{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T07:56:19Z","timestamp":1776930979508,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":74,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,16]]},"DOI":"10.1145\/3712285.3759880","type":"proceedings-article","created":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T16:04:47Z","timestamp":1762963487000},"page":"217-236","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["PGT-I: Scaling Spatiotemporal GNNs with Memory-Efficient Distributed Training"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5692-9359","authenticated-orcid":false,"given":"Seth","family":"Ockerman","sequence":"first","affiliation":[{"name":"University of Wisconsin-Madison, Madison, USA and Argonne National Laboratory, DuPage, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4830-3139","authenticated-orcid":false,"given":"Amal","family":"Gueroudji","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, DuPage, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3716-4693","authenticated-orcid":false,"given":"Tanwi","family":"Mallick","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, DuPage, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5990-0658","authenticated-orcid":false,"given":"Yixuan","family":"He","sequence":"additional","affiliation":[{"name":"Arizona State University, Phoenix, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2120-6521","authenticated-orcid":false,"given":"Line","family":"Pouchard","sequence":"additional","affiliation":[{"name":"Sandia National Laboratories, Albuquerque, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5435-5857","authenticated-orcid":false,"given":"Robert","family":"Ross","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, DuPage, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9575-7935","authenticated-orcid":false,"given":"Shivaram","family":"Venkataraman","sequence":"additional","affiliation":[{"name":"University of Wisconsin-Madison, Madison, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,15]]},"reference":[{"key":"e_1_3_3_3_2_2","series-title":"(NIPS \u201920)","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","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. In Proceedings of the 34th International Conference on Neural Information Processing Systems (Vancouver, BC, Canada) (NIPS \u201920). Curran Associates Inc., Red Hook, NY, USA, Article 1494, 12\u00a0pages."},{"key":"e_1_3_3_3_3_2","doi-asserted-by":"publisher","unstructured":"Maciej Besta and Torsten Hoefler. 2024. Parallel and Distributed Graph Neural Networks: An In-Depth Concurrency Analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024). 10.1109\/TPAMI.2023.3303431","DOI":"10.1109\/TPAMI.2023.3303431"},{"key":"e_1_3_3_3_4_2","unstructured":"Francois Chaubard Duncan Eddy and Mykel\u00a0J. Kochenderfer. 2024. Beyond Gradient Averaging in Parallel Optimization: Improved Robustness through Gradient Agreement Filtering. arxiv:https:\/\/arXiv.org\/abs\/2412.18052\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2412.18052"},{"key":"e_1_3_3_3_5_2","doi-asserted-by":"publisher","unstructured":"Rong Chen Jiaxin Shi Yanzhe Chen Binyu Zang Haibing Guan and Haibo Chen. 2019. PowerLyra: Differentiated Graph Computation and Partitioning on Skewed Graphs. ACM Trans. Parallel Comput. 5 3 Article 13 (Jan. 2019) 39\u00a0pages. 10.1145\/3298989","DOI":"10.1145\/3298989"},{"key":"e_1_3_3_3_6_2","doi-asserted-by":"publisher","unstructured":"V.\u00a0Maxime Croft Senna C. J.\u00a0L. van Iersel and Cosimo Della\u00a0Santina. 2023. Forecasting infections with spatio-temporal graph neural networks: a case study of the Dutch SARS-CoV-2 spread. Frontiers in Physics 11 (2023). 10.3389\/fphy.2023.1277052","DOI":"10.3389\/fphy.2023.1277052"},{"key":"e_1_3_3_3_7_2","doi-asserted-by":"publisher","unstructured":"Simon Daenens Timothy Verstraeten Pieter-Jan Daems Ann Nowe and Jan Helsen. 2024. Spatio-Temporal Graph Neural Networks for Power Prediction in Offshore Wind Farms Using SCADA Data. 10.5194\/wes-2024-113","DOI":"10.5194\/wes-2024-113"},{"key":"e_1_3_3_3_8_2","doi-asserted-by":"publisher","unstructured":"C.O. de Burgh-Day and T. Leeuwenburg. 2023. Machine learning for numerical weather and climate modelling: a review. Geoscientific Model Development (2023). 10.5194\/gmd-16-6433-2023","DOI":"10.5194\/gmd-16-6433-2023"},{"key":"e_1_3_3_3_9_2","unstructured":"Anis Elgabli Jihong Park Amrit\u00a0S. Bedi Mehdi Bennis and Vaneet Aggarwal. 2020. GADMM: Fast and Communication Efficient Framework for Distributed Machine Learning. arxiv:https:\/\/arXiv.org\/abs\/1909.00047\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/1909.00047"},{"key":"e_1_3_3_3_10_2","doi-asserted-by":"crossref","unstructured":"Yangxin Fan Raymond\u00a0J. Wieser Xuanji Yu Yinghui Wu Laura\u00a0S. Bruckman and Roger\u00a0H. French. 2024. Using spatio-temporal graph neural networks to estimate fleet-wide photovoltaic performance degradation patterns. PLOS ONE 19 (2024).","DOI":"10.1371\/journal.pone.0297445"},{"key":"e_1_3_3_3_11_2","unstructured":"Matthias Fey and Jan\u00a0Eric Lenssen. 2019. Fast Graph Representation Learning with PyTorch Geometric. arxiv:https:\/\/arXiv.org\/abs\/1903.02428\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/1903.02428"},{"key":"e_1_3_3_3_12_2","doi-asserted-by":"crossref","unstructured":"Cornelius Fritz Emilio Dorigatti and David R\u00fcgamer. 2022. Combining graph neural networks and spatio-temporal disease models to improve the prediction of weekly COVID-19 cases in Germany volume = 12 journal = Scientific Reports doi = 10.1038\/s41598-022-07757-5. Scientific Reports (03 2022) 3930.","DOI":"10.1038\/s41598-022-07757-5"},{"key":"e_1_3_3_3_13_2","first-page":"551","volume-title":"15th USENIX Symposium on Operating Systems Design and Implementation (OSDI 21)","author":"Gandhi Swapnil","year":"2021","unstructured":"Swapnil Gandhi and Anand\u00a0Padmanabha Iyer. 2021. P3: Distributed Deep Graph Learning at Scale. In 15th USENIX Symposium on Operating Systems Design and Implementation (OSDI 21). USENIX Association, 551\u2013568. https:\/\/www.usenix.org\/conference\/osdi21\/presentation\/gandhi"},{"key":"e_1_3_3_3_14_2","unstructured":"Priya Goyal Piotr Doll\u00e1r Ross Girshick Pieter Noordhuis Lukasz Wesolowski Aapo Kyrola Andrew Tulloch Yangqing Jia and Kaiming He. 2018. Accurate Large Minibatch SGD: Training ImageNet in 1 Hour. arxiv:https:\/\/arXiv.org\/abs\/1706.02677\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1706.02677"},{"key":"e_1_3_3_3_15_2","unstructured":"Jake Grigsby Zhe Wang Nam Nguyen and Yanjun Qi. 2023. Long-Range Transformers for Dynamic Spatiotemporal Forecasting. arxiv:https:\/\/arXiv.org\/abs\/2109.12218\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2109.12218"},{"key":"e_1_3_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534540.3534691"},{"key":"e_1_3_3_3_17_2","doi-asserted-by":"publisher","unstructured":"Shengnan Guo Youfang Lin Ning Feng Chao Song and Huaiyu Wan. 2019. Attention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting. Proceedings of the AAAI Conference on Artificial Intelligence 33 01 (July 2019) 922\u2013929. 10.1609\/aaai.v33i01.3301922","DOI":"10.1609\/aaai.v33i01.3301922"},{"key":"e_1_3_3_3_18_2","unstructured":"William\u00a0L. Hamilton Rex Ying and Jure Leskovec. 2018. Inductive Representation Learning on Large Graphs. arxiv:https:\/\/arXiv.org\/abs\/1706.02216\u00a0[cs.SI] https:\/\/arxiv.org\/abs\/1706.02216"},{"key":"e_1_3_3_3_19_2","doi-asserted-by":"publisher","unstructured":"Silu He Qinyao Luo Ronghua Du Ling Zhao Guangjun He Han Fu and Haifeng Li. 2023. STGC-GNNs: A GNN-based traffic prediction framework with a spatial\u2013temporal Granger causality graph. Physica A: Statistical Mechanics and its Applications 623 (2023) 128913. 10.1016\/j.physa.2023.128913","DOI":"10.1016\/j.physa.2023.128913"},{"key":"e_1_3_3_3_20_2","unstructured":"Lei Huang Jie Qin Yi Zhou Fan Zhu Li Liu and Ling Shao. 2020. Normalization Techniques in Training DNNs: Methodology Analysis and Application. arxiv:https:\/\/arXiv.org\/abs\/2009.12836\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2009.12836"},{"key":"e_1_3_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/CSCI62032.2023.00022"},{"key":"e_1_3_3_3_22_2","unstructured":"Grammarly Inc.2024. Grammarly. https:\/\/www.grammarly.com\/. Writing assistant software."},{"key":"e_1_3_3_3_23_2","doi-asserted-by":"publisher","unstructured":"Shengwei Ji Shengjie Li Fei Liu and Qiang Xu. 2024. LocalDGP: local degree-balanced graph partitioning for lightweight GNNs. Applied Intelligence 55 2 (Dec. 2024) 19\u00a0pages. 10.1007\/s10489-024-05964-3","DOI":"10.1007\/s10489-024-05964-3"},{"key":"e_1_3_3_3_24_2","volume-title":"Serial order: a parallel distributed processing approach","author":"Jordan M\u00a0I","year":"1985","unstructured":"M\u00a0I Jordan. June 1985-March 1986. Serial order: a parallel distributed processing approach. Technical report. University of California, San Diego. https:\/\/www.osti.gov\/biblio\/6910294"},{"key":"e_1_3_3_3_25_2","unstructured":"Jared Kaplan Sam McCandlish Tom Henighan Tom\u00a0B. Brown Benjamin Chess Rewon Child Scott Gray Alec Radford Jeffrey Wu and Dario Amodei. 2020. Scaling Laws for Neural Language Models. arxiv:https:\/\/arXiv.org\/abs\/2001.08361\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2001.08361"},{"key":"e_1_3_3_3_26_2","doi-asserted-by":"publisher","unstructured":"Ahmad\u00a0Maroof Karimi Yinghui Wu Mehmet Koyuturk and Roger French. 2021. Spatiotemporal Graph Neural Network for Performance Prediction of Photovoltaic Power Systems. Proceedings of the AAAI Conference on Artificial Intelligence 35 (05 2021) 15323\u201315330. 10.1609\/aaai.v35i17.17799","DOI":"10.1609\/aaai.v35i17.17799"},{"key":"e_1_3_3_3_27_2","doi-asserted-by":"publisher","unstructured":"K. Kashinath et\u00a0al. 2021. Physics-informed machine learning: case studies for weather and climate modelling. Philosophical Transactions of the Royal Society A: Mathematical Physical and Engineering Sciences (2021). 10.1098\/rsta.2020.0093 arXiv:https:\/\/royalsocietypublishing.org\/doi\/pdf\/10.1098\/rsta.2020.0093","DOI":"10.1098\/rsta.2020.0093"},{"key":"e_1_3_3_3_28_2","unstructured":"Weiyang Kong Kaiqi Wu Sen Zhang and Yubao Liu. 2025. GraphSparseNet: a Novel Method for Large Scale Traffic Flow Prediction. arxiv:https:\/\/arXiv.org\/abs\/2502.19823\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2502.19823"},{"key":"e_1_3_3_3_29_2","unstructured":"Alex Krizhevsky. 2014. One weird trick for parallelizing convolutional neural networks. arxiv:https:\/\/arXiv.org\/abs\/1404.5997\u00a0[cs.NE] https:\/\/arxiv.org\/abs\/1404.5997"},{"key":"e_1_3_3_3_30_2","doi-asserted-by":"publisher","unstructured":"Y. Lecun L. Bottou Y. Bengio and P. Haffner. 1998. Gradient-based learning applied to document recognition. Proc. IEEE 86 11 (1998) 2278\u20132324. 10.1109\/5.726791","DOI":"10.1109\/5.726791"},{"key":"e_1_3_3_3_31_2","doi-asserted-by":"publisher","unstructured":"Claire\u00a0Songhyun Lee V. Hewes Giuseppe Cerati Kewei Wang Adam Aurisano Ankit Agrawal Alok Choudhary and Wei-Keng Liao. 2024. Addressing GPU memory limitations for Graph Neural Networks in High-Energy Physics applications. Frontiers in High Performance Computing 2 (2024). 10.3389\/fhpcp.2024.1458674","DOI":"10.3389\/fhpcp.2024.1458674"},{"key":"e_1_3_3_3_32_2","unstructured":"Fuxian Li et\u00a0al. 2021. Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solution. arxiv:https:\/\/arXiv.org\/abs\/2104.14917\u00a0[cs.LG]"},{"key":"e_1_3_3_3_33_2","doi-asserted-by":"publisher","unstructured":"Shen Li et\u00a0al. 2020. PyTorch distributed: experiences on accelerating data parallel training. Proc. VLDB Endow. 13 12 (aug 2020) 3005\u20133018. 10.14778\/3415478.3415530","DOI":"10.14778\/3415478.3415530"},{"key":"e_1_3_3_3_34_2","doi-asserted-by":"publisher","unstructured":"Wei Li Xi Zhan Xin Liu Lei Zhang Yu Pan and Zhisong Pan. 2023. SASTGCN: A Self-Adaptive Spatio-Temporal Graph Convolutional Network for Traffic Prediction. ISPRS International Journal of Geo-Information 12 8 (2023). 10.3390\/ijgi12080346","DOI":"10.3390\/ijgi12080346"},{"key":"e_1_3_3_3_35_2","volume-title":"ICLR \u201918","author":"Li Yaguang","year":"2018","unstructured":"Yaguang Li et\u00a0al. 2018. Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting. In ICLR \u201918."},{"key":"e_1_3_3_3_36_2","doi-asserted-by":"publisher","unstructured":"Haitao Lin Zhangyang Gao Yongjie Xu Lirong Wu Ling Li and Stan\u00a0Z. Li. 2022. Conditional Local Convolution for Spatio-Temporal Meteorological Forecasting. Proceedings of the AAAI Conference on Artificial Intelligence 36 7 (Jun. 2022) 7470\u20137478. 10.1609\/aaai.v36i7.20711","DOI":"10.1609\/aaai.v36i7.20711"},{"key":"e_1_3_3_3_37_2","unstructured":"Chenxi Liu Sun Yang Qianxiong Xu Zhishuai Li Cheng Long Ziyue Li and Rui Zhao. 2024. Spatial-Temporal Large Language Model for Traffic Prediction. arxiv:https:\/\/arXiv.org\/abs\/2401.10134\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2401.10134"},{"key":"e_1_3_3_3_38_2","doi-asserted-by":"publisher","unstructured":"Tanwi Mallick et\u00a0al. 2020. Graph-Partitioning-Based Diffusion Convolutional Recurrent Neural Network for Large-Scale Traffic Forecasting. Transportation Research Record: Journal of the Transportation Research Board (2020). 10.1177\/0361198120930010","DOI":"10.1177\/0361198120930010"},{"key":"e_1_3_3_3_39_2","unstructured":"Qi Meng Wei Chen Yue Wang Zhi-Ming Ma and Tie-Yan Liu. 2017. Convergence Analysis of Distributed Stochastic Gradient Descent with Shuffling. arxiv:https:\/\/arXiv.org\/abs\/1709.10432\u00a0[stat.ML] https:\/\/arxiv.org\/abs\/1709.10432"},{"key":"e_1_3_3_3_40_2","doi-asserted-by":"publisher","unstructured":"Vishal Meshram et\u00a0al. 2021. Machine learning in agriculture domain: A state-of-art survey. Artificial Intelligence in the Life Sciences (2021). 10.1016\/j.ailsci.2021.100010","DOI":"10.1016\/j.ailsci.2021.100010"},{"key":"e_1_3_3_3_41_2","doi-asserted-by":"crossref","unstructured":"Vishwali Mhasawade Yuan Zhao and Rumi Chunara. 2021. Machine learning and algorithmic fairness in public and population health. Nature Machine Intelligence 3 (2021) 659 \u2013 666.","DOI":"10.1038\/s42256-021-00373-4"},{"key":"e_1_3_3_3_42_2","doi-asserted-by":"crossref","unstructured":"Seyyed\u00a0Ali Mohammadiyeh and Behzad\u00a0Soleimani Neysiani. 2023. Analyzing and Improving Prediction of Spatiotemporal Signal Data Using Grid Search on Graph Convolutional Networks. 2023 9th International Conference on Web Research (ICWR) (2023) 294\u2013299. https:\/\/api.semanticscholar.org\/CorpusID:259100915","DOI":"10.1109\/ICWR57742.2023.10139174"},{"key":"e_1_3_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS53621.2022.00109"},{"key":"e_1_3_3_3_44_2","unstructured":"Seth Ockerman Zachary Klamer and Brian Haab. 2023. Accelerating Biological Spatial Cluster Analysis with the Parallel Integral Image Technique. arxiv:https:\/\/arXiv.org\/abs\/2410.16291\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2410.16291"},{"key":"e_1_3_3_3_45_2","unstructured":"State of California. [n. d.]. Caltrans Performance Measurement System (PeMS). data retrieved from PeMS https:\/\/pems.dot.ca.gov."},{"key":"e_1_3_3_3_46_2","doi-asserted-by":"publisher","unstructured":"Paul\u00a0A. O\u2019Gorman and John\u00a0G. Dwyer. 2018. Using Machine Learning to Parameterize Moist Convection: Potential for Modeling of Climate Climate Change and Extreme Events. Journal of Advances in Modeling Earth Systems 10 10 (2018) 2548\u20132563. 10.1029\/2018MS001351 arXiv:https:\/\/agupubs.onlinelibrary.wiley.com\/doi\/pdf\/10.1029\/2018MS001351","DOI":"10.1029\/2018MS001351"},{"key":"e_1_3_3_3_47_2","doi-asserted-by":"publisher","unstructured":"David Olawade et\u00a0al. 2023. Using artificial intelligence to improve public health: a narrative review. Frontiers in Public Health (10 2023). 10.3389\/fpubh.2023.1196397","DOI":"10.3389\/fpubh.2023.1196397"},{"key":"e_1_3_3_3_48_2","unstructured":"OpenAI. 2024. ChatGPT (v4). https:\/\/www.openai.com\/chatgpt"},{"key":"e_1_3_3_3_49_2","unstructured":"Alec Radford Jeff Wu Rewon Child David Luan Dario Amodei and Ilya Sutskever. 2019. Language Models are Unsupervised Multitask Learners. https:\/\/api.semanticscholar.org\/CorpusID:160025533"},{"key":"e_1_3_3_3_50_2","unstructured":"Samyam Rajbhandari Jeff Rasley Olatunji Ruwase and Yuxiong He. 2020. ZeRO: Memory Optimizations Toward Training Trillion Parameter Models. arxiv:https:\/\/arXiv.org\/abs\/1910.02054\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/1910.02054"},{"key":"e_1_3_3_3_51_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-75768-7_8"},{"key":"e_1_3_3_3_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482014"},{"key":"e_1_3_3_3_53_2","unstructured":"Benedek Rozemberczki Paul Scherer Oliver Kiss Rik Sarkar and Tamas Ferenci. 2021. Chickenpox Cases in Hungary: a Benchmark Dataset for Spatiotemporal Signal Processing with Graph Neural Networks. arxiv:https:\/\/arXiv.org\/abs\/2102.08100\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2102.08100"},{"key":"e_1_3_3_3_54_2","first-page":"318","volume-title":"Learning Internal Representations by Error Propagation","author":"Rumelhart David\u00a0E.","year":"1987","unstructured":"David\u00a0E. Rumelhart and James\u00a0L. McClelland. 1987. Learning Internal Representations by Error Propagation. MIT Press, 318\u2013362."},{"key":"e_1_3_3_3_55_2","unstructured":"Zahraa\u00a0Al Sahili and Mariette Awad. 2023. Spatio-Temporal Graph Neural Networks: A Survey. arxiv:https:\/\/arXiv.org\/abs\/2301.10569\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2301.10569"},{"key":"e_1_3_3_3_56_2","doi-asserted-by":"publisher","unstructured":"Yingxia Shao et\u00a0al. 2024. Distributed Graph Neural Network Training: A Survey. ACM Comput. Surv. (apr 2024). 10.1145\/3648358","DOI":"10.1145\/3648358"},{"key":"e_1_3_3_3_57_2","unstructured":"Sam Shleifer Clara McCreery and Vamsi Chitters. 2019. Incrementally Improving Graph WaveNet Performance on Traffic Prediction. arxiv:https:\/\/arXiv.org\/abs\/1912.07390\u00a0[eess.SP] https:\/\/arxiv.org\/abs\/1912.07390"},{"key":"e_1_3_3_3_58_2","doi-asserted-by":"publisher","unstructured":"Dalwinder Singh and Birmohan Singh. 2020. Investigating the impact of data normalization on classification performance. Applied Soft Computing 97 (2020) 105524. 10.1016\/j.asoc.2019.105524","DOI":"10.1016\/j.asoc.2019.105524"},{"key":"e_1_3_3_3_59_2","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan\u00a0N. Gomez Lukasz Kaiser and Illia Polosukhin. 2023. Attention Is All You Need. arxiv:https:\/\/arXiv.org\/abs\/1706.03762\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/1706.03762"},{"key":"e_1_3_3_3_60_2","doi-asserted-by":"publisher","unstructured":"Alessio Verdone Simone Scardapane and Massimo Panella. 2024. Explainable Spatio-Temporal Graph Neural Networks for multi-site photovoltaic energy production. Applied Energy 353 (2024) 122151. 10.1016\/j.apenergy.2023.122151","DOI":"10.1016\/j.apenergy.2023.122151"},{"key":"e_1_3_3_3_61_2","doi-asserted-by":"publisher","unstructured":"Xing Wan. 2019. Influence of feature scaling on convergence of gradient iterative algorithm. Journal of Physics: Conference Series 1213 (06 2019) 032021. 10.1088\/1742-6596\/1213\/3\/032021","DOI":"10.1088\/1742-6596\/1213\/3\/032021"},{"key":"e_1_3_3_3_62_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/264"},{"key":"e_1_3_3_3_63_2","unstructured":"Minjie Wang et\u00a0al. 2020. Deep Graph Library: A Graph-Centric Highly-Performant Package for Graph Neural Networks. arXiv:https:\/\/arXiv.org\/abs\/1909.01315https:\/\/arxiv.org\/abs\/1909.01315"},{"key":"e_1_3_3_3_64_2","doi-asserted-by":"crossref","unstructured":"Thomas Wolf Lysandre Debut Victor Sanh Julien Chaumond Clement Delangue Anthony Moi Pierric Cistac Tim Rault R\u00e9mi Louf Morgan Funtowicz Joe Davison Sam Shleifer Patrick von Platen Clara Ma Yacine Jernite Julien Plu Canwen Xu Teven\u00a0Le Scao Sylvain Gugger Mariama Drame Quentin Lhoest and Alexander\u00a0M. Rush. 2020. HuggingFace\u2019s Transformers: State-of-the-art Natural Language Processing. arxiv:https:\/\/arXiv.org\/abs\/1910.03771\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/1910.03771","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_3_3_3_65_2","doi-asserted-by":"publisher","unstructured":"Sjaak Wolfert Lan Ge Cor Verdouw and Marc-Jeroen Bogaardt. 2017. Big Data in Smart Farming \u2013 A review. Agricultural Systems (2017). 10.1016\/j.agsy.2017.01.023","DOI":"10.1016\/j.agsy.2017.01.023"},{"key":"e_1_3_3_3_66_2","doi-asserted-by":"publisher","DOI":"10.5555\/3367243.3367303"},{"key":"e_1_3_3_3_67_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539274"},{"key":"e_1_3_3_3_68_2","unstructured":"Yang You Igor Gitman and Boris Ginsburg. 2017. Large Batch Training of Convolutional Networks. arxiv:https:\/\/arXiv.org\/abs\/1708.03888\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1708.03888"},{"key":"e_1_3_3_3_69_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/505"},{"key":"e_1_3_3_3_70_2","doi-asserted-by":"publisher","unstructured":"Ling Zhao Yujiao Song Chao Zhang Yu Liu Pu Wang Tao Lin Min Deng and Haifeng Li. 2020. T-GCN: A Temporal Graph Convolutional Network for Traffic Prediction. IEEE Transactions on Intelligent Transportation Systems 21 (2020) 3848\u20133858. Issue 9. 10.1109\/TITS.2019.2935152","DOI":"10.1109\/TITS.2019.2935152"},{"key":"e_1_3_3_3_71_2","doi-asserted-by":"publisher","DOI":"10.1109\/IA351965.2020.00011"},{"key":"e_1_3_3_3_72_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607056"},{"key":"e_1_3_3_3_73_2","unstructured":"Jiawei Zhu Yujiao Song Ling Zhao and Haifeng Li. 2020. A3T-GCN: Attention Temporal Graph Convolutional Network for Traffic Forecasting. arxiv:https:\/\/arXiv.org\/abs\/2006.11583\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2006.11583"},{"key":"e_1_3_3_3_74_2","doi-asserted-by":"publisher","unstructured":"Jiawei Zhu Qiongjie Wang Chao Tao Hanhan Deng Ling Zhao and Haifeng Li. 2021. AST-GCN: Attribute-Augmented Spatiotemporal Graph Convolutional Network for Traffic Forecasting. IEEE Access 9 (2021) 35973\u201335983. 10.1109\/ACCESS.2021.3062114","DOI":"10.1109\/ACCESS.2021.3062114"},{"key":"e_1_3_3_3_75_2","unstructured":"Jingwei Zuo Karine Zeitouni Yehia Taher and Sandra Garcia-Rodriguez. 2022. Graph Convolutional Networks for Traffic Forecasting with Missing Values. arxiv:https:\/\/arXiv.org\/abs\/2212.06419\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2212.06419"}],"event":{"name":"SC '25: The International Conference for High Performance Computing, Networking, Storage and Analysis","location":"St. Louis MO USA","acronym":"SC '25","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3712285.3759880","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T18:46:41Z","timestamp":1773254801000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3712285.3759880"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,15]]},"references-count":74,"alternative-id":["10.1145\/3712285.3759880","10.1145\/3712285"],"URL":"https:\/\/doi.org\/10.1145\/3712285.3759880","relation":{},"subject":[],"published":{"date-parts":[[2025,11,15]]},"assertion":[{"value":"2025-11-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}