{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T17:10:41Z","timestamp":1768583441205,"version":"3.49.0"},"reference-count":56,"publisher":"Association for Computing Machinery (ACM)","issue":"1","funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"crossref","award":["2021ZD0113304"],"award-info":[{"award-number":["2021ZD0113304"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U23A20316"],"award-info":[{"award-number":["U23A20316"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Key R&D Project of Hubei Province","award":["2021BAA029"],"award-info":[{"award-number":["2021BAA029"]}]},{"name":"Founded by Joint&Laboratory on Credit Technology"},{"name":"General Program of Natural Science Foundation of China (NSFC) of China","award":["62072346"],"award-info":[{"award-number":["62072346"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Internet Technol."],"published-print":{"date-parts":[[2026,2,28]]},"abstract":"<jats:p>AI has found extensive application in edge analytics, with Deep Neural Networks effectively processing and analyzing data. Some applications need to deal with unstructured data like graphs. This complexity and diversity of unstructured features pose challenges for traditional DNN models. Therefore, Graph Neural Networks have emerged as a significant solution. However, GNNs encounter two primary challenges in edge analytics scenarios: scalability and efficiency. These challenges arise primarily from significant structural differences among various graphs and models. To address these issues, we propose AGF, an Adaptive GNN Framework. AGF consists of three components: subgraph partitioning and model partitioning, scalable hardware architecture, and design space exploration. Subgraph partitioning and model partitioning transform complex and diverse GNNs into a uniform computing flow and subgraphs. These can be directly mapped onto the hardware kernel, leveraging GNN characteristics to achieve independent parallelism. The hardware architecture is based on a multi-level processing element structure, which can efficiently parallelize subgraphs and vertices based on the partitioning. The design space exploration selects kernel allocation strategies and setups based on the hardware, dataset, and model. We validated AGF using six datasets and three GNN models. The results demonstrate that our framework achieves an acceleration ranging from 4.54 to 53.17\u00d7 compared to the GPU-based GNN framework. When compared to other FPGA-based GNN accelerators, AGF achieves a latency reduction ranging from 1.16 to 33.6\u00d7 in model execution and from 1.09 to 2.37\u00d7 in end-to-end scenarios.<\/jats:p>","DOI":"10.1145\/3744923","type":"journal-article","created":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T21:18:35Z","timestamp":1750281515000},"page":"1-30","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["AGF: Adaptive GNN Framework via Subgraph and Model Partitioning for Edge Analysis"],"prefix":"10.1145","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8281-0458","authenticated-orcid":false,"given":"Zimeng","family":"Fan","sequence":"first","affiliation":[{"name":"School of Computer Science, Wuhan University","place":["Wuhan, China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8766-1105","authenticated-orcid":false,"given":"Min","family":"Peng","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University","place":["Wuhan, China"]}]}],"member":"320","published-online":{"date-parts":[[2026,1,14]]},"reference":[{"key":"e_1_3_1_2_2","unstructured":"Stefan Abi-Karam Yuqi He Rishov Sarkar Lakshmi Sathidevi Zihang Qiao and Cong Hao. 2022. GenGNN: A generic FPGA framework for graph neural network acceleration. arXiv preprint arXiv:2201.08475."},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2016.110"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218751"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3146347.3146356"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2017.85"},{"key":"e_1_3_1_7_2","unstructured":"Jingji Chen Zhuoming Chen and Xuehai Qian. 2023. GNNPipe: Scaling deep GNN training with pipelined model parallelism. arXiv preprint arXiv:2308.10087."},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330925"},{"key":"e_1_3_1_9_2","volume-title":"Proceedings of the NeurIPS 2022 Workshop: New Frontiers in Graph Learning","author":"Ding Mucong","year":"2022","unstructured":"Mucong Ding, Tahseen Rabbani, Bang An, Evan Z. Wang, and Furong Huang. 2022. Sketch-GNN: Scalable graph neural networks with sublinear training complexity. In Proceedings of the NeurIPS 2022 Workshop: New Frontiers in Graph Learning."},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313488"},{"key":"e_1_3_1_11_2","article-title":"Fast graph representation learning with PyTorch geometric","author":"Fey Matthias","year":"2019","unstructured":"Matthias Fey and Jan Eric Lenssen. 2019. Fast graph representation learning with PyTorch geometric. In Proceedings of the ICLR Workshop on Representation Learning on Graphs and Manifold.","journal-title":"Proceedings of the ICLR Workshop on Representation Learning on Graphs and Manifold"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3281714"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00079"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2022.102578"},{"key":"e_1_3_1_15_2","article-title":"Inductive representation learning on large graphs","author":"Hamilton Will","year":"2017","unstructured":"Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. In Proceedings of the 31st International Conference on Neural Information Processing Systems.","journal-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511990"},{"key":"e_1_3_1_17_2","first-page":"22118","article-title":"Open graph benchmark: Datasets for machine learning on graphs","author":"Hu Weihua","year":"2020","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 Proceedings of the 34th International Conference on Neural Information Processing Systems. 22118\u201322133.","journal-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00079"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10070983"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401072"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1137\/S1064827595287997"},{"key":"e_1_3_1_22_2","volume-title":"Proceedings of the 5th International Conference on Learning Representations, ICLR","author":"Kipf Thomas N.","year":"2017","unstructured":"Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of the 5th International Conference on Learning Representations, ICLR."},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/IV51971.2022.9827230"},{"key":"e_1_3_1_24_2","first-page":"120","article-title":"PyTorch-BigGraph: A large scale graph embedding system","volume":"1","author":"Lerer Adam","year":"2019","unstructured":"Adam Lerer, Ledell Wu, Jiajun Shen, Timothee Lacroix, Luca Wehrstedt, Abhijit Bose, and Alex Peysakhovich. 2019. PyTorch-BigGraph: A large scale graph embedding system. Proceedings of Machine Learning and Systems 1 (2019), 120\u2013131.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00070"},{"issue":"11","key":"e_1_3_1_26_2","first-page":"2834","article-title":"SGCNAX: A scalable graph convolutional neural network accelerator with workload balancing","volume":"33","author":"Li Jiajun","year":"2021","unstructured":"Jiajun Li, Hao Zheng, Ke Wang, and Ahmed Louri. 2021. SGCNAX: A scalable graph convolutional neural network accelerator with workload balancing. IEEE Transactions on Parallel and Distributed Systems 33, 11 (2021), 2834\u20132845.","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599374"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530479"},{"key":"e_1_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Libo Qin Xiao Xu Wanxiang Che and Ting Liu. 2020. AGIF: An adaptive graph-interactive framework for joint multiple intent detection and slot filling. Findings of the Association for Computational Linguistics (2020) 1807\u20131816.","DOI":"10.18653\/v1\/2020.findings-emnlp.163"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071015"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v29i3.2157"},{"key":"e_1_3_1_32_2","volume-title":"Proceedings of the 11th International Conference on Learning Representations","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 Proceedings of the 11th International Conference on Learning Representations."},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583340"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3691636"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS47924.2020.00100"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2022.06.010"},{"key":"e_1_3_1_37_2","volume-title":"Proceedings of the International Conference on Learning Representations","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 Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_1_38_2","unstructured":"Minjie Wang Da Zheng Zihao Ye Quan Gan Mufei Li Xiang Song Jinjing Zhou Chao Ma Lingfan Yu Yu Gai et\u00a0al. 2019. Deep graph library: A graph-centric highly-performant package for graph neural networks. arXiv preprint arXiv:1909.01315."},{"key":"e_1_3_1_39_2","first-page":"515","volume-title":"Proceedings of the 15th USENIX Symposium on Operating Systems Design and Implementation (OSDI 21)","author":"Wang Yuke","year":"2021","unstructured":"Yuke Wang, Boyuan Feng, Gushu Li, Shuangchen Li, Lei Deng, Yuan Xie, and Yufei Ding. 2021. \\(\\lbrace\\) GNNAdvisor \\(\\rbrace\\) : An adaptive and efficient runtime system for \\(\\lbrace\\) GNN \\(\\rbrace\\) acceleration on \\(\\lbrace\\) GPUs \\(\\rbrace\\) . In Proceedings of the 15th USENIX Symposium on Operating Systems Design and Implementation (OSDI 21). 515\u2013531."},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068925"},{"key":"e_1_3_1_41_2","unstructured":"Xilinx. 2018. PYNQ: Python Productivity for Zynq. [Online]. Retrieved Sep. 12 2024 from http:\/\/www.pynq.io"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2023.3288755"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-022-04402-x"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106194"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00041"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2022.102596"},{"key":"e_1_3_1_47_2","volume-title":"Proceedings of the 8th International Conference on Learning Representations, ICLR","author":"Zeng Hanqing","year":"2020","unstructured":"Hanqing Zeng, Hongkuan Zhou, Ajitesh Srivastava, Rajgopal Kannan, and Viktor K. Prasanna. 2020. GraphSAINT: Graph sampling based inductive learning method. In Proceedings of the 8th International Conference on Learning Representations, ICLR."},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3229422"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3287883"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098033"},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3279302"},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247875"},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575723"},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3587135.3592199"},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586181"},{"key":"e_1_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746942"},{"key":"e_1_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00020"}],"container-title":["ACM Transactions on Internet Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3744923","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T05:10:33Z","timestamp":1768540233000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3744923"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,14]]},"references-count":56,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,2,28]]}},"alternative-id":["10.1145\/3744923"],"URL":"https:\/\/doi.org\/10.1145\/3744923","relation":{},"ISSN":["1533-5399","1557-6051"],"issn-type":[{"value":"1533-5399","type":"print"},{"value":"1557-6051","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,14]]},"assertion":[{"value":"2024-12-17","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-06-07","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}