Modeling complex spatial and temporal correlations in the correlated time series data is indispensable for understanding the traffic dynamics and predicting the future status of an evolving traffic system. Recent works focus on designing complicated graph neural network architectures to capture shared patterns with the help of pre-defined graphs. In this paper, we argue that learning node-specific patterns is essential for traffic forecasting while pre-defined graph is avoidable. To this end, we propose two adaptive modules for enhancing Graph Convolutional Network (GCN) with new capabilities: 1) a Node Adaptive Parameter Learning (NAPL) module to capture node-specific patterns; 2) a Data Adaptive Graph Generation (DAGG) module to infer the inter-dependencies among different traffic series automatically. We further propose an Adaptive Graph Convolutional Recurrent Network (AGCRN) to capture fine-grained spatial and temporal correlations in traffic series automatically based on the two modules and recurrent networks. Our experiments on two real-world traffic datasets show AGCRN outperforms state-of-the-art by a significant margin without pre-defined graphs about spatial connections.
LEI BAI (UNSW, Sydney)
Lina Yao (University of New South Wales)
Can Li (University of New South Wales)
Xianzhi Wang (University of Technology Sydney)
Xianzhi Wang's research interests include Internet of Things, data mining, machine learning, recommender systems, and cybersecurity. His work has been published in top-tier journals and conferences such as IEEE TNNLS, IEEE MC, IEEE TSC, ACM TOIT, ICDM, KDD, AAAI, IJCAI, UbiComp, SIGIR, CIKM, ER, PAKDD, IJCNN, ICSOC, ICWS. He served as the guest editor for ACM Trans. on Sensor Networks, Journal of Big Data, and editorial board member for IJWET. He was the program co-chair for EUSPN 2018: Semantic Web Technologies Track, IEEE MS 2015: Special track on Services for the Ubiquitous Web, and DPBA 2015. He also serves as the publicity chair for IUPT 2017 and panelist for ACSW 2019: Early Career Researcher panel. He is the program committee member of over 40 conferences and the reviewer for over 60 journals and conferences including IEEE TSC, IEEE TCC, IEEE TBD, IEEE TAAS, IEEE TETCI, ACM Computing Surveys, ACM TIS, ACM TOSN, ACM TOIT, ACM TWeb, ICDM, KDD. He is the recipient of Australian Research Council Discovery Early Career Researcher Award (DECRA) (2017), IBM Ph.D. Fellowship (2013), Best Paper Award of CCF National Conference on Service Computing (2010). He was recognized as an Outstanding Reviewer by the International Journal of Human-Computer Studies in 2018.
Can Wang (Griffith University)
More from the Same Authors
2019 Poster: Quaternion Knowledge Graph Embeddings »
SHUAI ZHANG · Yi Tay · Lina Yao · Qi Liu