{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T03:56:50Z","timestamp":1767844610647,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":99,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,13]],"date-time":"2024-10-13T00:00:00Z","timestamp":1728777600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-sa\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,14]]},"DOI":"10.1145\/3656019.3676892","type":"proceedings-article","created":{"date-parts":[[2024,10,11]],"date-time":"2024-10-11T10:34:08Z","timestamp":1728642848000},"page":"91-107","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["GraNNDis: Fast Distributed Graph Neural Network Training Framework for Multi-Server Clusters"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9976-7487","authenticated-orcid":false,"given":"Jaeyong","family":"Song","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Seoul National University, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4291-6124","authenticated-orcid":false,"given":"Hongsun","family":"Jang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Seoul National University, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4945-1423","authenticated-orcid":false,"given":"Hunseong","family":"Lim","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Seoul National University, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0770-9277","authenticated-orcid":false,"given":"Jaewon","family":"Jung","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Seoul National University, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1015-9969","authenticated-orcid":false,"given":"Youngsok","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Yonsei University, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4010-6611","authenticated-orcid":false,"given":"Jinho","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Seoul National University, South Korea"}]}],"member":"320","published-online":{"date-parts":[[2024,10,13]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"8","article-title":"NeutronOrch: Rethinking Sample-Based GNN Training under CPU-GPU Heterogeneous Environments","volume":"17","author":"Ai Xin","year":"2024","unstructured":"Xin Ai, Qiange Wang, Chunyu Cao, Yanfeng Zhang, Chaoyi Chen, Hao Yuan, Yu Gu, and Ge Yu. 2024. NeutronOrch: Rethinking Sample-Based GNN Training under CPU-GPU Heterogeneous Environments. Proceedings of the VLDB Endowment (VLDB) 17, 8 (may 2024), 1995\u20132008.","journal-title":"Proceedings of the VLDB Endowment (VLDB)"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-29939-5"},{"key":"e_1_3_2_1_3_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Bruna Joan","year":"2014","unstructured":"Joan Bruna, Wojciech Zaremba, Arthur Szlam, and Yann Lecun. 2014. Spectral networks and locally connected networks on graphs. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3572848.3577528"},{"key":"e_1_3_2_1_5_1","volume-title":"DGNN-Booster: A Generic FPGA Accelerator Framework For Dynamic Graph Neural Network Inference. In International Symposium on Field-Programmable Custom Computing Machines (FCCM).","author":"Chen Hanqiu","year":"2023","unstructured":"Hanqiu Chen and Cong Hao. 2023. DGNN-Booster: A Generic FPGA Accelerator Framework For Dynamic Graph Neural Network Inference. In International Symposium on Field-Programmable Custom Computing Machines (FCCM)."},{"key":"e_1_3_2_1_6_1","volume-title":"International Conference on Learning Representations (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 International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10070964"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00532"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330925"},{"key":"e_1_3_2_1_10_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 (NeurIPS)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.14778\/3574245.3574256"},{"key":"e_1_3_2_1_12_1","volume-title":"Graph Neural Network-Based Anomaly Detection in Multivariate Time Series. In AAAI conference on artificial intelligence (AAAI).","author":"Deng Ailin","year":"2021","unstructured":"Ailin Deng and Bryan Hooi. 2021. Graph Neural Network-Based Anomaly Detection in Multivariate Time Series. In AAAI conference on artificial intelligence (AAAI)."},{"key":"e_1_3_2_1_13_1","volume-title":"Global Neighbor Sampling for Mixed CPU-GPU Training on Giant Graphs. In ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD).","author":"Dong Jialin","year":"2021","unstructured":"Jialin Dong, Da Zheng, Lin\u00a0F. Yang, and George Karypis. 2021. Global Neighbor Sampling for Mixed CPU-GPU Training on Giant Graphs. In ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)."},{"key":"e_1_3_2_1_14_1","unstructured":"Facebook 2023. GLOO. https:\/\/github.com\/facebookincubator\/gloo visited on 2023-02-01."},{"key":"e_1_3_2_1_15_1","volume-title":"Graph Neural Networks for Social Recommendation. In The World Wide Web Conference (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 The World Wide Web Conference (WWW)."},{"key":"e_1_3_2_1_16_1","volume-title":"ICLR Workshop on Representation Learning on Graphs and Manifolds (ICLRW)","author":"Fey Matthias","year":"2019","unstructured":"Matthias Fey and Jan\u00a0Eric Lenssen. 2019. Fast graph representation learning with PyTorch Geometric. ICLR Workshop on Representation Learning on Graphs and Manifolds (ICLRW) (2019)."},{"key":"e_1_3_2_1_17_1","volume-title":"International Conference on Machine Learning (ICML).","author":"Fey M.","unstructured":"M. Fey, J.\u00a0E. Lenssen, F. Weichert, and J. Leskovec. 2021. GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings. In International Conference on Machine Learning (ICML)."},{"key":"e_1_3_2_1_18_1","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 (NeurIPS)."},{"key":"e_1_3_2_1_19_1","volume-title":"USENIX Symposium on Operating Systems Design and Implementation (OSDI).","author":"Gandhi Swapnil","year":"2021","unstructured":"Swapnil Gandhi and Anand\u00a0Padmanabha Iyer. 2021. P3: Distributed Deep Graph Learning at Scale.. In USENIX Symposium on Operating Systems Design and Implementation (OSDI)."},{"key":"e_1_3_2_1_20_1","unstructured":"Johannes Gasteiger Florian Becker and Stephan G\u00fcnnemann. 2021. GemNet: Universal Directional Graph Neural Networks for Molecules. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00079"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783759"},{"key":"e_1_3_2_1_23_1","unstructured":"Will Hamilton Zhitao Ying and Jure Leskovec. 2017. Inductive Representation Learning on Large Graphs. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"e_1_3_2_1_26_1","unstructured":"Weihua Hu Matthias Fey Marinka Zitnik Yuxiao Dong Hongyu Ren Bowen Liu Michele Catasta and Jure Leskovec. 2020. Open Graph Benchmark: Datasets for Machine Learning on Graphs. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Binxuan Huang and Kathleen Carley. 2019. Syntax-Aware Aspect Level Sentiment Classification with Graph Attention Networks. In Conference on Empirical Methods in Natural Language Processing and International Joint Conference on Natural Language Processing (EMNLP-IJCNLP).","DOI":"10.18653\/v1\/D19-1549"},{"key":"e_1_3_2_1_28_1","volume-title":"Conference on Machine Learning and Systems (MLSys).","author":"Jia Zhihao","year":"2020","unstructured":"Zhihao Jia, Sina Lin, Mingyu Gao, Matei Zaharia, and Alex Aiken. 2020. Improving the Accuracy, Scalability, and Performance of Graph Neural Networks with Roc. In Conference on Machine Learning and Systems (MLSys)."},{"key":"e_1_3_2_1_29_1","volume-title":"HBM (High Bandwidth Memory) DRAM Technology and Architecture. In IEEE International Memory Workshop (IMW).","author":"Jun Hongshin","year":"2017","unstructured":"Hongshin Jun, Jinhee Cho, Kangseol Lee, Ho-Young Son, Kwiwook Kim, Hanho Jin, and Keith Kim. 2017. HBM (High Bandwidth Memory) DRAM Technology and Architecture. In IEEE International Memory Workshop (IMW)."},{"key":"e_1_3_2_1_30_1","volume-title":"Communication-Efficient Graph Neural Networks with Probabilistic Neighborhood Expansion Analysis and Caching. In Conference on Machine Learning and Systems (MLSys).","author":"Kaler Tim","year":"2023","unstructured":"Tim Kaler, Alexandros-Stavros Iliopoulos, Philip Murzynowski, Tao\u00a0B. Schardl, Charles\u00a0E. Leiserson, and Jie Chen. 2023. Communication-Efficient Graph Neural Networks with Probabilistic Neighborhood Expansion Analysis and Caching. In Conference on Machine Learning and Systems (MLSys)."},{"key":"e_1_3_2_1_31_1","volume-title":"Conference on Machine Learning and Systems (MLSys).","author":"Kaler Tim","year":"2022","unstructured":"Tim Kaler, Nickolas Stathas, Anne Ouyang, Alexandros-Stavros Iliopoulos, Tao Schardl, Charles\u00a0E Leiserson, and Jie Chen. 2022. Accelerating training and inference of graph neural networks with fast sampling and pipelining. In Conference on Machine Learning and Systems (MLSys)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1137\/S1064827595287997"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599843"},{"key":"e_1_3_2_1_34_1","volume-title":"Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907","author":"Kipf N","year":"2016","unstructured":"Thomas\u00a0N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)."},{"key":"e_1_3_2_1_35_1","volume-title":"Gradient-based learning applied to document recognition. Proc","author":"LeCun Yann","year":"1998","unstructured":"Yann LeCun, L\u00e9on Bottou, Yoshua Bengio, and Patrick Haffner. 1998. Gradient-based learning applied to document recognition. Proc. IEEE (1998)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.14778\/3137765.3137776"},{"key":"e_1_3_2_1_37_1","volume-title":"Shrinking Diameters and Possible Explanations. In ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD).","author":"Leskovec Jure","year":"2005","unstructured":"Jure Leskovec, Jon Kleinberg, and Christos Faloutsos. 2005. Graphs over Time: Densification Laws, Shrinking Diameters and Possible Explanations. In ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)."},{"key":"e_1_3_2_1_38_1","volume-title":"NVLink, NV-SLI, NVSwitch and GPUDirect","author":"Li Ang","year":"2020","unstructured":"Ang Li, Shuaiwen\u00a0Leon Song, Jieyang Chen, Jiajia Li, Xu Liu, Nathan\u00a0R. Tallent, and Kevin\u00a0J. Barker. 2020. Evaluating Modern GPU Interconnect: PCIe, NVLink, NV-SLI, NVSwitch and GPUDirect. IEEE Transactions on Parallel and Distributed Systems (IEEE TPDS) (2020)."},{"key":"e_1_3_2_1_39_1","volume-title":"International Conference on Machine Learning (ICML).","author":"Li Guohao","year":"2021","unstructured":"Guohao Li, Matthias M\u00fcller, Bernard Ghanem, and Vladlen Koltun. 2021. Training Graph Neural Networks with 1000 Layers. In International Conference on Machine Learning (ICML)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00936"},{"key":"e_1_3_2_1_41_1","volume-title":"Deepergcn: All you need to train deeper gcns. arXiv preprint arXiv:2006.07739","author":"Li Guohao","year":"2020","unstructured":"Guohao Li, Chenxin Xiong, Ali Thabet, and Bernard Ghanem. 2020. Deepergcn: All you need to train deeper gcns. arXiv preprint arXiv:2006.07739 (2020)."},{"key":"e_1_3_2_1_42_1","volume-title":"Scaling Distributed Machine Learning with the Parameter Server. In USENIX Symposium on Operating Systems Design and Implementation (OSDI).","author":"Li Mu","year":"2014","unstructured":"Mu Li, David\u00a0G. Andersen, Jun\u00a0Woo Park, Alexander\u00a0J. Smola, Amr Ahmed, Vanja Josifovski, James Long, Eugene\u00a0J. Shekita, and Bor-Yiing Su. 2014. Scaling Distributed Machine Learning with the Parameter Server. In USENIX Symposium on Operating Systems Design and Implementation (OSDI)."},{"key":"e_1_3_2_1_43_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Liao Yi-Lun","year":"2023","unstructured":"Yi-Lun Liao and Tess Smidt. 2023. Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_44_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Liao Yi-Lun","year":"2024","unstructured":"Yi-Lun Liao, Brandon Wood, Abhishek Das*, and Tess Smidt*. 2024. EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421281"},{"key":"e_1_3_2_1_46_1","volume-title":"BGL: GPU-Efficient GNN Training by Optimizing Graph Data I\/O and Preprocessing. arXiv preprint arXiv:2112.08541","author":"Liu Tianfeng","year":"2021","unstructured":"Tianfeng Liu, Yangrui Chen, Dan Li, Chuan Wu, Yibo Zhu, Jun He, Yanghua Peng, Hongzheng Chen, Hongzhi Chen, and Chuanxiong Guo. 2021. BGL: GPU-Efficient GNN Training by Optimizing Graph Data I\/O and Preprocessing. arXiv preprint arXiv:2112.08541 (2021)."},{"key":"e_1_3_2_1_47_1","volume-title":"USENIX Annual Technical Conference (ATC).","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 USENIX Annual Technical Conference (ATC)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.14778\/3476249.3476264"},{"key":"e_1_3_2_1_49_1","volume-title":"Simple and Deep Graph Convolutional Networks. In International Conference on Machine Learning (ICML).","author":"Ming\u00a0Chen Zhewei\u00a0Wei","year":"2020","unstructured":"Zhewei\u00a0Wei Ming\u00a0Chen, Bolin\u00a0Ding Zengfeng\u00a0Huang, and Yaliang Li. 2020. Simple and Deep Graph Convolutional Networks. In International Conference on Machine Learning (ICML)."},{"key":"e_1_3_2_1_50_1","unstructured":"NVIDIA. 2023. InfiniBand Network. https:\/\/docs.nvidia.com\/networking\/display\/MLNXOFEDv493150\/InfiniBand+Network visited on 2023-01-30."},{"key":"e_1_3_2_1_51_1","unstructured":"NVIDIA. 2023. NCCL. https:\/\/github.com\/NVIDIA\/nccl visited on 2023-02-01."},{"key":"e_1_3_2_1_52_1","unstructured":"NVIDIA. 2023. NVLink Bridge. https:\/\/www.nvidia.com\/en-us\/design-visualization\/nvlink-bridges\/ visited on 2023-06-01."},{"key":"e_1_3_2_1_53_1","volume-title":"Graph Neural Networks Exponentially Lose Expressive Power for Node Classification. In International Conference on Learning Representations (ICLR).","author":"Oono Kenta","year":"2020","unstructured":"Kenta Oono and Taiji Suzuki. 2020. Graph Neural Networks Exponentially Lose Expressive Power for Node Classification. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.14778\/3551793.3551819"},{"key":"e_1_3_2_1_55_1","volume-title":"Pytorch: Tensors and dynamic neural networks in python with strong gpu acceleration.","author":"Paszke Adam","year":"2017","unstructured":"Adam Paszke, Sam Gross, Soumith Chintala, and Gregory Chanan. 2017. Pytorch: Tensors and dynamic neural networks in python with strong gpu acceleration. (2017)."},{"key":"e_1_3_2_1_56_1","volume-title":"Proceedings of the VLDB Endowment (VLDB)","author":"Peng Jingshu","year":"2022","unstructured":"Jingshu Peng, Zhao Chen, Yingxia Shao, Yanyan Shen, Lei Chen, and Jiannong Cao. 2022. Sancus: Staleness-Aware Communication-Avoiding Full-Graph Decentralized Training in Large-Scale Graph Neural Networks. Proceedings of the VLDB Endowment (VLDB) (2022)."},{"key":"e_1_3_2_1_57_1","volume-title":"Self-Supervised Graph Transformer on Large-Scale Molecular Data. Advances in Neural Information Processing Systems (NeurIPS)","author":"Rong Yu","year":"2020","unstructured":"Yu Rong, Yatao Bian, Tingyang Xu, Weiyang Xie, Ying Wei, Wenbing Huang, and Junzhou Huang. 2020. Self-Supervised Graph Transformer on Large-Scale Molecular Data. Advances in Neural Information Processing Systems (NeurIPS) (2020)."},{"key":"e_1_3_2_1_58_1","volume-title":"DropEdge: Towards Deep Graph Convolutional Networks on Node Classification. In International Conference on Learning Representations (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 International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_59_1","volume-title":"FlowGNN: A Dataflow Architecture for Real-Time Workload-Agnostic Graph Neural Network Inference. In International Symposium on High-Performance Computer Architecture (HPCA).","author":"Sarkar Rishov","year":"2023","unstructured":"Rishov Sarkar, Stefan Abi-Karam, Yuqi He, Lakshmi Sathidevi, and Cong Hao. 2023. FlowGNN: A Dataflow Architecture for Real-Time Workload-Agnostic Graph Neural Network Inference. In International Symposium on High-Performance Computer Architecture (HPCA)."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"crossref","unstructured":"Marco Serafini and Hui Guan. 2021. Scalable Graph Neural Network Training: The Case for Sampling. SIGOPS Oper. Syst. Rev. (2021).","DOI":"10.1145\/3469379.3469387"},{"key":"e_1_3_2_1_61_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Shi Zhihao","year":"2023","unstructured":"Zhihao Shi, Xize Liang, and Jie Wang. 2023. LMC: Fast Training of GNNs via Subgraph Sampling with Provable Convergence. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2024.3376680"},{"key":"e_1_3_2_1_63_1","volume-title":"Graph neural networks in particle physics","author":"Shlomi Jonathan","year":"2020","unstructured":"Jonathan Shlomi, Peter Battaglia, and Jean-Roch Vlimant. 2020. Graph neural networks in particle physics. Machine Learning: Science and Technology (2020)."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","unstructured":"Jaeyong Song Hongsun Jang Hunseong Lim Jaewon Jung Youngsok Kim and Jinho Lee. 2024. AIS-SNU\/GraNNDis_Artifact: Artifact Evaluation Submission. https:\/\/doi.org\/10.5281\/zenodo.12738844","DOI":"10.5281\/zenodo.12738844"},{"key":"e_1_3_2_1_65_1","volume-title":"Legion: Automatically Pushing the Envelope of Multi-GPU System for Billion-Scale GNN Training. In USENIX Annual Technical Conference (USENIX ATC 23)","author":"Sun Jie","year":"2023","unstructured":"Jie Sun, Li Su, Zuocheng Shi, Wenting Shen, Zeke Wang, Lei Wang, Jie Zhang, Yong Li, Wenyuan Yu, Jingren Zhou, and Fei Wu. 2023. Legion: Automatically Pushing the Envelope of Multi-GPU System for Billion-Scale GNN Training. In USENIX Annual Technical Conference (USENIX ATC 23). 165\u2013179."},{"key":"e_1_3_2_1_66_1","volume-title":"Helios: An Efficient Out-of-core GNN Training System on Terabyte-scale Graphs with In-memory Performance. arXiv preprint arXiv:2310.00837","author":"Sun Jie","year":"2023","unstructured":"Jie Sun, Mo Sun, Zheng Zhang, Jun Xie, Zuocheng Shi, Zihan Yang, Jie Zhang, Fei Wu, and Zeke Wang. 2023. Helios: An Efficient Out-of-core GNN Training System on Terabyte-scale Graphs with In-memory Performance. arXiv preprint arXiv:2310.00837 (2023)."},{"key":"e_1_3_2_1_67_1","unstructured":"Ilya Sutskever Oriol Vinyals and Quoc\u00a0V. Le. 2014. Sequence to Sequence Learning with Neural Networks. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_68_1","volume-title":"Quiver: Supporting GPUs for Low-Latency, High-Throughput GNN Serving with Workload Awareness. arXiv preprint","author":"Tan Zeyuan","year":"2023","unstructured":"Zeyuan Tan, Xiulong Yuan, Congjie He, Man-Kit Sit, Guo Li, Xiaoze Liu, Baole Ai, Kai Zeng, Peter Pietzuch, and Luo Mai. 2023. Quiver: Supporting GPUs for Low-Latency, High-Throughput GNN Serving with Workload Awareness. arXiv preprint (2023)."},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/1401890.1402008"},{"key":"e_1_3_2_1_70_1","volume-title":"Optimization of Collective Communication Operations in MPICH. IJHPCA","author":"Thakur Rajeev","year":"2005","unstructured":"Rajeev Thakur, Rolf Rabenseifner, and William Gropp. 2005. Optimization of Collective Communication Operations in MPICH. IJHPCA (2005), 49\u201366."},{"key":"e_1_3_2_1_71_1","volume-title":"USENIX Symposium on Operating Systems Design and Implementation (OSDI).","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\u00a0Harry Xu. 2021. Dorylus: Affordable, Scalable, and Accurate GNN Training with Distributed CPU Servers and Serverless Threads. In USENIX Symposium on Operating Systems Design and Implementation (OSDI)."},{"key":"e_1_3_2_1_72_1","volume-title":"Reducing Communication in Graph Neural Network Training. In International Conference for High Performance Computing, Networking, Storage and Analysis (SC).","author":"Tripathy Alok","year":"2020","unstructured":"Alok Tripathy, Katherine Yelick, and Ayd\u0131n Bulu\u00e7. 2020. Reducing Communication in Graph Neural Network Training. In International Conference for High Performance Computing, Networking, Storage and Analysis (SC)."},{"key":"e_1_3_2_1_73_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan\u00a0N. Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_74_1","volume-title":"Graph Attention Networks. In International Conference on Learning Representations (ICLR).","author":"Veli\u010dkovi\u0107 Petar","year":"2018","unstructured":"Petar Veli\u010dkovi\u0107, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Li\u00f2, and Yoshua Bengio. 2018. Graph Attention Networks. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_75_1","volume-title":"MariusGNN: Resource-Efficient Out-of-Core Training of Graph Neural Networks. In European Conference on Computer Systems (EuroSys).","author":"Waleffe Roger","year":"2023","unstructured":"Roger Waleffe, Jason Mohoney, Theodoros Rekatsinas, and Shivaram Venkataraman. 2023. MariusGNN: Resource-Efficient Out-of-Core Training of Graph Neural Networks. In European Conference on Computer Systems (EuroSys)."},{"key":"e_1_3_2_1_76_1","volume-title":"BNS-GCN: Efficient Full-Graph Training of Graph Convolutional Networks with Partition-Parallelism and Random Boundary Node Sampling. In Conference on Machine Learning and Systems (MLSys).","author":"Wan Cheng","year":"2022","unstructured":"Cheng Wan, Youjie Li, Ang Li, Nam\u00a0Sung Kim, and Yingyan Lin. 2022. BNS-GCN: Efficient Full-Graph Training of Graph Convolutional Networks with Partition-Parallelism and Random Boundary Node Sampling. In Conference on Machine Learning and Systems (MLSys)."},{"key":"e_1_3_2_1_77_1","volume-title":"PipeGCN: Efficient Full-Graph Training of Graph Convolutional Networks with Pipelined Feature Communication. In International Conference on Learning Representations (ICLR).","author":"Wan Cheng","year":"2022","unstructured":"Cheng Wan, Youjie Li, Cameron\u00a0R. Wolfe, Anastasios Kyrillidis, Nam\u00a0Sung Kim, and Yingyan Lin. 2022. PipeGCN: Efficient Full-Graph Training of Graph Convolutional Networks with Pipelined Feature Communication. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_78_1","volume-title":"Deep graph library: A graph-centric, highly-performant package for graph neural networks. arXiv preprint arXiv:1909.01315","author":"Wang Minjie","year":"2019","unstructured":"Minjie Wang, Da Zheng, Zihao Ye, Quan Gan, Mufei Li, Xiang Song, Jinjing Zhou, Chao Ma, Lingfan Yu, Yu Gai, 2019. Deep graph library: A graph-centric, highly-performant package for graph neural networks. arXiv preprint arXiv:1909.01315 (2019)."},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626733"},{"key":"e_1_3_2_1_80_1","volume-title":"NeutronStar: Distributed GNN Training with Hybrid Dependency Management. In International Conference on Management of Data (SIGMOD).","author":"Wang Qiange","year":"2022","unstructured":"Qiange Wang, Yanfeng Zhang, Hao Wang, Chaoyi Chen, Xiaodong Zhang, and Ge Yu. 2022. NeutronStar: Distributed GNN Training with Hybrid Dependency Management. In International Conference on Management of Data (SIGMOD)."},{"key":"e_1_3_2_1_81_1","unstructured":"Zhanghao Wu Paras Jain Matthew Wright Azalia Mirhoseini Joseph\u00a0E Gonzalez and Ion Stoica. 2021. Representing Long-Range Context for Graph Neural Networks with Global Attention. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_82_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Xu Keyulu","year":"2019","unstructured":"Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. 2019. How Powerful are Graph Neural Networks?. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00012"},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783417"},{"key":"e_1_3_2_1_85_1","volume-title":"Revisiting over-smoothing in deep GCNs. arXiv preprint","author":"Yang Chaoqi","year":"2020","unstructured":"Chaoqi Yang, Ruijie Wang, Shuochao Yao, Shengzhong Liu, and Tarek Abdelzaher. 2020. Revisiting over-smoothing in deep GCNs. arXiv preprint (2020)."},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"crossref","unstructured":"Dongxu Yang Junhong Liu Jiaxing Qi and Junjie Lai. 2022. WholeGraph: A Fast Graph Neural Network Training Framework with Multi-GPU Distributed Shared Memory Architecture. In International Conference on High Performance Computing Networking Storage and Analysis (SC).","DOI":"10.1109\/SC41404.2022.00059"},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1145\/3492321.3519557"},{"key":"e_1_3_2_1_88_1","unstructured":"Chengxuan Ying Tianle Cai Shengjie Luo Shuxin Zheng Guolin Ke Di He Yanming Shen and Tie-Yan Liu. 2021. Do Transformers Really Perform Badly for Graph Representation?. In Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.1145\/3559009.3569693"},{"key":"e_1_3_2_1_90_1","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2021.3090954"},{"key":"e_1_3_2_1_91_1","volume-title":"SGCN: Exploiting Compressed-Sparse Features in Deep Graph Convolutional Network Accelerators. In International Symposium on High-Performance Computer Architecture (HPCA).","author":"Yoo M.","unstructured":"M. Yoo, J. Song, J. Lee, N. Kim, Y. Kim, and J. Lee. 2023. SGCN: Exploiting Compressed-Sparse Features in Deep Graph Convolutional Network Accelerators. In International Symposium on High-Performance Computer Architecture (HPCA)."},{"key":"e_1_3_2_1_92_1","unstructured":"Hanqing Zeng Muhan Zhang Yinglong Xia Ajitesh Srivastava Andrey Malevich Rajgopal Kannan Viktor Prasanna Long Jin and Ren Chen. 2021. Decoupling the Depth and Scope of Graph Neural Networks. In Advances in Neural Information Processing Systems (NeurIPS) A.\u00a0Beygelzimer Y.\u00a0Dauphin P.\u00a0Liang and J.\u00a0Wortman Vaughan (Eds.)."},{"key":"e_1_3_2_1_93_1","volume-title":"GraphSAINT: Graph Sampling Based Inductive Learning Method. In International Conference on Learning Representations (ICLR).","author":"Zeng Hanqing","year":"2020","unstructured":"Hanqing Zeng, Hongkuan Zhou, Ajitesh Srivastava, Rajgopal Kannan, and Viktor\u00a0K. Prasanna. 2020. GraphSAINT: Graph Sampling Based Inductive Learning Method. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_94_1","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415539"},{"key":"e_1_3_2_1_95_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589311"},{"key":"e_1_3_2_1_96_1","volume-title":"DistDGL: Distributed Graph Neural Network Training for Billion-Scale Graphs. arXiv preprint arXiv:2010.05337","author":"Zheng Da","year":"2020","unstructured":"Da Zheng, Chao Ma, Minjie Wang, Jinjing Zhou, Qidong Su, Xiang Song, Quan Gan, Zheng Zhang, and George Karypis. 2020. DistDGL: Distributed Graph Neural Network Training for Billion-Scale Graphs. arXiv preprint arXiv:2010.05337 (2020)."},{"key":"e_1_3_2_1_97_1","volume-title":"Distributed Hybrid CPU and GPU Training for Graph Neural Networks on Billion-Scale Heterogeneous Graphs. In ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD).","author":"Zheng Da","year":"2022","unstructured":"Da Zheng, Xiang Song, Chengru Yang, Dominique LaSalle, and George Karypis. 2022. Distributed Hybrid CPU and GPU Training for Graph Neural Networks on Billion-Scale Heterogeneous Graphs. In ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)."},{"key":"e_1_3_2_1_98_1","doi-asserted-by":"publisher","DOI":"10.1145\/3559009.3569670"},{"key":"e_1_3_2_1_99_1","doi-asserted-by":"publisher","DOI":"10.14778\/3352063.3352127"}],"event":{"name":"PACT '24: International Conference on Parallel Architectures and Compilation Techniques","location":"Long Beach CA USA","acronym":"PACT '24","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 2024 International Conference on Parallel Architectures and Compilation Techniques"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3656019.3676892","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3656019.3676892","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T19:55:28Z","timestamp":1755892528000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3656019.3676892"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,13]]},"references-count":99,"alternative-id":["10.1145\/3656019.3676892","10.1145\/3656019"],"URL":"https:\/\/doi.org\/10.1145\/3656019.3676892","relation":{},"subject":[],"published":{"date-parts":[[2024,10,13]]},"assertion":[{"value":"2024-10-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}