{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T21:54:43Z","timestamp":1775598883870,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,6,17]],"date-time":"2023-06-17T00:00:00Z","timestamp":1686960000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFB4501403"],"award-info":[{"award-number":["2022YFB4501403"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61832006"],"award-info":[{"award-number":["61832006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61825202"],"award-info":[{"award-number":["61825202"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61929103"],"award-info":[{"award-number":["61929103"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Huawei Technologies Co., Ltd","award":["YBN2021035018"],"award-info":[{"award-number":["YBN2021035018"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,6,17]]},"DOI":"10.1145\/3579371.3589091","type":"proceedings-article","created":{"date-parts":[[2023,6,16]],"date-time":"2023-06-16T20:25:28Z","timestamp":1686947128000},"page":"1-13","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":30,"title":["MetaNMP: Leveraging Cartesian-Like Product to Accelerate HGNNs with Near-Memory Processing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4158-5239","authenticated-orcid":false,"given":"Dan","family":"Chen","sequence":"first","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4662-1777","authenticated-orcid":false,"given":"Haiheng","family":"He","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3934-7605","authenticated-orcid":false,"given":"Hai","family":"Jin","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7903-2061","authenticated-orcid":false,"given":"Long","family":"Zheng","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3927-1102","authenticated-orcid":false,"given":"Yu","family":"Huang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6500-8517","authenticated-orcid":false,"given":"Xinyang","family":"Shen","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6302-813X","authenticated-orcid":false,"given":"Xiaofei","family":"Liao","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,6,17]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the Annual International Symposium on Computer Architecture (ISCA). 105--117","author":"Ahn Junwhan","year":"2015","unstructured":"Junwhan Ahn , Sungpack Hong , Sungjoo Yoo , Onur Mutlu , and Kiyoung Choi . 2015 . A Scalable Processing-In-Memory Accelerator for Parallel Graph Processing . In Proceedings of the Annual International Symposium on Computer Architecture (ISCA). 105--117 . Junwhan Ahn, Sungpack Hong, Sungjoo Yoo, Onur Mutlu, and Kiyoung Choi. 2015. A Scalable Processing-In-Memory Accelerator for Parallel Graph Processing. In Proceedings of the Annual International Symposium on Computer Architecture (ISCA). 105--117."},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the IEEE\/ACM International Conference On Computer Aided Design (ICCAD). 1--9.","author":"Arka Aqeeb Iqbal","year":"2021","unstructured":"Aqeeb Iqbal Arka , Biresh Kumar Joardar , Janardhan Rao Doppa , Partha Pratim Pande , and Krishnendu Chakrabarty . 2021 . DARe: DropLayer-Aware Manycore ReRAM Architecture for Training Graph Neural Networks . In Proceedings of the IEEE\/ACM International Conference On Computer Aided Design (ICCAD). 1--9. Aqeeb Iqbal Arka, Biresh Kumar Joardar, Janardhan Rao Doppa, Partha Pratim Pande, and Krishnendu Chakrabarty. 2021. DARe: DropLayer-Aware Manycore ReRAM Architecture for Training Graph Neural Networks. In Proceedings of the IEEE\/ACM International Conference On Computer Aided Design (ICCAD). 1--9."},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the Design Automation Conference (DAC). 1--6.","author":"Auten Adam","year":"2020","unstructured":"Adam Auten , Matthew Tomei , and Rakesh Kumar . 2020 . Hardware Acceleration of Graph Neural Networks . In Proceedings of the Design Automation Conference (DAC). 1--6. Adam Auten, Matthew Tomei, and Rakesh Kumar. 2020. Hardware Acceleration of Graph Neural Networks. In Proceedings of the Design Automation Conference (DAC). 1--6."},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the IEEE\/ACM International Conference On Computer Aided Design (ICCAD). 1--9.","author":"Challapalle Nagadastagiri","year":"2021","unstructured":"Nagadastagiri Challapalle , Karthik Swaminathan , Nandhini Chandramoorthy , and Vijaykrishnan Narayanan . 2021 . Crossbar based Processing in Memory Accelerator Architecture for Graph Convolutional Networks . In Proceedings of the IEEE\/ACM International Conference On Computer Aided Design (ICCAD). 1--9. Nagadastagiri Challapalle, Karthik Swaminathan, Nandhini Chandramoorthy, and Vijaykrishnan Narayanan. 2021. Crossbar based Processing in Memory Accelerator Architecture for Graph Convolutional Networks. In Proceedings of the IEEE\/ACM International Conference On Computer Aided Design (ICCAD). 1--9."},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC). 632--645","author":"Chen Dan","year":"2022","unstructured":"Dan Chen , Chuangyi Gui , Yi Zhang , Hai Jin , Long Zheng , Yu Huang , and Xiaofei Liao . 2022 . GraphFly: Efficient Asynchronous Streaming Graphs Processing via Dependency-Flow . In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC). 632--645 . Dan Chen, Chuangyi Gui, Yi Zhang, Hai Jin, Long Zheng, Yu Huang, and Xiaofei Liao. 2022. GraphFly: Efficient Asynchronous Streaming Graphs Processing via Dependency-Flow. In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC). 632--645."},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the IEEE International Parallel and Distributed Processing Symposium (IPDPS). 246--257","author":"Chen Dan","year":"2022","unstructured":"Dan Chen , Hai Jin , Long Zheng , Yu Huang , Pengcheng Yao , Chuangyi Gui , Qinggang Wang , Haifeng Liu , Haiheng He , Xiaofei Liao , and Ran Zheng . 2022 . A General Offloading Approach for Near-DRAM Processing-In-Memory Architectures . In Proceedings of the IEEE International Parallel and Distributed Processing Symposium (IPDPS). 246--257 . Dan Chen, Hai Jin, Long Zheng, Yu Huang, Pengcheng Yao, Chuangyi Gui, Qinggang Wang, Haifeng Liu, Haiheng He, Xiaofei Liao, and Ran Zheng. 2022. A General Offloading Approach for Near-DRAM Processing-In-Memory Architectures. In Proceedings of the IEEE International Parallel and Distributed Processing Symposium (IPDPS). 246--257."},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the Design, Automation & Test in Europe Conference & Exhibition (DATE). IEEE, 33--38","author":"Chen Ke","unstructured":"Ke Chen , Sheng Li , Naveen Muralimanohar , Jung Ho Ahn , Jay B. Brockman , and Norman P. Jouppi . 2012. CACTI-3DD: Architecture-level Modeling for 3D Die-stacked DRAM Main Memory . In Proceedings of the Design, Automation & Test in Europe Conference & Exhibition (DATE). IEEE, 33--38 . Ke Chen, Sheng Li, Naveen Muralimanohar, Jung Ho Ahn, Jay B. Brockman, and Norman P. Jouppi. 2012. CACTI-3DD: Architecture-level Modeling for 3D Die-stacked DRAM Main Memory. In Proceedings of the Design, Automation & Test in Europe Conference & Exhibition (DATE). IEEE, 33--38."},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the Annual International Symposium on Computer Architecture (ISCA). 130--145","author":"Dai Guohao","year":"2022","unstructured":"Guohao Dai , Zhenhua Zhu , Tianyu Fu , Chiyue Wei , Bangyan Wang , Xiangyu Li , Yuan Xie , Huazhong Yang , and Yu Wang . 2022 . DIMMining: Pruning-Efficient and Parallel Graph Mining on Near-Memory-Computing . In Proceedings of the Annual International Symposium on Computer Architecture (ISCA). 130--145 . Guohao Dai, Zhenhua Zhu, Tianyu Fu, Chiyue Wei, Bangyan Wang, Xiangyu Li, Yuan Xie, Huazhong Yang, and Yu Wang. 2022. DIMMining: Pruning-Efficient and Parallel Graph Mining on Near-Memory-Computing. In Proceedings of the Annual International Symposium on Computer Architecture (ISCA). 130--145."},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the Annual International Symposium on Computer Architecture (ISCA). 639--651","author":"Drumond Mario","unstructured":"Mario Drumond , Alexandros Daglis , Nooshin Sadat Mirzadeh , Dmitrii Ustiugov , Javier Picorel , Babak Falsafi , Boris Grot , and Dionisios N. Pnevmatikatos . 2017. The Mondrian Data Engine . In Proceedings of the Annual International Symposium on Computer Architecture (ISCA). 639--651 . Mario Drumond, Alexandros Daglis, Nooshin Sadat Mirzadeh, Dmitrii Ustiugov, Javier Picorel, Babak Falsafi, Boris Grot, and Dionisios N. Pnevmatikatos. 2017. The Mondrian Data Engine. In Proceedings of the Annual International Symposium on Computer Architecture (ISCA). 639--651."},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the International Symposium on High Performance Computer Architecture (HPCA). 283--295","author":"Farahani Amin Farmahini","year":"2015","unstructured":"Amin Farmahini Farahani , Jung Ho Ahn , Katherine Morrow , and Nam Sung Kim . 2015 . NDA: Near-DRAM Acceleration Architecture Leveraging Commodity DRAM Devices and Standard Memory Modules . In Proceedings of the International Symposium on High Performance Computer Architecture (HPCA). 283--295 . Amin Farmahini Farahani, Jung Ho Ahn, Katherine Morrow, and Nam Sung Kim. 2015. NDA: Near-DRAM Acceleration Architecture Leveraging Commodity DRAM Devices and Standard Memory Modules. In Proceedings of the International Symposium on High Performance Computer Architecture (HPCA). 283--295."},{"key":"e_1_3_2_1_11_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 ). Matthias Fey and Jan Eric Lenssen. 2019. Fast Graph Representation Learning with PyTorch Geometric. CoRR abs\/1903.02428 (2019)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380297"},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems (NeurIPS). 585--593","author":"Gao Jing","year":"2009","unstructured":"Jing Gao , Feng Liang , Wei Fan , Yizhou Sun , and Jiawei Han . 2009 . Graph-based Consensus Maximization among Multiple Supervised and Unsupervised Models . In Proceedings of the Annual Conference on Neural Information Processing Systems (NeurIPS). 585--593 . Jing Gao, Feng Liang, Wei Fan, Yizhou Sun, and Jiawei Han. 2009. Graph-based Consensus Maximization among Multiple Supervised and Unsupervised Models. In Proceedings of the Annual Conference on Neural Information Processing Systems (NeurIPS). 585--593."},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the International Conference on Parallel Architectures and Compilation Techniques (PACT). 113--124","author":"Gao Mingyu","year":"2015","unstructured":"Mingyu Gao , Grant Ayers , and Christos Kozyrakis . 2015 . Practical Near-Data Processing for In-Memory Analytics Frameworks . In Proceedings of the International Conference on Parallel Architectures and Compilation Techniques (PACT). 113--124 . Mingyu Gao, Grant Ayers, and Christos Kozyrakis. 2015. Practical Near-Data Processing for In-Memory Analytics Frameworks. In Proceedings of the International Conference on Parallel Architectures and Compilation Techniques (PACT). 113--124."},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS). 751--764","author":"Gao Mingyu","year":"2017","unstructured":"Mingyu Gao , Jing Pu , Xuan Yang , Mark Horowitz , and Christos Kozyrakis . 2017 . TETRIS: Scalable and Efficient Neural Network Acceleration with 3D Memory . In Proceedings of the International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS). 751--764 . Mingyu Gao, Jing Pu, Xuan Yang, Mark Horowitz, and Christos Kozyrakis. 2017. TETRIS: Scalable and Efficient Neural Network Acceleration with 3D Memory. In Proceedings of the International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS). 751--764."},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO). 922--936","author":"Geng Tong","unstructured":"Tong Geng , Ang Li , Runbin Shi , Chunshu Wu , Tianqi Wang , Yanfei Li , Pouya Haghi , Antonino Tumeo , Shuai Che , Steven K. Reinhardt , and Martin C. Herbordt . 2020. AWB-GCN: A Graph Convolutional Network Accelerator with Runtime Workload Rebalancing . In Proceedings of the Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO). 922--936 . Tong Geng, Ang Li, Runbin Shi, Chunshu Wu, Tianqi Wang, Yanfei Li, Pouya Haghi, Antonino Tumeo, Shuai Che, Steven K. Reinhardt, and Martin C. Herbordt. 2020. AWB-GCN: A Graph Convolutional Network Accelerator with Runtime Workload Rebalancing. In Proceedings of the Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO). 922--936."},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the IEEE International Conference on Computer Vision (ICCV). 4274--4282","author":"Geng Xue","year":"2015","unstructured":"Xue Geng , Hanwang Zhang , Jingwen Bian , and Tat-Seng Chua . 2015 . Learning Image and User Features for Recommendation in Social Networks . In Proceedings of the IEEE International Conference on Computer Vision (ICCV). 4274--4282 . Xue Geng, Hanwang Zhang, Jingwen Bian, and Tat-Seng Chua. 2015. Learning Image and User Features for Recommendation in Social Networks. In Proceedings of the IEEE International Conference on Computer Vision (ICCV). 4274--4282."},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the ACM\/IEEE Design Automation Conference (DAC). 577--582","author":"He Yintao","year":"2021","unstructured":"Yintao He , Ying Wang , Cheng Liu , Huawei Li , and Xiaowei Li . 2021 . TARe: Task-Adaptive in-situ ReRAM Computing for Graph Learning . In Proceedings of the ACM\/IEEE Design Automation Conference (DAC). 577--582 . Yintao He, Ying Wang, Cheng Liu, Huawei Li, and Xiaowei Li. 2021. TARe: Task-Adaptive in-situ ReRAM Computing for Graph Learning. In Proceedings of the ACM\/IEEE Design Automation Conference (DAC). 577--582."},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP). 300--314","author":"Hong Changwan","year":"2019","unstructured":"Changwan Hong , Aravind Sukumaran-Rajam , Israt Nisa , Kunal Singh , and Ponnuswamy Sadayappan . 2019 . Adaptive Sparse Tiling for Sparse Matrix Multiplication . In Proceedings of the ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP). 300--314 . Changwan Hong, Aravind Sukumaran-Rajam, Israt Nisa, Kunal Singh, and Ponnuswamy Sadayappan. 2019. Adaptive Sparse Tiling for Sparse Matrix Multiplication. In Proceedings of the ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP). 300--314."},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD). 1507--1515","author":"Hou Shifu","year":"2017","unstructured":"Shifu Hou , Yanfang Ye , Yangqiu Song , and Melih Abdulhayoglu . 2017 . HinDroid: An Intelligent Android Malware Detection System Based on Structured Heterogeneous Information Network . In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD). 1507--1515 . Shifu Hou, Yanfang Ye, Yangqiu Song, and Melih Abdulhayoglu. 2017. HinDroid: An Intelligent Android Malware Detection System Based on Structured Heterogeneous Information Network. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD). 1507--1515."},{"key":"e_1_3_2_1_21_1","unstructured":"HP laboratories. 2009. CACTI 6.0: A tool to model large caches. Available: https:\/\/www.hpl.hp.com\/techreports\/2009\/HPL-2009-85.pdf.  HP laboratories. 2009. CACTI 6.0: A tool to model large caches. Available: https:\/\/www.hpl.hp.com\/techreports\/2009\/HPL-2009-85.pdf."},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of the ACM\/IEEE Annual International Symposium on Computer Architecture (ISCA). 204--216","author":"Hsieh Kevin","unstructured":"Kevin Hsieh , Eiman Ebrahimi , Gwangsun Kim , Niladrish Chatterjee , Mike O'Connor , Nandita Vijaykumar , Onur Mutlu , and Stephen W. Keckler . 2016. Transparent Offloading and Mapping (TOM): Enabling Programmer-Transparent Near-Data Processing in GPU Systems . In Proceedings of the ACM\/IEEE Annual International Symposium on Computer Architecture (ISCA). 204--216 . Kevin Hsieh, Eiman Ebrahimi, Gwangsun Kim, Niladrish Chatterjee, Mike O'Connor, Nandita Vijaykumar, Onur Mutlu, and Stephen W. Keckler. 2016. Transparent Offloading and Mapping (TOM): Enabling Programmer-Transparent Near-Data Processing in GPU Systems. In Proceedings of the ACM\/IEEE Annual International Symposium on Computer Architecture (ISCA). 204--216."},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence (AAAI). 946--953","author":"Hu Binbin","year":"2019","unstructured":"Binbin Hu , Zhiqiang Zhang , Chuan Shi , Jun Zhou , Xiaolong Li , and Yuan Qi . 2019 . Cash-Out User Detection Based on Attributed Heterogeneous Information Network with a Hierarchical Attention Mechanism . In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI). 946--953 . Binbin Hu, Zhiqiang Zhang, Chuan Shi, Jun Zhou, Xiaolong Li, and Yuan Qi. 2019. Cash-Out User Detection Based on Attributed Heterogeneous Information Network with a Hierarchical Attention Mechanism. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI). 946--953."},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems (NeurIPS). 4869--4880","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 Annual Conference on Neural Information Processing Systems (NeurIPS). 4869--4880 . 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 Annual Conference on Neural Information Processing Systems (NeurIPS). 4869--4880."},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the IEEE International Symposium on High Performance Computer Architecture (HPCA). 1029--1042","author":"Huang Yu","year":"2022","unstructured":"Yu Huang , Long Zheng , Pengcheng Yao , Qinggang Wang , Xiaofei Liao , Hai Jin , and Jingling Xue . 2022 . Accelerating Graph Convolutional Networks Using Crossbar-based Processing-In-Memory Architectures . In Proceedings of the IEEE International Symposium on High Performance Computer Architecture (HPCA). 1029--1042 . Yu Huang, Long Zheng, Pengcheng Yao, Qinggang Wang, Xiaofei Liao, Hai Jin, and Jingling Xue. 2022. Accelerating Graph Convolutional Networks Using Crossbar-based Processing-In-Memory Architectures. In Proceedings of the IEEE International Symposium on High Performance Computer Architecture (HPCA). 1029--1042."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2022.3199152"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2023.3257514"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the International Conference on Computer-Aided Design (ICCAD). 294--301","author":"Jouppi Norman P.","year":"2012","unstructured":"Norman P. Jouppi , Andrew B. Kahng , Naveen Muralimanohar , and Vaishnav Srinivas . 2012 . Cacti-io: Cacti with Off-chip Power-Area-Timing Models . In Proceedings of the International Conference on Computer-Aided Design (ICCAD). 294--301 . Norman P. Jouppi, Andrew B. Kahng, Naveen Muralimanohar, and Vaishnav Srinivas. 2012. Cacti-io: Cacti with Off-chip Power-Area-Timing Models. In Proceedings of the International Conference on Computer-Aided Design (ICCAD). 294--301."},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of the ACM\/IEEE Annual International Symposium on Computer Architecture (ISCA). 679--691","author":"Kal Hongju","year":"2021","unstructured":"Hongju Kal , Seokmin Lee , Gun Ko , and Won Woo Ro . 2021 . SPACE: Locality-Aware Processing in Heterogeneous Memory for Personalized Recommendations . In Proceedings of the ACM\/IEEE Annual International Symposium on Computer Architecture (ISCA). 679--691 . Hongju Kal, Seokmin Lee, Gun Ko, and Won Woo Ro. 2021. SPACE: Locality-Aware Processing in Heterogeneous Memory for Personalized Recommendations. In Proceedings of the ACM\/IEEE Annual International Symposium on Computer Architecture (ISCA). 679--691."},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the ACM\/IEEE Annual International Symposium on Computer Architecture (ISCA). 790--803","author":"Ke Liu","year":"2020","unstructured":"Liu Ke , Udit Gupta , Benjamin Youngjae Cho , David Brooks , Vikas Chandra , Utku Diril , Amin Firoozshahian , Kim M. Hazelwood , Bill Jia , Hsien-Hsin S. Lee , Meng Li , Bert Maher , Dheevatsa Mudigere , Maxim Naumov , Martin Schatz , Mikhail Smelyanskiy , Xiaodong Wang , Brandon Reagen , Carole-Jean Wu , Mark Hempstead , and Xuan Zhang . 2020 . RecNMP: Accelerating Personalized Recommendation with Near-Memory Processing . In Proceedings of the ACM\/IEEE Annual International Symposium on Computer Architecture (ISCA). 790--803 . Liu Ke, Udit Gupta, Benjamin Youngjae Cho, David Brooks, Vikas Chandra, Utku Diril, Amin Firoozshahian, Kim M. Hazelwood, Bill Jia, Hsien-Hsin S. Lee, Meng Li, Bert Maher, Dheevatsa Mudigere, Maxim Naumov, Martin Schatz, Mikhail Smelyanskiy, Xiaodong Wang, Brandon Reagen, Carole-Jean Wu, Mark Hempstead, and Xuan Zhang. 2020. RecNMP: Accelerating Personalized Recommendation with Near-Memory Processing. In Proceedings of the ACM\/IEEE Annual International Symposium on Computer Architecture (ISCA). 790--803."},{"key":"e_1_3_2_1_31_1","volume-title":"Proceedings of the ACM\/IEEE Annual International Symposium on Computer Architecture (ISCA). 380--392","author":"Kim Duckhwan","year":"2016","unstructured":"Duckhwan Kim , Jaeha Kung , Sek M. Chai , Sudhakar Yalamanchili , and Saibal Mukhopadhyay . 2016 . Neurocube: A Programmable Digital Neuromorphic Architecture with High-Density 3D Memory . In Proceedings of the ACM\/IEEE Annual International Symposium on Computer Architecture (ISCA). 380--392 . Duckhwan Kim, Jaeha Kung, Sek M. Chai, Sudhakar Yalamanchili, and Saibal Mukhopadhyay. 2016. Neurocube: A Programmable Digital Neuromorphic Architecture with High-Density 3D Memory. In Proceedings of the ACM\/IEEE Annual International Symposium on Computer Architecture (ISCA). 380--392."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2015.2414456"},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of the USENIX Conference on File and Storage Technologies (FAST). 147--164","author":"Kwon Miryeong","year":"2022","unstructured":"Miryeong Kwon , Donghyun Gouk , Sangwon Lee , and Myoungsoo Jung . 2022 . Hardware\/Software Co-Programmable Framework for Computational SSDs to Accelerate Deep Learning Service on Large-Scale Graphs . In Proceedings of the USENIX Conference on File and Storage Technologies (FAST). 147--164 . Miryeong Kwon, Donghyun Gouk, Sangwon Lee, and Myoungsoo Jung. 2022. Hardware\/Software Co-Programmable Framework for Computational SSDs to Accelerate Deep Learning Service on Large-Scale Graphs. In Proceedings of the USENIX Conference on File and Storage Technologies (FAST). 147--164."},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the Annual International Symposium on Computer Architecture (ISCA). 932--945","author":"Lee Yunjae","year":"2022","unstructured":"Yunjae Lee , Jinha Chung , and Minsoo Rhu . 2022 . SmartSAGE: Training Large-scale Graph Neural Networks using In-Storage Processing Architectures . In Proceedings of the Annual International Symposium on Computer Architecture (ISCA). 932--945 . Yunjae Lee, Jinha Chung, and Minsoo Rhu. 2022. SmartSAGE: Training Large-scale Graph Neural Networks using In-Storage Processing Architectures. In Proceedings of the Annual International Symposium on Computer Architecture (ISCA). 932--945."},{"key":"e_1_3_2_1_35_1","volume-title":"Proceedings of the IEEE International Symposium on High-Performance Computer Architecture (HPCA). 775--788","author":"Li Jiajun","unstructured":"Jiajun Li , Ahmed Louri , Avinash Karanth , and Razvan C. Bunescu . 2021. GCNAX: A Flexible and Energy-efficient Accelerator for Graph Convolutional Neural Networks . In Proceedings of the IEEE International Symposium on High-Performance Computer Architecture (HPCA). 775--788 . Jiajun Li, Ahmed Louri, Avinash Karanth, and Razvan C. Bunescu. 2021. GCNAX: A Flexible and Energy-efficient Accelerator for Graph Convolutional Neural Networks. In Proceedings of the IEEE International Symposium on High-Performance Computer Architecture (HPCA). 775--788."},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of USENIX Annual Technical Conference (ATC). 443--458","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 Proceedings of USENIX Annual Technical Conference (ATC). 443--458 . 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 Proceedings of USENIX Annual Technical Conference (ATC). 443--458."},{"key":"e_1_3_2_1_37_1","volume-title":"Proceedings of the Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO). 50:1--50:13","author":"Moghaddam Hadi Asghari","year":"2016","unstructured":"Hadi Asghari Moghaddam , Young Hoon Son , Jung Ho Ahn , and Nam Sung Kim . 2016 . Chameleon: Versatile and Practical Near-DRAM Acceleration Architecture for Large Memory Systems . In Proceedings of the Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO). 50:1--50:13 . Hadi Asghari Moghaddam, Young Hoon Son, Jung Ho Ahn, and Nam Sung Kim. 2016. Chameleon: Versatile and Practical Near-DRAM Acceleration Architecture for Large Memory Systems. In Proceedings of the Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO). 50:1--50:13."},{"key":"e_1_3_2_1_38_1","volume-title":"Proceedings of the International Symposium on High Performance Computer Architecture (HPCA). 457--468","author":"Nai Lifeng","year":"2017","unstructured":"Lifeng Nai , Ramyad Hadidi , Jaewoong Sim , Hyojong Kim , Pranith Kumar , and Hyesoon Kim . 2017 . GraphPIM: Enabling Instruction-Level PIM Offloading in Graph Computing Frameworks . In Proceedings of the International Symposium on High Performance Computer Architecture (HPCA). 457--468 . Lifeng Nai, Ramyad Hadidi, Jaewoong Sim, Hyojong Kim, Pranith Kumar, and Hyesoon Kim. 2017. GraphPIM: Enabling Instruction-Level PIM Offloading in Graph Computing Frameworks. In Proceedings of the International Symposium on High Performance Computer Architecture (HPCA). 457--468."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2508148.2485963"},{"key":"e_1_3_2_1_40_1","volume-title":"Proceedings of the World Wide Web Conference (WWW). 243--246","author":"Sinha Arnab","year":"2015","unstructured":"Arnab Sinha , Zhihong Shen , Yang Song , Hao Ma , Darrin Eide , Bo-June Paul Hsu , and Kuansan Wang . 2015 . An Overview of Microsoft Academic Service (MAS) and Applications . In Proceedings of the World Wide Web Conference (WWW). 243--246 . Arnab Sinha, Zhihong Shen, Yang Song, Hao Ma, Darrin Eide, Bo-June Paul Hsu, and Kuansan Wang. 2015. An Overview of Microsoft Academic Service (MAS) and Applications. In Proceedings of the World Wide Web Conference (WWW). 243--246."},{"key":"e_1_3_2_1_41_1","volume-title":"Proceedings of the ACM\/IEEE Annual International Symposium on Computer Architecture (ISCA). 237--250","author":"Sun Weiyi","year":"2021","unstructured":"Weiyi Sun , Zhaoshi Li , Shouyi Yin , Shaojun Wei , and Leibo Liu . 2021 . ABC-DIMM: Alleviating the Bottleneck of Communication in DIMM-based Near-Memory Processing with Inter-DIMM Broadcast . In Proceedings of the ACM\/IEEE Annual International Symposium on Computer Architecture (ISCA). 237--250 . Weiyi Sun, Zhaoshi Li, Shouyi Yin, Shaojun Wei, and Leibo Liu. 2021. ABC-DIMM: Alleviating the Bottleneck of Communication in DIMM-based Near-Memory Processing with Inter-DIMM Broadcast. In Proceedings of the ACM\/IEEE Annual International Symposium on Computer Architecture (ISCA). 237--250."},{"key":"e_1_3_2_1_42_1","volume-title":"Proceedings of the USENIX Symposium on Operating Systems Design and Implementation (OSDI). 495--514","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 Proceedings of the USENIX Symposium on Operating Systems Design and Implementation (OSDI). 495--514 . 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 Proceedings of the USENIX Symposium on Operating Systems Design and Implementation (OSDI). 495--514."},{"key":"e_1_3_2_1_43_1","volume-title":"Proceedings of the IEEE\/ACM International Symposium on Microarchitecture (MICRO). 641--654","author":"Tsai Po-An","year":"2018","unstructured":"Po-An Tsai , Changping Chen , and Daniel S\u00e1nchez . 2018 . Adaptive Scheduling for Systems with Asymmetric Memory Hierarchies . In Proceedings of the IEEE\/ACM International Symposium on Microarchitecture (MICRO). 641--654 . Po-An Tsai, Changping Chen, and Daniel S\u00e1nchez. 2018. Adaptive Scheduling for Systems with Asymmetric Memory Hierarchies. In Proceedings of the IEEE\/ACM International Symposium on Microarchitecture (MICRO). 641--654."},{"key":"e_1_3_2_1_44_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 ). 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)."},{"key":"e_1_3_2_1_45_1","volume-title":"Proceedings of the World Wide Web Conference (WWW). 2022--2032","author":"Wang Xiao","unstructured":"Xiao Wang , Houye Ji , Chuan Shi , Bai Wang , Yanfang Ye , Peng Cui , and Philip S. Yu . 2019. Heterogeneous Graph Attention Network . In Proceedings of the World Wide Web Conference (WWW). 2022--2032 . Xiao Wang, Houye Ji, Chuan Shi, Bai Wang, Yanfang Ye, Peng Cui, and Philip S. Yu. 2019. Heterogeneous Graph Attention Network. In Proceedings of the World Wide Web Conference (WWW). 2022--2032."},{"key":"e_1_3_2_1_46_1","volume-title":"Proceedings of the USENIX Symposium on Operating Systems Design and Implementation (OSDI). 515--531","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 Proceedings of the USENIX Symposium on Operating Systems Design and Implementation (OSDI). 515--531 . 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 Proceedings of the USENIX Symposium on Operating Systems Design and Implementation (OSDI). 515--531."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"e_1_3_2_1_48_1","volume-title":"SHGNN: Structure-Aware Heterogeneous Graph Neural Network. CoRR abs\/2112.06244","author":"Xu Wentao","year":"2021","unstructured":"Wentao Xu , Yingce Xia , Weiqing Liu , Jiang Bian , Jian Yin , and Tie-Yan Liu . 2021 . SHGNN: Structure-Aware Heterogeneous Graph Neural Network. CoRR abs\/2112.06244 (2021). Wentao Xu, Yingce Xia, Weiqing Liu, Jiang Bian, Jian Yin, and Tie-Yan Liu. 2021. SHGNN: Structure-Aware Heterogeneous Graph Neural Network. CoRR abs\/2112.06244 (2021)."},{"key":"e_1_3_2_1_49_1","volume-title":"Proceedings of the International Symposium on High Performance Computer Architecture (HPCA). 15--29","author":"Yan Mingyu","year":"2020","unstructured":"Mingyu Yan , Lei Deng , Xing Hu , Ling Liang , Yujing Feng , Xiaochun Ye , Zhimin Zhang , Dongrui Fan , and Yuan Xie . 2020 . HyGCN: A GCN Accelerator with Hybrid Architecture . In Proceedings of the International Symposium on High Performance Computer Architecture (HPCA). 15--29 . Mingyu Yan, Lei Deng, Xing Hu, Ling Liang, Yujing Feng, Xiaochun Ye, Zhimin Zhang, Dongrui Fan, and Yuan Xie. 2020. HyGCN: A GCN Accelerator with Hybrid Architecture. In Proceedings of the International Symposium on High Performance Computer Architecture (HPCA). 15--29."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2022.3198281"},{"key":"e_1_3_2_1_51_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence (AAAI). 7386--7393","author":"Yasunaga Michihiro","unstructured":"Michihiro Yasunaga , Jungo Kasai , Rui Zhang , Alexander R. Fabbri , Irene Li , Dan Friedman , and Dragomir R. Radev . 2019. ScisummNet: A Large Annotated Corpus and Content-Impact Models for Scientific Paper Summarization with Citation Networks . In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI). 7386--7393 . Michihiro Yasunaga, Jungo Kasai, Rui Zhang, Alexander R. Fabbri, Irene Li, Dan Friedman, and Dragomir R. Radev. 2019. ScisummNet: A Large Annotated Corpus and Content-Impact Models for Scientific Paper Summarization with Citation Networks. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI). 7386--7393."},{"key":"e_1_3_2_1_52_1","volume-title":"Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD). 635--644","author":"Zhao Huan","year":"2017","unstructured":"Huan Zhao , Quanming Yao , Jianda Li , Yangqiu Song , and Dik Lun Lee . 2017 . Meta-Graph Based Recommendation Fusion over Heterogeneous Information Networks . In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD). 635--644 . Huan Zhao, Quanming Yao, Jianda Li, Yangqiu Song, and Dik Lun Lee. 2017. Meta-Graph Based Recommendation Fusion over Heterogeneous Information Networks. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD). 635--644."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2022.3197510"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2015.2485222"}],"event":{"name":"ISCA '23: 50th Annual International Symposium on Computer Architecture","location":"Orlando FL USA","acronym":"ISCA '23","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture","IEEE"]},"container-title":["Proceedings of the 50th Annual International Symposium on Computer Architecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3579371.3589091","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:46:39Z","timestamp":1750178799000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3579371.3589091"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,17]]},"references-count":54,"alternative-id":["10.1145\/3579371.3589091","10.1145\/3579371"],"URL":"https:\/\/doi.org\/10.1145\/3579371.3589091","relation":{},"subject":[],"published":{"date-parts":[[2023,6,17]]},"assertion":[{"value":"2023-06-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}