{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:22:34Z","timestamp":1750220554996,"version":"3.41.0"},"reference-count":46,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2021,8,12]],"date-time":"2021-08-12T00:00:00Z","timestamp":1628726400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"New Generation AI Major Project of Ministry of Science and Technology of China","award":["2018AAA0100601"],"award-info":[{"award-number":["2018AAA0100601"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Intell. Syst. Technol."],"published-print":{"date-parts":[[2021,8,31]]},"abstract":"<jats:p>This article is about a challenging problem called matrix sequence prediction, which is motivated from the application of taxi order prediction. Remarkably, the problem differs greatly from previous sequence prediction tasks in the sense that the time-wise correlations are quite elusive; namely, distant entries could be strongly correlated and nearby entries are unnecessarily related. Such distinct specifics make prevalent convolution-recurrence-based methods inadequate to apply. To remedy this trouble, we propose a novel architecture called Parallel Connected LSTM (PcLSTM), which integrates two new mechanisms, Multi-channel Linearized Connection (McLC) and Adaptive Parallel Unit (APU), into the framework of LSTM. Benefiting from the strengths of McLC and APU, our PcLSTM is able to handle well both the elusive correlations within each timestamp and the temporal dependencies across different timestamps, achieving state-of-the-art performance in a set of experiments demonstrated on synthetic and real-world datasets.<\/jats:p>","DOI":"10.1145\/3469437","type":"journal-article","created":{"date-parts":[[2021,8,12]],"date-time":"2021-08-12T20:52:30Z","timestamp":1628801550000},"page":"1-16","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Parallel Connected LSTM for Matrix Sequence Prediction with Elusive Correlations"],"prefix":"10.1145","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5444-8933","authenticated-orcid":false,"given":"Qi","family":"Zhao","sequence":"first","affiliation":[{"name":"Nanjing University of Information Science and Technologyt, NanJing City, JiangSu Province, China"}]},{"given":"Chuqiao","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Civil Engineering and Architecture, Zhejiang University, HangZhou City, ZheJiang Province, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9428-4387","authenticated-orcid":false,"given":"Guangcan","family":"Liu","sequence":"additional","affiliation":[{"name":"Nanjing University of Information Science and Technology, NanJing City, JiangSu Province, China"}]},{"given":"Qingshan","family":"Liu","sequence":"additional","affiliation":[{"name":"Nanjing University of Information Science and Technology, NanJing City, JiangSu Province, China"}]},{"given":"Shengyong","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Tianjin University of Technology, TianJing City, China"}]}],"member":"320","published-online":{"date-parts":[[2021,8,12]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/3026877.3026899"},{"key":"e_1_2_1_2_1","volume-title":"6th International Conference on Learning Representations (ICLR'18)","author":"Babaeizadeh Mohammad","year":"2018","unstructured":"Mohammad Babaeizadeh , Chelsea Finn , Dumitru Erhan , Roy H. Campbell , and Sergey Levine . 2018 . Stochastic variational video prediction . In 6th International Conference on Learning Representations (ICLR'18) , Conference Track Proceedings. Mohammad Babaeizadeh, Chelsea Finn, Dumitru Erhan, Roy H. Campbell, and Sergey Levine. 2018. Stochastic variational video prediction. In 6th International Conference on Learning Representations (ICLR'18), Conference Track Proceedings."},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.38"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3274895.3274896"},{"key":"e_1_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Gang Chang Yi Zhang Danya Yao and Yun Yue. [n.d.]. A Summary of Short-Term Traffic Flow Forecasting Methods. 1696\u20131707. https:\/\/doi.org\/10.1061\/41186(421)168    10.1061\/41186(421)168\nGang Chang Yi Zhang Danya Yao and Yun Yue. [n.d.]. A Summary of Short-Term Traffic Flow Forecasting Methods. 1696\u20131707. https:\/\/doi.org\/10.1061\/41186(421)168","DOI":"10.1061\/41186(421)168"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123349"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2998297"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.5555\/2319074.2321415"},{"key":"e_1_2_1_9_1","volume-title":"Stochastic video generation with a learned prior. CoRR abs\/1802.07687","author":"Denton Emily","year":"2018","unstructured":"Emily Denton and Rob Fergus . 2018. Stochastic video generation with a learned prior. CoRR abs\/1802.07687 ( 2018 ). Emily Denton and Rob Fergus. 2018. Stochastic video generation with a learned prior. CoRR abs\/1802.07687 (2018)."},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403356"},{"key":"e_1_2_1_11_1","volume-title":"The 31st Innovative Applications of Artificial Intelligence Conference (IAAI'19), The 9th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI'19)","author":"Geng Xu","year":"2019","unstructured":"Xu Geng , Yaguang Li , Leye Wang , Lingyu Zhang , Qiang Yang , Jieping Ye , and Yan Liu . 2019 . Spatiotemporal multi-graph convolution network for ride-hailing demand forecasting. In The 33d AAAI Conference on Artificial Intelligence (AAAI'19) , The 31st Innovative Applications of Artificial Intelligence Conference (IAAI'19), The 9th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI'19) . 3656\u20133663. https:\/\/doi.org\/10.1609\/aaai.v33i01.33013656 10.1609\/aaai.v33i01.33013656 Xu Geng, Yaguang Li, Leye Wang, Lingyu Zhang, Qiang Yang, Jieping Ye, and Yan Liu. 2019. Spatiotemporal multi-graph convolution network for ride-hailing demand forecasting. In The 33d AAAI Conference on Artificial Intelligence (AAAI'19), The 31st Innovative Applications of Artificial Intelligence Conference (IAAI'19), The 9th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI'19). 3656\u20133663. https:\/\/doi.org\/10.1609\/aaai.v33i01.33013656"},{"key":"#cr-split#-e_1_2_1_12_1.1","doi-asserted-by":"crossref","unstructured":"Shengnan Guo Youfang Lin Ning Feng Chao Song and Huaiyu Wan. 2019. Attention based spatial-temporal graph convolutional networks for traffic flow forecasting. In The 33rd AAAI Conference on Artificial Intelligence (AAAI'19) The 31st Innovative Applications of Artificial Intelligence Conference (IAAI'19) The 9th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI'19). 922-929. https:\/\/doi.org\/10.1609\/aaai.v33i01.3301922 10.1609\/aaai.v33i01.3301922","DOI":"10.1609\/aaai.v33i01.3301922"},{"key":"#cr-split#-e_1_2_1_12_1.2","doi-asserted-by":"crossref","unstructured":"Shengnan Guo Youfang Lin Ning Feng Chao Song and Huaiyu Wan. 2019. Attention based spatial-temporal graph convolutional networks for traffic flow forecasting. In The 33rd AAAI Conference on Artificial Intelligence (AAAI'19) The 31st Innovative Applications of Artificial Intelligence Conference (IAAI'19) The 9th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI'19). 922-929. https:\/\/doi.org\/10.1609\/aaai.v33i01.3301922","DOI":"10.1609\/aaai.v33i01.3301922"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313730"},{"volume-title":"3rd International Conference on Learning Representations (ICLR'15)","author":"Diederik","key":"e_1_2_1_15_1","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization . In 3rd International Conference on Learning Representations (ICLR'15) , Conference Track Proceedings. Diederik P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In 3rd International Conference on Learning Representations (ICLR'15), Conference Track Proceedings."},{"key":"e_1_2_1_16_1","volume-title":"Stochastic adversarial video prediction. CoRR abs\/1804.01523","author":"Lee Alex X.","year":"2018","unstructured":"Alex X. Lee , Richard Zhang , Frederik Ebert , Pieter Abbeel , Chelsea Finn , and Sergey Levine . 2018. Stochastic adversarial video prediction. CoRR abs\/1804.01523 ( 2018 ). Alex X. Lee, Richard Zhang, Frederik Ebert, Pieter Abbeel, Chelsea Finn, and Sergey Levine. 2018. Stochastic adversarial video prediction. CoRR abs\/1804.01523 (2018)."},{"key":"e_1_2_1_17_1","volume-title":"6th International Conference on Learning Representations (ICLR'18)","author":"Li Yaguang","year":"2018","unstructured":"Yaguang Li , Rose Yu , Cyrus Shahabi , and Yan Liu . 2018 . Diffusion convolutional recurrent neural network: Data-driven traffic forecasting . In 6th International Conference on Learning Representations (ICLR'18) , Conference Track Proceedings. https:\/\/openreview.net\/forum?id=SJiHXGWAZ. Yaguang Li, Rose Yu, Cyrus Shahabi, and Yan Liu. 2018. Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. In 6th International Conference on Learning Representations (ICLR'18), Conference Track Proceedings. https:\/\/openreview.net\/forum?id=SJiHXGWAZ."},{"key":"e_1_2_1_18_1","first-page":"1","article-title":"Matrix completion with deterministic sampling: Theories and methods","volume":"1","author":"Liu Guangcan","year":"2019","unstructured":"Guangcan Liu , Qingshan Liu , Xiao-Tong Yuan , and Meng Wang . 2019 . Matrix completion with deterministic sampling: Theories and methods . IEEE Transactions on Pattern Analysis and Machine Intelligence 1 , 1 (2019), 1 \u2013 18 . Guangcan Liu, Qingshan Liu, Xiao-Tong Yuan, and Meng Wang. 2019. Matrix completion with deterministic sampling: Theories and methods. IEEE Transactions on Pattern Analysis and Machine Intelligence 1, 1 (2019), 1\u201318.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_2_1_19_1","first-page":"1","article-title":"Recovery of future data via convolution nuclear norm minimization","volume":"1","author":"Liu Guangcan","year":"2020","unstructured":"Guangcan Liu and Wayne Zhang . 2020 . Recovery of future data via convolution nuclear norm minimization . Arxiv 1 , 1 (2020), 1 \u2013 16 . Guangcan Liu and Wayne Zhang. 2020. Recovery of future data via convolution nuclear norm minimization. Arxiv 1, 1 (2020), 1\u201316.","journal-title":"Arxiv"},{"key":"e_1_2_1_20_1","unstructured":"Pengfei Liu Shuaichen Chang Xuanjing Huang Jian Tang and Jackie Chi Kit Cheung. 2019. Contextualized non-local neural networks for sequence learning. In The 33rd AAAI Conference on Artificial Intelligence (AAAI'19) The 31st Innovative Applications of Artificial Intelligence Conference (IAAI'19) The 9th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI'19). 6762\u20136769.  Pengfei Liu Shuaichen Chang Xuanjing Huang Jian Tang and Jackie Chi Kit Cheung. 2019. Contextualized non-local neural networks for sequence learning. In The 33rd AAAI Conference on Artificial Intelligence (AAAI'19) The 31st Innovative Applications of Artificial Intelligence Conference (IAAI'19) The 9th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI'19). 6762\u20136769."},{"key":"e_1_2_1_21_1","volume-title":"International Conference on Learning Representations. 1\u201314","author":"Mathieu Michael","year":"2016","unstructured":"Michael Mathieu , Camille Couprie , and Yann LeCun . 2016 . Deep multi-scale video prediction beyond mean square error . In International Conference on Learning Representations. 1\u201314 . Michael Mathieu, Camille Couprie, and Yann LeCun. 2016. Deep multi-scale video prediction beyond mean square error. In International Conference on Learning Representations. 1\u201314."},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357832"},{"key":"#cr-split#-e_1_2_1_23_1.1","doi-asserted-by":"crossref","unstructured":"Z. Pan W. Zhang Y. Liang W. Zhang Y. Yu J. Zhang and Y. Zheng. 2020. Spatio-temporal meta learning for urban traffic prediction. IEEE Transactions on Knowledge and Data Engineering (2020) 1-1. https:\/\/doi.org\/10.1109\/TKDE.2020.2995855 10.1109\/TKDE.2020.2995855","DOI":"10.1109\/TKDE.2020.2995855"},{"key":"#cr-split#-e_1_2_1_23_1.2","doi-asserted-by":"crossref","unstructured":"Z. Pan W. Zhang Y. Liang W. Zhang Y. Yu J. Zhang and Y. Zheng. 2020. Spatio-temporal meta learning for urban traffic prediction. IEEE Transactions on Knowledge and Data Engineering (2020) 1-1. https:\/\/doi.org\/10.1109\/TKDE.2020.2995855","DOI":"10.1109\/TKDE.2020.2995855"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/3058878.3058894"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2009.932254"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969239.2969329"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295313"},{"key":"e_1_2_1_28_1","volume-title":"3rd International Conference on Learning Representations (ICLR'15)","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman . 2015 . Very deep convolutional networks for large-scale image recognition . In 3rd International Conference on Learning Representations (ICLR'15) , Conference Track Proceedings. Karen Simonyan and Andrew Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. In 3rd International Conference on Learning Representations (ICLR'15), Conference Track Proceedings."},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045209"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.5555\/2969442.2969505"},{"key":"e_1_2_1_31_1","unstructured":"Xiaolong Wang Ross B. Girshick Abhinav Gupta and Kaiming He. 2017. Non-local neural networks. CoRR abs\/1711.07971.  Xiaolong Wang Ross B. Girshick Abhinav Gupta and Kaiming He. 2017. Non-local neural networks. CoRR abs\/1711.07971."},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380186"},{"volume-title":"Proceedings of the 35th International Conference on Machine Learning (ICML'18)","author":"Wang Yunbo","key":"e_1_2_1_33_1","unstructured":"Yunbo Wang , Zhifeng Gao , Mingsheng Long , Jianmin Wang , and Philip S. Yu . 2018. PredRNN++: Towards a resolution of the deep-in-time dilemma in spatiotemporal predictive learning . In Proceedings of the 35th International Conference on Machine Learning (ICML'18) . 5110\u20135119. Yunbo Wang, Zhifeng Gao, Mingsheng Long, Jianmin Wang, and Philip S. Yu. 2018. PredRNN++: Towards a resolution of the deep-in-time dilemma in spatiotemporal predictive learning. In Proceedings of the 35th International Conference on Machine Learning (ICML'18). 5110\u20135119."},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.5555\/3294771.3294855"},{"volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR'19)","author":"Wang Yunbo","key":"e_1_2_1_35_1","unstructured":"Yunbo Wang , Jianjin Zhang , Hongyu Zhu , Mingsheng Long , Jianmin Wang , and Philip S. Yu . 2019. Memory in memory: A predictive neural network for learning higher-order non-stationarity from spatiotemporal dynamics . In IEEE Conference on Computer Vision and Pattern Recognition (CVPR'19) . 9154\u20139162. Yunbo Wang, Jianjin Zhang, Hongyu Zhu, Mingsheng Long, Jianmin Wang, and Philip S. Yu. 2019. Memory in memory: A predictive neural network for learning higher-order non-stationarity from spatiotemporal dynamics. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR'19). 9154\u20139162."},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)0733-947X(2003)129:6(664)"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351058"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01058"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350859"},{"key":"e_1_2_1_40_1","unstructured":"Huaxiu Yao Fei Wu Jintao Ke Xianfeng Tang Yitian Jia Siyu Lu Pinghua Gong Jieping Ye and Zhenhui Li. 2018. Deep multi-view spatial-temporal network for taxi demand prediction. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI'18) The 30th Innovative Applications of Artificial Intelligence (IAAI'18) and The 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI'18). 2588\u20132595. https:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI18\/paper\/view\/16069  Huaxiu Yao Fei Wu Jintao Ke Xianfeng Tang Yitian Jia Siyu Lu Pinghua Gong Jieping Ye and Zhenhui Li. 2018. Deep multi-view spatial-temporal network for taxi demand prediction. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI'18) The 30th Innovative Applications of Artificial Intelligence (IAAI'18) and The 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI'18). 2588\u20132595. https:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI18\/paper\/view\/16069"},{"key":"e_1_2_1_41_1","volume-title":"4th International Conference on Learning Representations (ICLR'16)","author":"Yu Fisher","year":"2016","unstructured":"Fisher Yu and Vladlen Koltun . 2016 . Multi-scale context aggregation by dilated convolutions . In 4th International Conference on Learning Representations (ICLR'16) , Conference Track Proceedings. Fisher Yu and Vladlen Koltun. 2016. Multi-scale context aggregation by dilated convolutions. In 4th International Conference on Learning Representations (ICLR'16), Conference Track Proceedings."},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0925-2312(01)00702-0"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.5555\/3298239.3298479"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2935152"}],"container-title":["ACM Transactions on Intelligent Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3469437","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3469437","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:28:23Z","timestamp":1750195703000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3469437"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,12]]},"references-count":46,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2021,8,31]]}},"alternative-id":["10.1145\/3469437"],"URL":"https:\/\/doi.org\/10.1145\/3469437","relation":{},"ISSN":["2157-6904","2157-6912"],"issn-type":[{"type":"print","value":"2157-6904"},{"type":"electronic","value":"2157-6912"}],"subject":[],"published":{"date-parts":[[2021,8,12]]},"assertion":[{"value":"2018-10-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-06-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-08-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}