Personal Update:
I am currently involved in the Mens, Manus, and Machina (M3S) project on Artificial Intelligence (AI) led by Prof. Jinhua Zhao at MIT. M3S applies AI and machine learning practically, addressing technology design, human skill development, and societal adaptation to AI, automation, and robotics, with the goal of creating inclusive and resilient solutions with global impact.
About Me
I am Xinyu Chen (陈新宇), now a Postdoctoral Associate at MIT (or visit MIT sites), leading the spatiotemporal data modeling project on GitHub. I am currently working on developing some theoretical machine learning methods (e.g., matrix/tensor decomposition) for modeling a wide range of spatiotemporal data. These data are by nature multidimensional tensors collected from real-world systems, including human mobility, trajectory data, traffic flow, fluid flow, climate/weather data, and energy consumption data. The specific scientific problems are 1) estimating and forecasting missing values of spatiotemporal data in real-world scenarios, 2) discovering dynamic patterns from spatiotemporal data (e.g., human mobility and climate data), and 3) generating high-resolution output from the low-resolution input data according to the spatiotemporal domain knowledge (e.g., speed field reconstruction and high-resolution climate variables generation). My Ph.D. thesis is entitled as "Matrix and Tensor Models for Spatiotemporal Traffic Data Imputation and Forecasting".
I like mathematics and computer science related stuff. My research interests include, but are not limited to, machine learning, spatiotemporal data modeling, intelligent transportation systems, urban science, and AI for science. My research philosophy comes from an ancient Chinese philosopher and writer Laozi, who stated "大道至简" (make it as simple and clear as possible). I am a strong advocate of open-source and reproducible research. To contribute more ideas to the research community, I am trying to make the datasets and Python codes of our research publicly available on GitHub. I am now leading some innovative open-source projects on GitHub (with 600+ followers), and they have accumulated more than 4.5k stars. Two most popular GitHub repositories are transdim (providing machine learning algorithms for transportation data imputation and prediction, 1.2k+ stars) and aswesome-latex-drawing (providing academic drawing examples in LaTeX, 1.3k+ stars).
Fortunately, I have received several awards during my PhD study, including IVADO PhD Excellence Scholarship ($100k by Institute for Data Valorisation (IVADO)) and CIRRELT PhD Excellence Scholarship ($5k by Interuniversity Research Centre on Enterprise Networks, Logistics and Transportation (CIRRELT)). I would like to thank IVADO and CIRRELT for funding my Ph.D. research.
Selected News
(For the full list of news please check the News tab.)
-
August 2024: Our paper "Forecasting urban traffic states with sparse data using Hankel temporal matrix factorization" (authors: Xinyu Chen, Xi-Le Zhao, Chun Cheng) was accepted to INFORMS Journal on Computing.
-
June 2024: Our paper "Laplacian convolutional representation for traffic time series imputation" (authors: Xinyu Chen, Zhanhong Cheng, HanQin Cai, Nicolas Saunier, Lijun Sun) was accepted to IEEE Transactions on Knowledge and Data Engineering.
-
December 2023: I successfully passed my PhD research defense. It would be my great pleasure to have Prof. Francesco Ciari, Prof. Nicolas Saunier, Prof. Lijun Sun, Prof. James Goulet, and Prof. Guillaume Rabusseau as the jury members. If you are interested in my PhD research, welcome to take a look at the slides. Special thanks to my supervisor Prof. Nicolas Saunier for the great suggestion when I was organizing all materials.
-
July 2023: Our paper "Discovering dynamic patterns from spatiotemporal data with time-varying low-rank autoregression" (authors: Xinyu Chen, Chengyuan Zhang, Xiaoxu Chen, Nicolas Saunier, Lijun Sun) was accepted to IEEE Transactions on Knowledge and Data Engineering.
-
December 2021: I am delighted to be awarded the CIRRELT PhD Excellence Scholarship. For more details on Interuniversity Research Centre on Enterprise Networks, Logistics and Transportation (CIRRELT) and its mission, please check out the website.
-
March 2021: Our paper "Bayesian temporal factorization for multidimensional time series prediction" (authors: Xinyu Chen, Lijun Sun) was accepted to IEEE Transactions on Pattern Analysis and Machine Intelligence.
-
April 2020: I am delighted to be awarded the IVADO PhD Excellence Scholarship. The awarded research topic is "City-Scale Traffic Data Imputation and Forecasting with Tensor Learning". For more details on Institute for Data Valorisation (IVADO) and its mission, please check out the website.
Archive
vistors & views since September 2021
