{"type":"ScholarlyArticle","title":"MetaER-TTE: An Adaptive Meta-learning Model for En Route Travel Time Estimation","authors":[{"name":"Yu Fan","slug":"yu-fan","given":"Yu","family":"Fan","affiliation":"School of Computer Science and Technology , Soochow University"},{"name":"Jiajie Xu","slug":"jiajie-xu","given":"Jiajie","family":"Xu","affiliation":"School of Computer Science and Technology , Soochow University"},{"name":"Rui Zhou","slug":"rui-zhou","given":"Rui","family":"Zhou","affiliation":"Swinburne University of Technology"},{"name":"Jianxin Li","slug":"jianxin-li","given":"Jianxin","family":"Li","affiliation":"Deakin University"},{"name":"Kai Zheng","slug":"kai-zheng","given":"Kai","family":"Zheng","affiliation":"University of Electronic Science and Technology of China"},{"name":"Lu Chen","slug":"lu-chen","given":"Lu","family":"Chen","affiliation":"Swinburne University of Technology"},{"name":"Chengfei Liu","slug":"chengfei-liu","given":"Chengfei","family":"Liu","affiliation":"Swinburne University of Technology"}],"abstract":"En route travel time estimation (ER-TTE) aims to predict the travel time on the remaining route. Since the traveled and remaining parts of a trip usually have some common characteristics like driving speed, it is desirable to explore these characteristics for improved performance via effective adaptation. This yet faces the severe problem of data sparsity due to the few sampled points in a traveled partial trajectory. Since trajectories with different contextual information tend to have different characteristics, the existing meta-learning method for ER-TTE cannot fit each trajectory well because it uses the same model for all trajectories. To this end, we propose a novel adaptive meta-learning model called MetaER-TTE. Particularly, we utilize soft-clustering and derive cluster-aware initialized parameters to better transfer the shared knowledge across trajectories with similar contextual information. In addition, we adopt a distribution-aware approach for adaptive learning rate optimization, so as to avoid task-overfitting which will occur when guiding the initial parameters with a fixed learning rate for tasks under imbalanced distribution. Finally, we conduct comprehensive experiments to demonstrate the superiority of MetaER-TTE.","doi":"10.24963/ijcai.2022/281","url":"https://ijcai.org/proceedings/2022/281","pdf":"https://ijcai.org/proceedings/2022/0281.pdf","markdown":"https://ijcai.org/proceedings/2022/281.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/281","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Data Mining","track":"Main Track","number":281,"pages":{"first":2023,"last":2029},"keywords":["Data Mining: Mining Spatial and/or Temporal Data","Multidisciplinary Topics and Applications: Transportation"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986791","length_sec":81,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984934","length_sec":337,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Andrychowicz et al., 2016] Marcin Andrychowicz, Misha Denil, Sergio Gomez, Matthew W Hoffman, David Pfau, Tom Schaul, Brendan Shillingford, and Nando De Freitas. Learning to learn by gradient descent by gradient descent. In NIPS, pages 3981-3989, 2016.","title":"Learning to learn by gradient descent by gradient descent","authors":"Marcin Andrychowicz, Misha Denil, Sergio Gomez, Matthew W Hoffman, David Pfau, Tom Schaul, Brendan Shillingford, Nando De Freitas","year":"2016","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Fang et al., 2020] Xiaomin Fang, Jizhou Huang, Fan Wang, Lingke Zeng, Haijin Liang, and Haifeng Wang. Const- gat: Contextual spatial-temporal graph attention network for travel time estimation at baidu maps. In KDD, pages 2697-2705, 2020.","title":"Constgat: Contextual spatial-temporal graph attention network for travel time estimation at baidu maps","authors":"Xiaomin Fang, Jizhou Huang, Fan Wang, Lingke Zeng, Haijin Liang, Haifeng Wang","year":"2020","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Fang et al., 2021] Xiaomin Fang, Jizhou Huang, Fan Wang, Lihang Liu, Yibo Sun, and Haifeng Wang. SSML: self- supervised meta-learner for en route travel time estimation at baidu maps. In KDD, pages 2840-2848, 2021.","title":"SSML: selfsupervised meta-learner for en route travel time estimation at baidu maps","authors":"Xiaomin Fang, Jizhou Huang, Fan Wang, Lihang Liu, Yibo Sun, Haifeng Wang","year":"2021","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Finn et al., 2017] Chelsea Finn, Pieter Abbeel, and Sergey Levine. Model-agnostic meta-learning for fast adaptation of deep networks. In ICML, volume 70, pages 1126-1135, 2017.","title":"Model-agnostic meta-learning for fast adaptation of deep networks","authors":"Finn","year":"2017","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Fu et al., 2020] Kun Fu, Fanlin Meng, Jieping Ye, and Zheng Wang. Compacteta: A fast inference system for travel time prediction. In KDD, pages 3337-3345, 2020.","title":"Compacteta: A fast inference system for travel time prediction","authors":"Kun Fu, Fanlin Meng, Jieping Ye, Zheng Wang","year":"2020","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Graves et al., 2014] Alex Graves, Greg Wayne, and Ivo Danihelka. Neural turing machines. CoRR, 2014.","title":"Neural turing machines","authors":"Alex Graves, Greg Wayne, Ivo Danihelka","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Hospedales et al., 2020] Timothy Hospedales, Antreas An- toniou, Paul Micaelli, and Amos Storkey. Meta-learning in neural networks: A survey. arXiv preprint arX- iv:2004.05439, 2020.","title":"Meta-learning in neural networks: A survey","authors":"Hospedales","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Kisialiou et al., 2018] Yauheni Kisialiou, Irina Gribkovska- ia, and Gilbert Laporte. The periodic supply vessel plan- ning problem with flexible departure times and coupled vessels. COR, 94:52-64, 2018.","title":"Yauheni Kisialiou, Irina Gribkovskaia, and Gilbert Laporte. The periodic supply vessel planning problem with flexible departure times and coupled vessels","authors":"Kisialiou","year":"2018","venue":"COR","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Madotto et al., 2019] Andrea Madotto, Zhaojiang Lin, Chien-Sheng Wu, and Pascale Fung. Personalizing dia- logue agents via meta-learning. In ACL, pages 5454-5459, 2019.","title":"Personalizing dialogue agents via meta-learning","authors":"Andrea Madotto, Zhaojiang Lin, Chien-Sheng Wu, Pascale Fung","year":"2019","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Mishra et al., 2017] Nikhil Mishra, Mostafa Rohaninejad, Xi Chen, and Pieter Abbeel. A simple neural attentive meta-learner. arXiv preprint arXiv:1707.03141, 2017.","title":"A simple neural attentive meta-learner","authors":"Nikhil Mishra, Mostafa Rohaninejad, Xi Chen, Pieter Abbeel","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Munkhdalai et al., 2018] Tsendsuren Munkhdalai, Xingdi Yuan, Soroush Mehri, and Adam Trischler. Rapid adap- tation with conditionally shifted neurons. In ICML, pages 3664-3673, 2018.","title":"Tsendsuren Munkhdalai, Xingdi Yuan, Soroush Mehri, and Adam Trischler. Rapid adaptation with conditionally shifted neurons","authors":"Munkhdalai","year":"2018","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Santoro et al., 2016] Adam Santoro, Sergey Bartunov, Matthew Botvinick, Daan Wierstra, and Timothy P. Lillicrap. Meta-learning with memory-augmented neural networks. In ICML, volume 48, pages 1842-1850, 2016.","title":"Meta-learning with memory-augmented neural networks","authors":"Adam Santoro, Sergey Bartunov, Matthew Botvinick, Daan Wierstra, Timothy P Lillicrap","year":"2016","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Snell et al., 2017] Jake Snell, Kevin Swersky, and Richard S Zemel. Prototypical networks for few-shot learning. arXiv preprint arXiv:1703.05175, 2017.","title":"Prototypical networks for few-shot learning","authors":"Jake Snell, Kevin Swersky, Richard S Zemel","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Sung et al., 2018] Flood Sung, Yongxin Yang, Li Zhang, Tao Xiang, Philip H. S. Torr, and Timothy M. Hospedales. Learning to compare: Relation network for few-shot learn- ing. In CVPR, pages 1199-1208, 2018.","title":"Learning to compare: Relation network for few-shot learning","authors":"Sung","year":"2018","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Wang et al., 2018] Dong Wang, Junbo Zhang, Wei Cao, Jian Li, and Yu Zheng. When will you arrive? estimat- ing travel time based on deep neural networks. In AAAI, pages 2500-2507, 2018.","title":"When will you arrive? estimating travel time based on deep neural networks","authors":"Wang","year":"2018","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Xu et al., 2015] Jiajie Xu, Yunjun Gao, Chengfei Liu, Lei Zhao, and Zhiming Ding. Efficient route search on hi- erarchical dynamic road networks. DPD, 33(2):227-252, 2015.","title":"Efficient route search on hierarchical dynamic road networks","authors":"Jiajie Xu, Yunjun Gao, Chengfei Liu, Lei Zhao, Zhiming Ding","year":"2015","venue":"DPD","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Xu et al., 2019] Jiajie Xu, Jing Chen, Rui Zhou, Junhua Fang, and Chengfei Liu. On workflow aware location- based service composition for personal trip planning. FGCS, 98:274-285, 2019.","title":"On workflow aware locationbased service composition for personal trip planning","authors":"Jiajie Xu, Jing Chen, Rui Zhou, Junhua Fang, Chengfei Liu","year":"2019","venue":"FGCS","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Xu et al., 2020] Saijun Xu, Jiajie Xu, Rui Zhou, Chengfei Liu, Zhixu Li, and An Liu. Tadnm: A transportation-mode aware deep neural model for travel time estimation. In DSFAA, pages 468-484, 2020.","title":"Tadnm: A transportation-mode aware deep neural model for travel time estimation","authors":"Saijun Xu, Jiajie Xu, Rui Zhou, Chengfei Liu, Zhixu Li, An Liu","year":"2020","venue":"DSFAA","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Yao et al., 2019] Huaxiu Yao, Ying Wei, Junzhou Huang, and Zhenhui Li. Hierarchically structured meta-learning. In Kamalika Chaudhuri and Ruslan Salakhutdinov, edi- tors, ICML, volume 97 of Proceedings of Machine Learn- ing Research, pages 7045-7054, 2019.","title":"Hierarchically structured meta-learning","authors":"Yao","year":"2019","venue":"Proceedings of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Ye et al., 2020] Han-Jia Ye, Xiang-Rong Sheng, and De- Chuan Zhan. Few-shot learning with adaptively initialized task optimizer: a practical meta-learning approach. ML, 109(3):643-664, 2020.","title":"Few-shot learning with adaptively initialized task optimizer: a practical meta-learning approach","authors":"Han-Jia Ye, Xiang-Rong Sheng, De-Chuan Zhan","year":"2020","venue":"ML","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Yu et al., 2021] Runsheng Yu, Yu Gong, Xu He, Yu Zhu, Qingwen Liu, Wenwu Ou, and Bo An. Personalized adap- tive meta learning for cold-start user preference prediction. In AAAI, pages 10772-10780, 2021.","title":"Personalized adaptive meta learning for cold-start user preference prediction","authors":"Runsheng Yu, Yu Gong, Xu He, Yu Zhu, Qingwen Liu, Wenwu Ou, Bo An","year":"2021","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Yuan et al., 2013] Nicholas Jing Yuan, Yu Zheng, Liuhang Zhang, and Xing Xie. T-finder: A recommender sys- tem for finding passengers and vacant taxis. TKDE, 25(10):2390-2403, 2013.","title":"T-finder: A recommender system for finding passengers and vacant taxis","authors":"Nicholas Jing Yuan, Yu Zheng, Liuhang Zhang, Xing Xie","year":"2013","venue":"TKDE","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Zhang et al., 2018] Hanyuan Zhang, Hao Wu, Weiwei Sun, and Baihua Zheng. Deeptravel: a neural network based travel time estimation model with auxiliary supervision. In IJCAI, pages 3655-3661, 2018.","title":"Deeptravel: a neural network based travel time estimation model with auxiliary supervision","authors":"Hanyuan Zhang, Hao Wu, Weiwei Sun, Baihua Zheng","year":"2018","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2018/508"}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}