{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T01:51:25Z","timestamp":1773193885808,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,2,21]],"date-time":"2023-02-21T00:00:00Z","timestamp":1676937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["51877004,61732002,61572062"],"award-info":[{"award-number":["51877004,61732002,61572062"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,2,25]]},"DOI":"10.1145\/3572848.3577487","type":"proceedings-article","created":{"date-parts":[[2023,2,21]],"date-time":"2023-02-21T16:02:30Z","timestamp":1676995350000},"page":"405-418","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":23,"title":["PiPAD"],"prefix":"10.1145","author":[{"given":"Chunyang","family":"Wang","sequence":"first","affiliation":[{"name":"Beihang University, Beijing, China"}]},{"given":"Desen","family":"Sun","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}]},{"given":"Yuebin","family":"Bai","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2023,2,21]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477141"},{"key":"e_1_3_2_1_2_1","volume-title":"Adaptive graph convolutional recurrent network for traffic forecasting. Advances in neural information processing systems 33","author":"Bai Lei","year":"2020","unstructured":"Lei Bai, Lina Yao, Can Li, Xianzhi Wang, and Can Wang. 2020. Adaptive graph convolutional recurrent network for traffic forecasting. Advances in neural information processing systems 33 (2020), 17804--17815."},{"key":"e_1_3_2_1_3_1","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Bai Zhihao","year":"2020","unstructured":"Zhihao Bai, Zhen Zhang, Yibo Zhu, and Xin Jin. 2020. {PipeSwitch}: Fast Pipelined Context Switching for Deep Learning Applications. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20). USENIX Association, USA, 499--514."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1654059.1654078"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3480858"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"e_1_3_2_1_7_1","volume-title":"Fast Graph Representation Learning with PyTorch Geometric. CoRR abs\/1903.02428","author":"Fey Matthias","year":"2019","unstructured":"Matthias Fey and Jan Eric Lenssen. 2019. Fast Graph Representation Learning with PyTorch Geometric. CoRR abs\/1903.02428 (2019), arXiv-1903. arXiv:1903.02428 http:\/\/arxiv.org\/abs\/1903.02428"},{"key":"e_1_3_2_1_8_1","volume-title":"Advances in Neural Information Processing Systems","author":"Fout Alex","year":"2017","unstructured":"Alex Fout, Jonathon Byrd, Basir Shariat, and Asa Ben-Hur. 2017. Protein Interface Prediction using Graph Convolutional Networks. In Advances in Neural Information Processing Systems, I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc., Long Beach, CA, USA, 6530--6539. https:\/\/proceedings.neurips.cc\/paper\/2017\/file\/f507783927f2ec2737ba40afbd17efb5-Paper.pdf"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3502181.3531467"},{"key":"e_1_3_2_1_10_1","volume-title":"Learning Graph Representations with Embedding Propagation. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","author":"Garc\u00eda-Dur\u00e1n Alberto","year":"2017","unstructured":"Alberto Garc\u00eda-Dur\u00e1n and Mathias Niepert. 2017. Learning Graph Representations with Embedding Propagation. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4--9, 2017, Long Beach, CA, USA. Curran Associates, Inc., USA, 5119--5130. https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/e0688d13958a19e087e123148555e4b4-Abstract.html"},{"key":"e_1_3_2_1_11_1","unstructured":"Alan Gray. 2019. Getting Started with CUDA Graphs. https:\/\/developer.nvidia.com\/blog\/cuda-graphs\/."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534540.3534691"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3056502"},{"key":"e_1_3_2_1_14_1","volume-title":"Long short-term memory. Neural computation 9, 8","author":"Hochreiter Sepp","year":"1997","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997), 1735--1780."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00076"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441585"},{"key":"e_1_3_2_1_17_1","volume-title":"Advances in Neural Information Processing Systems. Curran Associates","author":"Huang Yanping","year":"2019","unstructured":"Yanping Huang, Youlong Cheng, Ankur Bapna, Orhan Firat, Dehao Chen, Mia Chen, HyoukJoong Lee, Jiquan Ngiam, Quoc V Le, Yonghui Wu, and zhifeng Chen. 2019. GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism. In Advances in Neural Information Processing Systems. Curran Associates, Inc., USA, 103--112. https:\/\/proceedings.neurips.cc\/paper\/2019\/file\/093f65e080a295f8076b1c5722a46aa2-Paper.pdf"},{"key":"e_1_3_2_1_18_1","first-page":"172","article-title":"Accelerating training and inference of graph neural networks with fast sampling and pipelining","volume":"4","author":"Kaler Tim","year":"2022","unstructured":"Tim Kaler, Nickolas Stathas, Anne Ouyang, Alexandros-Stavros Iliopoulos, Tao Schardl, Charles E Leiserson, and Jie Chen. 2022. Accelerating training and inference of graph neural networks with fast sampling and pipelining. Proceedings of Machine Learning and Systems 4 (2022), 172--189.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_19_1","first-page":"1","article-title":"Representation learning for dynamic graphs: A survey","volume":"21","author":"Kazemi Seyed Mehran","year":"2020","unstructured":"Seyed Mehran Kazemi, Rishab Goel, Kshitij Jain, Ivan Kobyzev, Akshay Sethi, Peter Forsyth, and Pascal Poupart. 2020. Representation learning for dynamic graphs: A survey. J. Mach. Learn. Res. 21, 70 (2020), 1--73.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_1_20_1","volume-title":"Kipf and Max Welling","author":"Thomas","year":"2017","unstructured":"Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24--26, 2017, Conference Track Proceedings. OpenReview.net, USA, 1--14. https:\/\/openreview.net\/forum?id=SJU4ayYgl"},{"key":"e_1_3_2_1_21_1","first-page":"8343","article-title":"Nimble: Lightweight and parallel gpu task scheduling for deep learning","volume":"33","author":"Kwon Woosuk","year":"2020","unstructured":"Woosuk Kwon, Gyeong-In Yu, Eunji Jeong, and Byung-Gon Chun. 2020. Nimble: Lightweight and parallel gpu task scheduling for deep learning. Advances in Neural Information Processing Systems 33 (2020), 8343--8354.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482237"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527439"},{"key":"e_1_3_2_1_24_1","unstructured":"Justin Luitjens. 2013. CUDA Pro Tip: Increase Performance with Vectorized Memory Access. https:\/\/developer.nvidia.com\/blog\/cudapro-tip-increase-performance-with-vectorized-memory-access\/."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5945"},{"key":"e_1_3_2_1_26_1","volume-title":"NeuGraph: Parallel Deep Neural Network Computation on Large Graphs. In 2019 USENIX Annual Technical Conference, USENIX ATC 2019","author":"Ma Lingxiao","year":"2019","unstructured":"Lingxiao Ma, Zhi Yang, Youshan Miao, Jilong Xue, Ming Wu, Lidong Zhou, and Yafei Dai. 2019. NeuGraph: Parallel Deep Neural Network Computation on Large Graphs. In 2019 USENIX Annual Technical Conference, USENIX ATC 2019, Renton, WA, USA, July 10--12, 2019. USENIX Association, USA, 443--458. https:\/\/www.usenix.org\/conference\/atc19\/presentation\/ma"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18--24","volume":"7947","author":"Narayanan Deepak","year":"2021","unstructured":"Deepak Narayanan, Amar Phanishayee, Kaiyu Shi, Xie Chen, and Matei Zaharia. 2021. Memory-Efficient Pipeline-Parallel DNN Training. In Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18--24 July 2021 (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, USA, 7937--7947. http:\/\/proceedings.mlr.press\/v139\/narayanan21a.html"},{"key":"e_1_3_2_1_29_1","volume-title":"Nvidia: Profiler User's Guide. https:\/\/docs.nvidia.com\/cuda\/profiler-users-guide\/.","author":"NVIDIA.","year":"2022","unstructured":"NVIDIA. 2022. Nvidia: Profiler User's Guide. https:\/\/docs.nvidia.com\/cuda\/profiler-users-guide\/."},{"key":"e_1_3_2_1_30_1","unstructured":"NVIDIA. 2022. Nvidia system management interface. https:\/\/developer.nvidia.com\/nvidia-system-management-interface."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3492321.3519563"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i6.16616"},{"key":"e_1_3_2_1_33_1","volume-title":"Leiserson","author":"Pareja Aldo","year":"2020","unstructured":"Aldo Pareja, Giacomo Domeniconi, Jie Chen, Tengfei Ma, Toyotaro Suzumura, Hiroki Kanezashi, Tim Kaler, Tao B. Schardl, and Charles E. Leiserson. 2020. EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs. In The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, IAAI 2020, The Tenth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2020, February 7--12, 2020. AAAI Press, New York, NY, USA, 5363--5370. https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/5984"},{"key":"e_1_3_2_1_34_1","volume-title":"PyTorch: An Imperative Style","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In Advances in Neural Information Processing Systems, Vol. 32. Curran Associates, Inc., USA, 8024--8035. https:\/\/proceedings.neurips.cc\/paper\/2019\/file\/bdbca288fee7f92f2bfa9f7012727740-Paper.pdf"},{"key":"e_1_3_2_1_35_1","unstructured":"PyTorch. 2022. PyTorch: Pytorch profiler. https:\/\/pytorch.org\/tutorials\/recipes\/recipes\/profiler_recipe.html."},{"key":"e_1_3_2_1_36_1","volume-title":"Ahmed","author":"Rossi Ryan A.","year":"2014","unstructured":"Ryan A. Rossi and Nesreen K. Ahmed. 2014. NetworkRepository: A Graph Data Repository with Visual Interactive Analytics. CoRR abs\/1410.3560 (2014), arxiv-1410. arXiv:1410.3560 http:\/\/arxiv.org\/abs\/1410.3560"},{"key":"e_1_3_2_1_37_1","volume-title":"Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, January 25--30","author":"Ryan","year":"2015","unstructured":"Ryan A. Rossi and Nesreen K. Ahmed. 2015. The Network Data Repository with Interactive Graph Analytics and Visualization. In Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, January 25--30, 2015, Austin, Texas, USA, Blai Bonet and Sven Koenig (Eds.). AAAI Press, USA, 4292--4293. http:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI15\/paper\/view\/9553"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482014"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3082932"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2021.3052138"},{"key":"e_1_3_2_1_41_1","volume-title":"Proceedings of MLSys Workshop on Graph Neural Networks and Systems (GNNSys). mlsys.org","author":"Su Qidong","year":"2021","unstructured":"Qidong Su, Minjie Wang, Da Zheng, and Zheng Zhang. 2021. Adaptive Load Balancing for Parallel GNN Training. In Proceedings of MLSys Workshop on Graph Neural Networks and Systems (GNNSys). mlsys.org, San Jose, CA, USA, 1--8."},{"key":"e_1_3_2_1_42_1","volume-title":"Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis","author":"Sun Qingxiao","year":"2022","unstructured":"Qingxiao Sun, Yi Liu, Hailong Yang, Ruizhe Zhang, Ming Dun, Mingzhen Li, Xiaoyan Liu, Wencong Xiao, Yong Li, Zhongzhi Luan, and Depei Qian. 2022. CoGNN: Efficient Scheduling for Concurrent GNN Training on GPUs. In Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis (Dallas, Texas) (SC '22). IEEE Press, Los Alamitos, CA, USA, Article 39, 15 pages."},{"key":"e_1_3_2_1_43_1","volume-title":"15th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2021","author":"Thorpe John","year":"2021","unstructured":"John Thorpe, Yifan Qiao, Jonathan Eyolfson, Shen Teng, Guanzhou Hu, Zhihao Jia, Jinliang Wei, Keval Vora, Ravi Netravali, Miryung Kim, and Guoqing Harry Xu. 2021. Dorylus: Affordable, Scalable, and Accurate GNN Training with Distributed CPU Servers and Serverless Threads. In 15th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2021, July 14--16, 2021. USENIX Association, USA, 495--514. https:\/\/www.usenix.org\/conference\/osdi21\/presentation\/thorpe"},{"key":"e_1_3_2_1_44_1","volume-title":"6th International Conference on Learning Representations, ICLR","author":"Velickovic Petar","year":"2018","unstructured":"Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Li\u00f2, and Yoshua Bengio. 2018. Graph Attention Networks. In 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings. OpenReview.net, USA, 1--12. https:\/\/openreview.net\/forum?id=rJXMpikCZ"},{"key":"e_1_3_2_1_45_1","volume-title":"PipeGCN: Efficient Full-Graph Training of Graph Convolutional Networks with Pipelined Feature Communication. In The Tenth International Conference on Learning Representations, ICLR 2022","author":"Wan Cheng","year":"2022","unstructured":"Cheng Wan, Youjie Li, Cameron R. Wolfe, Anastasios Kyrillidis, Nam Sung Kim, and Yingyan Lin. 2022. PipeGCN: Efficient Full-Graph Training of Graph Convolutional Networks with Pipelined Feature Communication. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25--29, 2022. OpenReview.net, USA, 1--24. https:\/\/openreview.net\/forum?id=kSwqMH0zn1F"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447786.3456229"},{"key":"e_1_3_2_1_47_1","volume-title":"Deep Graph Library: Towards Efficient and Scalable Deep Learning on Graphs. CoRR abs\/1909.01315","author":"Wang Minjie","year":"2019","unstructured":"Minjie Wang, Lingfan Yu, Da Zheng, Quan Gan, Yu Gai, Zihao Ye, Mufei Li, Jinjing Zhou, Qi Huang, Chao Ma, Ziyue Huang, Qipeng Guo, Hao Zhang, Haibin Lin, Junbo Zhao, Jinyang Li, Alexander J. Smola, and Zheng Zhang. 2019. Deep Graph Library: Towards Efficient and Scalable Deep Learning on Graphs. CoRR abs\/1909.01315 (2019), arxiv-1909. arXiv:1909.01315 http:\/\/arxiv.org\/abs\/1909.01315"},{"key":"e_1_3_2_1_48_1","volume-title":"GNNAdvisor: An Adaptive and Efficient Runtime System for GNN Acceleration on GPUs. In 15th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2021","author":"Wang Yuke","year":"2021","unstructured":"Yuke Wang, Boyuan Feng, Gushu Li, Shuangchen Li, Lei Deng, Yuan Xie, and Yufei Ding. 2021. GNNAdvisor: An Adaptive and Efficient Runtime System for GNN Acceleration on GPUs. In 15th USENIX Symposium on Operating Systems Design and Implementation, OSDI 2021, July 14--16, 2021, Angela Demke Brown and Jay R. Lorch (Eds.). USENIX Association, USA, 515--531. https:\/\/www.usenix.org\/conference\/osdi21\/presentation\/wang-yuke"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3492321.3519557"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2935152"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2203.14883"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.14778\/3352063.3352127"}],"event":{"name":"PPoPP '23: The 28th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","location":"Montreal QC Canada","acronym":"PPoPP '23","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the 28th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3572848.3577487","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3572848.3577487","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:08:09Z","timestamp":1750183689000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3572848.3577487"}},"subtitle":["Pipelined and Parallel Dynamic GNN Training on GPUs"],"short-title":[],"issued":{"date-parts":[[2023,2,21]]},"references-count":52,"alternative-id":["10.1145\/3572848.3577487","10.1145\/3572848"],"URL":"https:\/\/doi.org\/10.1145\/3572848.3577487","relation":{},"subject":[],"published":{"date-parts":[[2023,2,21]]},"assertion":[{"value":"2023-02-21","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}