Title of the Report: Laplacian Convolutional Representation for Traffic Time Series Imputation

Time: July 11, 2024, 10:00-11:30 AM

Venue: B309

Speaker: Dr. Xinyu Chen, Postdoctoral Fellow

Host: Assistant Professor Dongdong He

Abstract:

Spatiotemporal traffic data imputation is of great significance in intelligent transportation systems and data-driven decision-making processes. To perform efficient learning and accurate reconstruction from partially observed traffic data, we assert the importance of characterizing both global and local trends in time series. In this study, we first introduce a Laplacian kernel to temporal regularization for characterizing local trends in traffic time series, which can be formulated as a circular convolution. Then, we develop a low-rank Laplacian convolutional representation (LCR) model by putting the circulant matrix nuclear norm and the Laplacian kernelized temporal regularization together, which is proved to meet a unified framework that has a fast Fourier transform solution in log-linear time complexity. Through extensive experiments on several traffic datasets, we demonstrate the superiority of LCR over several baseline models for imputing traffic time series of various time series behaviors and reconstructing sparse speed fields of vehicular traffic flow. The proposed LCR model is also an efficient solution to large-scale traffic data imputation over the existing imputation models.

Speaker Biography:

Dr. Xinyu Chen is currently conducting postdoctoral research at the Massachusetts Institute of Technology (MIT) in the United States. He previously earned his Ph.D. from the University of Montreal in Canada. His research areas include machine learning, data science, urban science, and intelligent transportation. His research interests encompass machine learning theory and algorithms, spatiotemporal data modeling techniques, tensor computation, and data mining.

As the first author, he has published three academic papers in top-tier computer science journals, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) and IEEE Transactions on Knowledge and Data Engineering (TKDE). He has also published six academic papers in leading intelligent transportation journals, Transportation Research Part C: Emerging Technologies and IEEE Transactions on Intelligent Transportation Systems. His papers have been cited over 1100 times, with two papers recognized as ESI Hot Papers and two others as ESI Highly Cited Papers.