{"type":"ScholarlyArticle","title":"Location Prediction over Sparse User Mobility Traces Using RNNs: Flashback in Hidden States!","authors":[{"name":"Dingqi Yang","slug":"dingqi-yang","given":"Dingqi","family":"Yang","affiliation":"University of Fribourg , Switzerland; University of Macau , SAR China"},{"name":"Benjamin Fankhauser","slug":"benjamin-fankhauser","given":"Benjamin","family":"Fankhauser","affiliation":"University of Bern , Switzerland"},{"name":"Paolo Rosso","slug":"paolo-rosso","given":"Paolo","family":"Rosso","affiliation":"University of Fribourg , Switzerland"},{"name":"Philippe Cudre-Mauroux","slug":"philippe-cudre-mauroux","given":"Philippe","family":"Cudre-Mauroux","affiliation":"University of Fribourg , Switzerland"}],"abstract":"Location prediction is a key problem in human mobility modeling, which predicts a user's next location based on historical user mobility traces. As a sequential prediction problem by nature, it has been recently studied using Recurrent Neural Networks (RNNs). Due to the sparsity of user mobility traces, existing techniques strive to improve RNNs by considering spatiotemporal contexts. The most adopted scheme is to incorporate spatiotemporal factors into the recurrent hidden state passing process of RNNs using context-parameterized transition matrices or gates. However, such a scheme oversimplifies the temporal periodicity and spatial regularity of user mobility, and thus cannot fully benefit from rich historical spatiotemporal contexts encoded in user mobility traces. Against this background, we propose Flashback, a general RNN architecture designed for modeling sparse user mobility traces by doing flashbacks on hidden states in RNNs. Specifically, Flashback explicitly uses spatiotemporal contexts to search past hidden states with high predictive power (i.e., historical hidden states sharing similar contexts as the current one) for location prediction, which can then directly benefit from rich spatiotemporal contexts. Our extensive evaluation compares Flashback against a sizable collection of state-of-the-art techniques on two real-world LBSN datasets. Results show that Flashback consistently and significantly outperforms state-of-the-art RNNs involving spatiotemporal factors by 15.9% to 27.6% in the next location prediction task.","doi":"10.24963/ijcai.2020/302","url":"https://ijcai.org/proceedings/2020/302","pdf":"https://ijcai.org/proceedings/2020/0302.pdf","markdown":"https://ijcai.org/proceedings/2020/302.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/302","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Machine Learning","track":"Main track","number":302,"pages":{"first":2184,"last":2190},"keywords":["Machine Learning: Deep Learning: Sequence Modeling","Data Mining: Mining Spatial, Temporal Data"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/24019/file_24019.m3u8","length_sec":285,"provider":"hls"}],"references":[{"position":1,"raw":"[Cheng et al., 2013] Chen Cheng, Haiqin Yang, Michael R Lyu, and Irwin King. Where you like to go next: Succes- sive point-of-interest recommendation. In IJCAI, 2013.","title":"Where you like to go next: Successive point-of-interest recommendation","authors":"Chen Cheng, Haiqin Yang, Irwin Michael R Lyu, King","year":"2013","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2013/384"},{"position":2,"raw":"[Cho et al., 2014] Kyunghyun Cho, Bart Van Merriënboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. Learning phrase representations using rnn encoder-decoder for statistical machine translation. arXiv:1406.1078, 2014.","title":"Learning phrase representations using rnn encoder-decoder for statistical machine translation","authors":"Cho","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Feng et al., 2015] Shanshan Feng, Xutao Li, Yifeng Zeng, Gao Cong, Yeow Meng Chee, and Quan Yuan. Person- alized ranking metric embedding for next new poi recom- mendation. In IJCAI, 2015.","title":"Personalized ranking metric embedding for next new poi recommendation","authors":"Shanshan Feng, Xutao Li, Yifeng Zeng, Gao Cong, Yeow Meng Chee, Quan Yuan","year":"2015","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2015/293"},{"position":4,"raw":"[Feng et al., 2018] Jie Feng, Yong Li, Chao Zhang, Funing Sun, Fanchao Meng, Ang Guo, and Depeng Jin. Deep- move: Predicting human mobility with attentional recur- rent networks. In WWW, pages 1459-1468, 2018.","title":"Deepmove: Predicting human mobility with attentional recurrent networks","authors":"Jie Feng, Yong Li, Chao Zhang, Funing Sun, Fanchao Meng, Ang Guo, Depeng Jin","year":"2018","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Figueiredo et al., 2016] Flavio Figueiredo, Bruno Ribeiro, Jussara M Almeida, and Christos Faloutsos. Tribeflow: Mining & predicting user trajectories. In WWW, pages 695-706, 2016.","title":"Tribeflow: Mining & predicting user trajectories","authors":"Flavio Figueiredo, Bruno Ribeiro, Jussara M Almeida, Christos Faloutsos","year":"2016","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Gao et al., 2012] Huiji Gao, Jiliang Tang, and Huan Liu. Exploring social-historical ties on location-based social networks. In ICWSM, 2012.","title":"Exploring social-historical ties on location-based social networks","authors":"Gao","year":"2012","venue":"ICWSM","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Gonzalez et al., 2008] Marta C Gonzalez, Cesar A Hidalgo, and Albert-Laszlo Barabasi. Understanding individual hu- man mobility patterns. Nature, 453(7196):779, 2008.","title":"Understanding individual human mobility patterns","authors":"Marta C Gonzalez, Cesar A Hidalgo, Albert-Laszlo Barabasi","year":"2008","venue":"Nature","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hidasi et al., 2016] Balázs Hidasi, Alexandros Karat- zoglou, Linas Baltrunas, and Domonkos Tikk. Session- based recommendations with recurrent neural networks. In ICLR, 2016.","title":"Sessionbased recommendations with recurrent neural networks","authors":"Balázs Hidasi, Alexandros Karatzoglou, Linas Baltrunas, Domonkos Tikk","year":"2016","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Hochreiter and Schmidhuber, 1997] Sepp Hochreiter and Jürgen Schmidhuber. Long short-term memory. Neural computation, 9(8):1735-1780, 1997.","title":"Long short-term memory","authors":"Schmidhuber Hochreiter, Sepp Hochreiter, Jürgen Schmidhuber","year":"1997","venue":"Neural computation","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Hu et al., 2008] Yifan Hu, Yehuda Koren, and Chris Volin- sky. Collaborative filtering for implicit feedback datasets. In ICDM, pages 263-272. Ieee, 2008.","title":"Collaborative filtering for implicit feedback datasets","authors":"Yifan Hu, Yehuda Koren, Chris Volinsky","year":"2008","venue":"ICDM","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Kong and Wu, 2018] Dejiang Kong and Fei Wu. Hst-lstm: A hierarchical spatial-temporal long-short term memory network for location prediction. In IJCAI, pages 2341- 2347, 2018.","title":"Hst-lstm: A hierarchical spatial-temporal long-short term memory network for location prediction","authors":"Wu ; ] Dejiang Kong, Fei Kong, Wu","year":"2018","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2018/324"},{"position":12,"raw":"[Kurashima et al., 2013] Takeshi Kurashima, Tomoharu Iwata, Takahide Hoshide, Noriko Takaya, and Ko Fu- jimura. Geo topic model: joint modeling of user's activity area and interests for location recommendation. In WSDM, pages 375-384. ACM, 2013.","title":"Geo topic model: joint modeling of user's activity area and interests for location recommendation","authors":"Takeshi Kurashima, Tomoharu Iwata, Takahide Hoshide, Noriko Takaya, Ko Fujimura","year":"2013","venue":"WSDM","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Liu et al., 2016] Qiang Liu, Shu Wu, Liang Wang, and Tie- niu Tan. Predicting the next location: A recurrent model with spatial and temporal contexts. In AAAI, 2016.","title":"Predicting the next location: A recurrent model with spatial and temporal contexts","authors":"Qiang Liu, Shu Wu, Liang Wang, Tieniu Tan","year":"2016","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Mathew et al., 2012] Wesley Mathew, Ruben Raposo, and Bruno Martins. Predicting future locations with hidden markov models. In UbiComp, pages 911-918. ACM, 2012.","title":"Predicting future locations with hidden markov models","authors":"Mathew","year":"2012","venue":"UbiComp","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Mikolov et al., 2010] Tomáš Mikolov, Martin Karafiát, Lukáš Burget, Jan Černockỳ, and Sanjeev Khudanpur. Re- current neural network based language model. In INTER- SPEECH, 2010.","title":"Recurrent neural network based language model","authors":"Mikolov","year":"2010","venue":"INTER-SPEECH","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Neil et al., 2016] Daniel Neil, Michael Pfeiffer, and Shih- Chii Liu. Phased lstm: Accelerating recurrent network training for long or event-based sequences. In NIPS, pages 3882-3890, 2016.","title":"Phased lstm: Accelerating recurrent network training for long or event-based sequences","authors":"Daniel Neil, Michael Pfeiffer, Shih-Chii Liu","year":"2016","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Noulas et al., 2012] Anastasios Noulas, Salvatore Scellato, Neal Lathia, and Cecilia Mascolo. Mining user mobil- ity features for next place prediction in location-based ser- vices. In ICDM, pages 1038-1043. IEEE, 2012.","title":"Mining user mobility features for next place prediction in location-based services","authors":"Anastasios Noulas, Salvatore Scellato, Neal Lathia, Cecilia Mascolo","year":"2012","venue":"ICDM","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Rendle et al., 2009] Steffen Rendle, Christoph Freuden- thaler, Zeno Gantner, and Lars Schmidt-Thieme. Bpr: Bayesian personalized ranking from implicit feedback. In UAI, pages 452-461. AUAI Press, 2009.","title":"Bpr: Bayesian personalized ranking from implicit feedback","authors":"Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, Lars Schmidt-Thieme","year":"2009","venue":"UAI","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Rendle et al., 2010] Steffen Rendle, Christoph Freuden- thaler, and Lars Schmidt-Thieme. Factorizing personal- ized markov chains for next-basket recommendation. In WWW, pages 811-820. ACM, 2010.","title":"Factorizing personalized markov chains for next-basket recommendation","authors":"Steffen Rendle, Christoph Freudenthaler, Lars Schmidt-Thieme","year":"2010","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Xie et al., 2016] Min Xie, Hongzhi Yin, Hao Wang, Fan- jiang Xu, Weitong Chen, and Sen Wang. Learning graph- based poi embedding for location-based recommendation. In CIKM, pages 15-24. ACM, 2016.","title":"Learning graphbased poi embedding for location-based recommendation","authors":"Xie","year":"2016","venue":"CIKM","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Yang et al., 2013a] Dingqi Yang, Daqing Zhang, Zhiyong Yu, and Zhu Wang. A sentiment-enhanced personalized location recommendation system. In HT, 2013.","title":"A sentiment-enhanced personalized location recommendation system","authors":"Yang","year":"2013","venue":"HT","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Yang et al., 2013b] Dingqi Yang, Daqing Zhang, Zhiyong Yu, and Zhiwen Yu. Fine-grained preference-aware lo- cation search leveraging crowdsourced digital footprints from lbsns. In UbiComp, pages 479-488, 2013.","title":"Fine-grained preference-aware location search leveraging crowdsourced digital footprints from lbsns","authors":"Yang","year":"2013","venue":"UbiComp","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Yang et al., 2015] Dingqi Yang, Daqing Zhang, Vincent W Zheng, and Zhiyong Yu. Modeling user activity preference by leveraging user spatial temporal characteristics in lbsns. TSMC, 45(1):129-142, 2015.","title":"Modeling user activity preference by leveraging user spatial temporal characteristics in lbsns","authors":"Yang","year":"2015","venue":"TSMC","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Yang et al., 2016] Dingqi Yang, Bin Li, and Philippe Cudré- Mauroux. Poisketch: Semantic place labeling over user activity streams. In IJCAI, pages 2697-2703, 2016.","title":"Poisketch: Semantic place labeling over user activity streams","authors":"Yang","year":"2016","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2016/383"},{"position":25,"raw":"[Yang et al., 2019] Dingqi Yang, Bingqing Qu, Jie Yang, and Philippe Cudre-Mauroux. Revisiting user mobility and so- cial relationships in lbsns: a hypergraph embedding ap- proach. In WWW, pages 2147-2157. ACM, 2019.","title":"Revisiting user mobility and social relationships in lbsns: a hypergraph embedding approach","authors":"Yang","year":"2019","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Zhang et al., 2014] Yuyu Zhang, Hanjun Dai, Chang Xu, Jun Feng, Taifeng Wang, Jiang Bian, Bin Wang, and Tie- Yan Liu. Sequential click prediction for sponsored search with recurrent neural networks. In AAAI, 2014.","title":"Sequential click prediction for sponsored search with recurrent neural networks","authors":"Yuyu Zhang, Hanjun Dai, Chang Xu, Jun Feng, Taifeng Wang, Jiang Bian, Bin Wang, Tie-Yan Liu","year":"2014","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Zhao et al., 2019] Pengpeng Zhao, Haifeng Zhu, Yanchi Liu, Jiajie Xu, Zhixu Li, Fuzhen Zhuang, Victor S Sheng, and Xiaofang Zhou. Where to go next: A spatio-temporal gated network for next poi recommendation. In AAAI, vol- ume 33, pages 5877-5884, 2019.","title":"Where to go next: A spatio-temporal gated network for next poi recommendation","authors":"Pengpeng Zhao, Haifeng Zhu, Yanchi Liu, Jiajie Xu, Zhixu Li, Fuzhen Zhuang, Xiaofang Victor S Sheng, Zhou","year":"2019","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Zhu et al., 2017] Yu Zhu, Hao Li, Yikang Liao, Beidou Wang, Ziyu Guan, Haifeng Liu, and Deng Cai. What to do next: Modeling user behaviors by time-lstm. In IJCAI, pages 3602-3608, 2017.","title":"What to do next: Modeling user behaviors by time-lstm","authors":"Yu Zhu, Hao Li, Yikang Liao, Beidou Wang, Ziyu Guan, Haifeng Liu, Deng Cai","year":"2017","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2017/504"}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}