{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T21:54:39Z","timestamp":1775598879039,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,2,23]],"date-time":"2020-02-23T00:00:00Z","timestamp":1582416000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Intel Strategic Research Alliance"},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-1643351"],"award-info":[{"award-number":["CNS-1643351"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["FA8750-17-C-0086"],"award-info":[{"award-number":["FA8750-17-C-0086"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,2,23]]},"DOI":"10.1145\/3373087.3375312","type":"proceedings-article","created":{"date-parts":[[2020,2,24]],"date-time":"2020-02-24T16:44:40Z","timestamp":1582562680000},"page":"255-265","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":121,"title":["GraphACT"],"prefix":"10.1145","author":[{"given":"Hanqing","family":"Zeng","sequence":"first","affiliation":[{"name":"University of Southern California, Los Angeles, CA, USA"}]},{"given":"Viktor","family":"Prasanna","sequence":"additional","affiliation":[{"name":"University of Southern California, Los Angeles, CA, USA"}]}],"member":"320","published-online":{"date-parts":[[2020,2,24]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n. d.]. Gradient of softmax. https:\/\/deepnotes.io\/softmax-crossentropy. ([n. d.]). Accessed: 2019-09-08.  [n. d.]. Gradient of softmax. https:\/\/deepnotes.io\/softmax-crossentropy. ([n. d.]). Accessed: 2019-09-08."},{"key":"e_1_3_2_1_2_1","unstructured":"[n. d.]. NVIDIA Tesla P100 peak performance. https:\/\/images.nvidia.com\/content\/tesla\/pdf\/nvidia-tesla-p100-PCIedatasheet. pdf. ([n. d.]). Accessed: 2019--11--30.  [n. d.]. NVIDIA Tesla P100 peak performance. https:\/\/images.nvidia.com\/content\/tesla\/pdf\/nvidia-tesla-p100-PCIedatasheet. pdf. ([n. d.]). Accessed: 2019--11--30."},{"key":"e_1_3_2_1_3_1","unstructured":"[n. d.]. Xilinx Alveo U200 peak performance. https:\/\/www.xilinx.com\/products\/boards-andkits\/ alveo\/u200.html#specifications. ([n. d.]). Accessed: 2019--11--30.  [n. d.]. Xilinx Alveo U200 peak performance. https:\/\/www.xilinx.com\/products\/boards-andkits\/ alveo\/u200.html#specifications. ([n. d.]). Accessed: 2019--11--30."},{"key":"e_1_3_2_1_4_1","unstructured":"Anonymous. 2020. GraphSAINT: Graph Sampling Based Inductive Learning Method. In Submitted to International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=BJe8pkHFwS under review.  Anonymous. 2020. GraphSAINT: Graph Sampling Based Inductive Learning Method. In Submitted to International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=BJe8pkHFwS under review."},{"key":"e_1_3_2_1_5_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Chen Jie","year":"2018"},{"key":"e_1_3_2_1_6_1","unstructured":"Jianfei Chen Jun Zhu and Le Song. 2018. Stochastic Training of Graph Convolutional Networks with Variance Reduction.. In ICML. 941--949.  Jianfei Chen Jun Zhu and Le Song. 2018. Stochastic Training of Graph Convolutional Networks with Variance Reduction.. In ICML. 941--949."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2847263.2847339"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021739"},{"key":"e_1_3_2_1_9_1","first-page":"4","article-title":"Floating-point exponentiation units for reconfigurable computing","volume":"6","author":"Dinechin Florent De","year":"2013","journal-title":"ACM Transactions on Reconfigurable Technology and Systems (TRETS)"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2018.00021"},{"key":"e_1_3_2_1_11_1","unstructured":"Ian Goodfellow Yoshua Bengio and Aaron Courville. 2016. Deep Learning. MIT Press. http:\/\/www.deeplearningbook.org.  Ian Goodfellow Yoshua Bengio and Aaron Courville. 2016. Deep Learning. MIT Press. http:\/\/www.deeplearningbook.org."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939754"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289602.3293977"},{"key":"e_1_3_2_1_14_1","unstructured":"Will Hamilton Zhitao Ying and Jure Leskovec. 2017. Inductive Representation Learning on Large Graphs. In Advances in Neural Information Processing Systems 30. 1024--1034.  Will Hamilton Zhitao Ying and Jure Leskovec. 2017. Inductive Representation Learning on Large Graphs. In Advances in Neural Information Processing Systems 30. 1024--1034."},{"key":"e_1_3_2_1_15_1","unstructured":"Wenbing Huang Tong Zhang Yu Rong and Junzhou Huang. 2018. Adaptive sampling towards fast graph representation learning. In Advances in Neural Information Processing Systems. 4558--4567.  Wenbing Huang Tong Zhang Yu Rong and Junzhou Huang. 2018. Adaptive sampling towards fast graph representation learning. In Advances in Neural Information Processing Systems. 4558--4567."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3174243.3174260"},{"key":"e_1_3_2_1_17_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014"},{"key":"e_1_3_2_1_18_1","unstructured":"Thomas N. Kipf and Max Welling. 2016. Semi-Supervised Classification with Graph Convolutional Networks. CoRR abs\/1609.02907 (2016). arXiv:1609.02907 http:\/\/arxiv.org\/abs\/1609.02907  Thomas N. Kipf and Max Welling. 2016. Semi-Supervised Classification with Graph Convolutional Networks. CoRR abs\/1609.02907 (2016). arXiv:1609.02907 http:\/\/arxiv.org\/abs\/1609.02907"},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the 2017 ACM\/SIGDA Intl. Symposium on Field-Programmable Gate Arrays (FPGA '17)","author":"Yufei"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3317838"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"AM Mansour AM El-Sawy MS Aziz and AT Sayed. 2015. A new hardware implementation of base 2 logarithm for FPGA. (2015).  AM Mansour AM El-Sawy MS Aziz and AT Sayed. 2015. A new hardware implementation of base 2 logarithm for FPGA. (2015).","DOI":"10.12720\/ijsps.3.2.177-182"},{"key":"e_1_3_2_1_22_1","volume-title":"21st Annual Symposium on Foundations of Computer Science (sfcs 1980","author":"Micali S.","year":"1980"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289602.3293967"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623732"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2019.00031"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/1879141.1879192"},{"key":"e_1_3_2_1_27_1","unstructured":"David E Rumelhart Geoffrey E Hinton Ronald J Williams etal [n. d.]. Learning representations by back-propagating errors. Cognitive modeling 5 3 ([n. d.]) 1.  David E Rumelhart Geoffrey E Hinton Ronald J Williams et al. [n. d.]. Learning representations by back-propagating errors. Cognitive modeling 5 3 ([n. d.]) 1."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Shreyas Kolala Venkataramanaiah Yufei Ma Shihui Yin Eriko Nurvithadhi Aravind Dasu Yu Cao and Jae-sun Seo. 2019. Automatic Compiler Based FPGA Accelerator for CNN Training. arXiv preprint arXiv:1908.06724 (2019).  Shreyas Kolala Venkataramanaiah Yufei Ma Shihui Yin Eriko Nurvithadhi Aravind Dasu Yu Cao and Jae-sun Seo. 2019. Automatic Compiler Based FPGA Accelerator for CNN Training. arXiv preprint arXiv:1908.06724 (2019).","DOI":"10.1109\/FPL.2019.00034"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Chun Wang Shirui Pan Guodong Long Xingquan Zhu and Jing Jiang. 2017. Mgae: Marginalized graph autoencoder for graph clustering. In Proceedings of the 2017 ACM on Conference on Information and Knowledge Management. ACM 889--898. [30] Xuechao Wei Cody Hao Yu Peng Zhang Youxiang Chen Yuxin Wang Han Hu Yun Liang and Jason Cong. 2017. Automated Systolic Array Architecture Synthesis for High Throughput CNN Inference on FPGAs. In Proceedings of the 54th Annual Design Automation Conference 2017 (DAC '17). ACM New York NY USA Article 29 6 pages. https:\/\/doi.org\/10.1145\/3061639.3062207  Chun Wang Shirui Pan Guodong Long Xingquan Zhu and Jing Jiang. 2017. Mgae: Marginalized graph autoencoder for graph clustering. In Proceedings of the 2017 ACM on Conference on Information and Knowledge Management. ACM 889--898. [30] Xuechao Wei Cody Hao Yu Peng Zhang Youxiang Chen Yuxin Wang Han Hu Yun Liang and Jason Cong. 2017. Automated Systolic Array Architecture Synthesis for High Throughput CNN Inference on FPGAs. In Proceedings of the 54th Annual Design Automation Conference 2017 (DAC '17). ACM New York NY USA Article 29 6 pages. https:\/\/doi.org\/10.1145\/3061639.3062207","DOI":"10.1145\/3061639.3062207"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219890"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.5555\/3327345.3327389"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3174243.3174265"},{"key":"e_1_3_2_1_33_1","volume-title":"Efficient and Scalable Graph Embedding. In 2019 IEEE International Parallel and Distributed Processing Symposium (IPDPS). 462--471","author":"Zeng H.","year":"2019"},{"key":"e_1_3_2_1_34_1","volume-title":"Caffeine: Towards uniformed representation and acceleration for deep convolutional neural networks","author":"Zhang Chen","year":"2018"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021737"},{"key":"e_1_3_2_1_36_1","volume-title":"Frequency Improvement of Systolic Array-Based CNNs on FPGAs. In 2019 IEEE International Symposium on Circuits and Systems (ISCAS). 1--4. https:\/\/doi.org\/10","author":"Zhang J.","year":"2019"},{"key":"e_1_3_2_1_37_1","unstructured":"Muhan Zhang and Yixin Chen. 2018. Link prediction based on graph neural networks. In Advances in Neural Information Processing Systems. 5165--5175.  Muhan Zhang and Yixin Chen. 2018. Link prediction based on graph neural networks. In Advances in Neural Information Processing Systems. 5165--5175."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240765.3240801"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2016.7760779"},{"key":"e_1_3_2_1_40_1","volume-title":"High-Throughput and Energy- Efficient Graph Processing on FPGA. In 2016 IEEE 24th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM). 103-- 110","author":"Zhou S.","year":"2016"}],"event":{"name":"FPGA '20: The 2020 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays","location":"Seaside CA USA","acronym":"FPGA '20","sponsor":["SIGDA ACM Special Interest Group on Design Automation"]},"container-title":["Proceedings of the 2020 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3373087.3375312","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3373087.3375312","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3373087.3375312","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:41:26Z","timestamp":1750200086000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3373087.3375312"}},"subtitle":["Accelerating GCN Training on CPU-FPGA Heterogeneous Platforms"],"short-title":[],"issued":{"date-parts":[[2020,2,23]]},"references-count":40,"alternative-id":["10.1145\/3373087.3375312","10.1145\/3373087"],"URL":"https:\/\/doi.org\/10.1145\/3373087.3375312","relation":{},"subject":[],"published":{"date-parts":[[2020,2,23]]},"assertion":[{"value":"2020-02-24","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}