{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T05:25:02Z","timestamp":1755926702997,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,9,13]],"date-time":"2022-09-13T00:00:00Z","timestamp":1663027200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,9,18]]},"DOI":"10.1145\/3523227.3546760","type":"proceedings-article","created":{"date-parts":[[2022,9,13]],"date-time":"2022-09-13T14:13:46Z","timestamp":1663078426000},"page":"257-267","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["TinyKG: Memory-Efficient Training Framework for Knowledge Graph Neural Recommender Systems"],"prefix":"10.1145","author":[{"given":"Huiyuan","family":"Chen","sequence":"first","affiliation":[{"name":"Visa Research, United States"}]},{"given":"Xiaoting","family":"Li","sequence":"additional","affiliation":[{"name":"Visa Research, United States"}]},{"given":"Kaixiong","family":"Zhou","sequence":"additional","affiliation":[{"name":"Rice University, United States"}]},{"given":"Xia","family":"Hu","sequence":"additional","affiliation":[{"name":"Rice University, United States"}]},{"given":"Chin-Chia Michael","family":"Yeh","sequence":"additional","affiliation":[{"name":"Visa Research, United States"}]},{"given":"Yan","family":"Zheng","sequence":"additional","affiliation":[{"name":"Visa Research, United States"}]},{"given":"Hao","family":"Yang","sequence":"additional","affiliation":[{"name":"Visa Research, United States"}]}],"member":"320","published-online":{"date-parts":[[2022,9,13]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Translating embeddings for modeling multi-relational data. Advances in neural information processing systems 26","author":"Bordes Antoine","year":"2013","unstructured":"Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, and Oksana Yakhnenko. 2013. Translating embeddings for modeling multi-relational data. Advances in neural information processing systems 26 (2013)."},{"unstructured":"Han Cai Chuang Gan Ligeng Zhu and Song Han. 2020. TinyTL: Reduce Memory Not Parameters for Efficient On-Device Learning. In Advances in Neural Information Processing Systems.","key":"e_1_3_2_1_2_1"},{"doi-asserted-by":"crossref","unstructured":"Yixin Cao Xiang Wang Xiangnan He Zikun Hu and Tat-Seng Chua. 2019. Unifying knowledge graph learning and recommendation: Towards a better understanding of user preferences. In The world wide web conference. 151\u2013161.","key":"e_1_3_2_1_3_1","DOI":"10.1145\/3308558.3313705"},{"key":"e_1_3_2_1_4_1","volume-title":"Backprop with approximate activations for memory-efficient network training. Advances in Neural Information Processing Systems 32","author":"Chakrabarti Ayan","year":"2019","unstructured":"Ayan Chakrabarti and Benjamin Moseley. 2019. Backprop with approximate activations for memory-efficient network training. Advances in Neural Information Processing Systems 32 (2019)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_5_1","DOI":"10.24963\/ijcai.2020\/477"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_6_1","DOI":"10.1145\/3460231.3474258"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_7_1","DOI":"10.1145\/3404835.3462868"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_8_1","DOI":"10.1145\/3485447.3512162"},{"key":"e_1_3_2_1_9_1","volume-title":"International Conference on Machine Learning. 1803\u20131813","author":"Chen Jianfei","year":"2021","unstructured":"Jianfei Chen, Lianmin Zheng, Zhewei Yao, Dequan Wang, Ion Stoica, Michael Mahoney, and Joseph Gonzalez. 2021. Actnn: Reducing training memory footprint via 2-bit activation compressed training. In International Conference on Machine Learning. 1803\u20131813."},{"unstructured":"Tianqi Chen Bing Xu Chiyuan Zhang and Carlos Guestrin. 2016. Training deep nets with sublinear memory cost. arXiv preprint arXiv:1604.06174(2016).","key":"e_1_3_2_1_10_1"},{"doi-asserted-by":"crossref","unstructured":"Michael\u00a0P Connolly Nicholas\u00a0J Higham and Theo Mary. 2021. Stochastic rounding and its probabilistic backward error analysis. SIAM Journal on Scientific Computing(2021) A566\u2013A585.","key":"e_1_3_2_1_11_1","DOI":"10.1137\/20M1334796"},{"key":"e_1_3_2_1_12_1","volume-title":"Binaryconnect: Training deep neural networks with binary weights during propagations. Advances in neural information processing systems","author":"Courbariaux Matthieu","year":"2015","unstructured":"Matthieu Courbariaux, Yoshua Bengio, and Jean-Pierre David. 2015. Binaryconnect: Training deep neural networks with binary weights during propagations. Advances in neural information processing systems (2015)."},{"key":"e_1_3_2_1_13_1","volume-title":"VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization. Advances in Neural Information Processing Systems","author":"Ding Mucong","year":"2021","unstructured":"Mucong Ding, Kezhi Kong, Jingling Li, Chen Zhu, John Dickerson, Furong Huang, and Tom Goldstein. 2021. VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization. Advances in Neural Information Processing Systems (2021)."},{"key":"e_1_3_2_1_14_1","volume-title":"AC-GC: Lossy Activation Compression with Guaranteed Convergence. Advances in Neural Information Processing Systems 34","author":"Evans R\u00a0David","year":"2021","unstructured":"R\u00a0David Evans and Tor Aamodt. 2021. AC-GC: Lossy Activation Compression with Guaranteed Convergence. Advances in Neural Information Processing Systems 34 (2021)."},{"volume-title":"International semantic web conference","author":"F\u00e4rber Michael","unstructured":"Michael F\u00e4rber. 2019. The microsoft academic knowledge graph: a linked data source with 8 billion triples of scholarly data. In International semantic web conference. Springer, 113\u2013129.","key":"e_1_3_2_1_15_1"},{"key":"e_1_3_2_1_16_1","volume-title":"International Conference on Machine Learning. 3294\u20133304","author":"Fey Matthias","year":"2021","unstructured":"Matthias Fey, Jan\u00a0E Lenssen, Frank Weichert, and Jure Leskovec. 2021. Gnnautoscale: Scalable and expressive graph neural networks via historical embeddings. In International Conference on Machine Learning. 3294\u20133304."},{"key":"e_1_3_2_1_17_1","volume-title":"International Conference on Machine Learning. 3304\u20133314","author":"Fu Fangcheng","year":"2020","unstructured":"Fangcheng Fu, Yuzheng Hu, Yihan He, Jiawei Jiang, Yingxia Shao, Ce Zhang, and Bin Cui. 2020. Don\u2019t waste your bits! squeeze activations and gradients for deep neural networks via tinyscript. In International Conference on Machine Learning. 3304\u20133314."},{"key":"e_1_3_2_1_18_1","volume-title":"International Conference on Learning Representations.","author":"Godwin Jonathan","year":"2022","unstructured":"Jonathan Godwin, Michael Schaarschmidt, Alexander\u00a0L Gaunt, Alvaro Sanchez-Gonzalez, Yulia Rubanova, Petar Veli\u010dkovi\u0107, James Kirkpatrick, and Peter Battaglia. 2022. Simple GNN Regularisation for 3D Molecular Property Prediction and Beyond. In International Conference on Learning Representations."},{"unstructured":"Priya Goyal Piotr Doll\u00e1r Ross Girshick Pieter Noordhuis Lukasz Wesolowski Aapo Kyrola Andrew Tulloch Yangqing Jia and Kaiming He. 2017. Accurate large minibatch sgd: Training imagenet in 1 hour. arXiv preprint arXiv:1706.02677(2017).","key":"e_1_3_2_1_19_1"},{"key":"e_1_3_2_1_20_1","volume-title":"International conference on machine learning. 1737\u20131746","author":"Gupta Suyog","year":"2015","unstructured":"Suyog Gupta, Ankur Agrawal, Kailash Gopalakrishnan, and Pritish Narayanan. 2015. Deep learning with limited numerical precision. In International conference on machine learning. 1737\u20131746."},{"key":"e_1_3_2_1_21_1","volume-title":"Trained Quantization and Huffman Coding. International Conference on Learning Representations","author":"Han Song","year":"2016","unstructured":"Song Han, Huizi Mao, and William\u00a0J Dally. 2016. Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding. International Conference on Learning Representations (2016)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_22_1","DOI":"10.1145\/3373376.3378530"},{"key":"e_1_3_2_1_23_1","volume-title":"International Conference on Learning Representations.","author":"Jin Qing","year":"2022","unstructured":"Qing Jin, Jian Ren, Richard Zhuang, Sumant Hanumante, Zhengang Li, Zhiyu Chen, Yanzhi Wang, Kaiyuan Yang, and Sergey Tulyakov. 2022. F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_24_1","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_2_1_25_1","volume-title":"The International Conference on Learning Representations.","author":"Lin Yujun","year":"2018","unstructured":"Yujun Lin, Song Han, Huizi Mao, Yu Wang, and William\u00a0J Dally. 2018. Deep Gradient Compression: Reducing the communication bandwidth for distributed training. In The International Conference on Learning Representations."},{"key":"e_1_3_2_1_26_1","volume-title":"GACT: Activation Compressed Training for Generic Network Architectures. In International Conference on Machine Learning. 14139\u201314152","author":"Liu Xiaoxuan","year":"2022","unstructured":"Xiaoxuan Liu, Lianmin Zheng, Dequan Wang, Yukuo Cen, Weize Chen, Xu Han, Jianfei Chen, Zhiyuan Liu, Jie Tang, Joey Gonzalez, 2022. GACT: Activation Compressed Training for Generic Network Architectures. In International Conference on Machine Learning. 14139\u201314152."},{"key":"e_1_3_2_1_27_1","volume-title":"International Conference on Learning Representations.","author":"Liu Zirui","year":"2021","unstructured":"Zirui Liu, Kaixiong Zhou, Fan Yang, Li Li, Rui Chen, and Xia Hu. 2021. EXACT: Scalable graph neural networks training via extreme activation compression. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_28_1","volume-title":"Proc. of ML Systems Workshop in NIPS.","author":"Meng Chen","year":"2017","unstructured":"Chen Meng, Minmin Sun, Jun Yang, Minghui Qiu, and Yang Gu. 2017. Training deeper models by GPU memory optimization on TensorFlow. In Proc. of ML Systems Workshop in NIPS."},{"key":"e_1_3_2_1_29_1","volume-title":"Mixed Precision Training. In International Conference on Learning Representations.","author":"Micikevicius Paulius","year":"2018","unstructured":"Paulius Micikevicius, Sharan Narang, Jonah Alben, Gregory Diamos, Erich Elsen, David Garcia, Boris Ginsburg, Michael Houston, Oleksii Kuchaiev, Ganesh Venkatesh, and Hao Wu. 2018. Mixed Precision Training. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_30_1","volume-title":"International Conference on Machine Learning. 4646\u20134655","author":"Mostafa Hesham","year":"2019","unstructured":"Hesham Mostafa and Xin Wang. 2019. Parameter efficient training of deep convolutional neural networks by dynamic sparse reparameterization. In International Conference on Machine Learning. 4646\u20134655."},{"key":"e_1_3_2_1_31_1","volume-title":"Mesa: A Memory-saving Training Framework for Transformers. arXiv preprint arXiv:2111.11124(2021).","author":"Pan Zizheng","year":"2021","unstructured":"Zizheng Pan, Peng Chen, Haoyu He, Jing Liu, Jianfei Cai, and Bohan Zhuang. 2021. Mesa: A Memory-saving Training Framework for Transformers. arXiv preprint arXiv:2111.11124(2021)."},{"key":"e_1_3_2_1_32_1","volume-title":"\u201cwhen to sample","author":"Ramezani Morteza","year":"2020","unstructured":"Morteza Ramezani, Weilin Cong, Mehrdad Mahdavi, Anand Sivasubramaniam, and Mahmut Kandemir. 2020. Gcn meets gpu: Decoupling \u201cwhen to sample\u201d from \u201chow to sample\u201d. Advances in Neural Information Processing Systems (2020)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_33_1","DOI":"10.1145\/3534678.3539405"},{"key":"e_1_3_2_1_34_1","volume-title":"Ivan Titov, and Max Welling.","author":"Schlichtkrull Michael","year":"2018","unstructured":"Michael Schlichtkrull, Thomas\u00a0N Kipf, Peter Bloem, Rianne van\u00a0den Berg, Ivan Titov, and Max Welling. 2018. Modeling relational data with graph convolutional networks. In European semantic web conference. Springer, 593\u2013607."},{"key":"e_1_3_2_1_35_1","volume-title":"Increase the Batch Size. In International Conference on Learning Representations.","author":"Smith L.","year":"2018","unstructured":"Samuel\u00a0L. Smith, Pieter-Jan Kindermans, and Quoc\u00a0V. Le. 2018. Don\u2019t Decay the Learning Rate, Increase the Batch Size. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_36_1","volume-title":"And the Bit Goes Down: Revisiting the Quantization of Neural Networks. In International Conference on Learning Representations.","author":"Stock Pierre","year":"2020","unstructured":"Pierre Stock, Armand Joulin, R\u00e9mi Gribonval, Benjamin Graham, and Herv\u00e9 J\u00e9gou. 2020. And the Bit Goes Down: Revisiting the Quantization of Neural Networks. In International Conference on Learning Representations."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_37_1","DOI":"10.1145\/3240323.3240361"},{"key":"e_1_3_2_1_38_1","volume-title":"Degree-Quant: Quantization-Aware Training for Graph Neural Networks. In International Conference on Learning Representations.","author":"Tailor Shyam\u00a0Anil","year":"2021","unstructured":"Shyam\u00a0Anil Tailor, Javier Fernandez-Marques, and Nicholas\u00a0Donald Lane. 2021. Degree-Quant: Quantization-Aware Training for Graph Neural Networks. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_39_1","volume-title":"International Conference on Machine Learning. 9448\u20139457","author":"Teru Komal","year":"2020","unstructured":"Komal Teru, Etienne Denis, and Will Hamilton. 2020. Inductive relation prediction by subgraph reasoning. In International Conference on Machine Learning. 9448\u20139457."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_40_1","DOI":"10.1145\/3292500.3330836"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_41_1","DOI":"10.1145\/3292500.3330989"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_42_1","DOI":"10.1145\/3442381.3450133"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_43_1","DOI":"10.1145\/3534678.3539404"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_44_1","DOI":"10.1145\/3397271.3401141"},{"key":"e_1_3_2_1_45_1","volume-title":"International Conference on Learning Representations.","author":"Yang Bishan","year":"2015","unstructured":"Bishan Yang, Wen-tau Yih, Xiaodong He, Jianfeng Gao, and Li Deng. 2015. Embedding entities and relations for learning and inference in knowledge bases. In International Conference on Learning Representations."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_46_1","DOI":"10.1145\/3534678.3539068"},{"key":"e_1_3_2_1_47_1","first-page":"5812","article-title":"Graph contrastive learning with augmentations","volume":"33","author":"You Yuning","year":"2020","unstructured":"Yuning You, Tianlong Chen, Yongduo Sui, Ting Chen, Zhangyang Wang, and Yang Shen. 2020. Graph contrastive learning with augmentations. Advances in Neural Information Processing Systems 33 (2020), 5812\u20135823.","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_48_1","DOI":"10.1145\/2939672.2939673"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_49_1","DOI":"10.1145\/3397271.3401172"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_50_1","DOI":"10.1145\/3308558.3313508"}],"event":{"sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGAI ACM Special Interest Group on Artificial Intelligence","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval","SIGCHI ACM Special Interest Group on Computer-Human Interaction"],"acronym":"RecSys '22","name":"RecSys '22: Sixteenth ACM Conference on Recommender Systems","location":"Seattle WA USA"},"container-title":["Proceedings of the 16th ACM Conference on Recommender Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3523227.3546760","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3523227.3546760","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:45Z","timestamp":1750188645000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3523227.3546760"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,13]]},"references-count":50,"alternative-id":["10.1145\/3523227.3546760","10.1145\/3523227"],"URL":"https:\/\/doi.org\/10.1145\/3523227.3546760","relation":{},"subject":[],"published":{"date-parts":[[2022,9,13]]},"assertion":[{"value":"2022-09-13","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}