations for graph neural networks. In Advances in Neural Information Processing Systems. 9244\u20139255.","author":"Ying Zhitao","year":"2019"},{"key":"e_1_2_1_170_1","volume-title":"Proceedings of the International Workshop of the Initiative for the Evaluation of XML Retrieval. Springer, 458\u2013472","author":"Yong Sweah Liang","year":"2006"},{"key":"e_1_2_1_171_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2018.2840738"},{"key":"e_1_2_1_172_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/505"},{"key":"e_1_2_1_173_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220000"},{"key":"e_1_2_1_174_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00009"},{"key":"e_1_2_1_175_1","doi-asserted-by":"publisher","DOI":"10.1145\/3373087.3375312"},{"key":"e_1_2_1_176_1","volume-title":"Proceedings of the International Conference on Learning Representations.","author":"Zeng Hanqing","year":"2019"},{"key":"e_1_2_1_177_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP49362.2020.00019"},{"key":"e_1_2_1_178_1","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415539"},{"key":"e_1_2_1_179_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00378"},{"key":"e_1_2_1_180_1","unstructured":"Muhan Zhang and Yixin Chen. 2018. Link prediction based on graph neural networks. In Advances in Neural Information Processing Systems.  Muhan Zhang and Yixin Chen. 2018. Link prediction based on graph neural networks. In Advances in Neural Information Processing Systems."},{"key":"e_1_2_1_181_1","article-title":"Deep learning on graphs: A survey","volume":"14","author":"Zhang Ziwei","year":"2020","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"e_1_2_1_182_1","first-page":"59","article-title":"Architectural implications of graph neural networks","volume":"19","author":"Zhang Zhihui","year":"2020","journal-title":"IEEE Comput. Arch. Lett."},{"key":"e_1_2_1_183_1","unstructured":"Ziwei Zhang Chenhao Niu Peng Cui Bo Zhang Wei Cui and Wenwu Zhu. 2020. A simple and general graph neural network with stochastic message passing. arXiv:2009.02562. Retrieved from https:\/\/arxiv.org\/abs\/2009.02562.  Ziwei Zhang Chenhao Niu Peng Cui Bo Zhang Wei Cui and Wenwu Zhu. 2020. A simple and general graph neural network with stochastic message passing. arXiv:2009.02562. Retrieved from https:\/\/arxiv.org\/abs\/2009.02562."},{"key":"e_1_2_1_184_1","doi-asserted-by":"publisher","DOI":"10.1109\/IA351965.2020.00011"},{"key":"e_1_2_1_185_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.01.001"},{"key":"e_1_2_1_186_1","volume-title":"Leibniz Int. Proc. Inf. 114","author":"Zhu Di","year":"2018"},{"key":"e_1_2_1_187_1","volume-title":"VLDB Endow. (2018)","author":"Zhu Rong","year":"2018"},{"key":"e_1_2_1_188_1","volume-title":"Proceedings of the 7th International Conference on Learning Representations","author":"Z\u00fcgner Daniel","year":"2019"}],"container-title":["ACM Computing Surveys"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477141","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3477141","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:49:03Z","timestamp":1750193343000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477141"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,8]]},"references-count":188,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2022,12,31]]}},"alternative-id":["10.1145\/3477141"],"URL":"https:\/\/doi.org\/10.1145\/3477141","relation":{},"ISSN":["0360-0300","1557-7341"],"issn-type":[{"value":"0360-0300","type":"print"},{"value":"1557-7341","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,8]]},"assertion":[{"value":"2020-11-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-07-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-10-08","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}