I am an assistant professor in Northeastern University. I work on machine learning for large-scale spatiotemporal data and its applications. I am generally interested in optimization, deep learning and spatiotemporal modeling. My work has been applied to learning dynamical systems, sports analytics, intelligent transportation, and climate informatics. For more details, see my curriculum vitae and research statement. For prospective students, please read this before emailing me.
Contact Info
- E-mail: roseyu [at] northeastern [dot] edu.
- phone: (617) 373-6455
- Address: 177 Huntington Ave Office 921, Boston, MA 02115
News
- Mar 2019: Consider submit to our ICML 2019 Time Series workshop!
- Feb 2019: Co-organize KITP Conference: At the Crossroad of Physics and Machine Learning!
- Jan 2019: New paper on Multiresolution Sequence Imputation !
- Jan 2019: ICRA 2019 Neural Lander: Stable Drone Landing Control using Learned Dynamics!
- Nov 2018: Our paper on Neural-Lander was highlighted by ImportAI !
- Oct 2018: New paper on Learning Tensor Latent Features !
- Sep 2018: Give a keynote talk at NCAR Climate Informatics workshop !
- August 2018: Give a talk at MIT Henry L. Pierce Laboratory Seminar Series !
- July 2018: Give talks at Japan RIKEN Center for Advanced Intelligence Project (AIP)!
- May 2018: Won best dissertation award at USC Computer Science!
- April 2018: Co-organize KITP Conference: At the Crossroad of Physics and Machine Learning!
- Feb 2018: New paper on Multi-resolution Tensor Learning!
- Jan 2018: ICLR 2018 Diffusion Convolutional RNN!
- Dec 2017: AISTATS 2018 Tensor regression meets Gaussian Processes!
- Dec 2017: Won best poster award for Long-term Forecasting using Tensor-Train RNNs at NIPS TSW!
- Nov 2017: New paper on Diffusion Convolutional RNN selected for oral at NIPS TSW!
- Nov 2017: New paper on Long-term Forecasting using Tensor-Train RNNs!
- Oct 2017: Give talks at DOLCIT seminar !
- August 2017: Starting post-doc at Caltech CMS !
- July 2017: Give talks at Peking University, DiDi Chuxing, JiaoTong University and Zhejiang University !
- June 2017: Co-organize time series workshop at ICML 2017, please submit!
- May 2017: New paper on Graph Convolutional Recurrent Neural Network for Spatiotemporal Forecasting!
- April 2017: SDM Best paper runner-up for Deep Learning for Traffic Forecasting!
- April 2017: Won ACM scholarship for Turing Award Celebration!
- March 2017: Giving a talk at Brown University!
- Feb 2017: Giving a talk at Georgia Tech!
- Dec 2016: Co-organizing NIPS workshop on Learning with Tensors: Why Now and How? (Tensor-Learn 2016)!
- Sep 2016: Invited Speaker at AI With The Best!
- August 2016: Visiting Prof. Christopher Ré 's group at Stanford!
- May 2016: Papers accepted in ICML and KDD 2016!
- April 2016: Co-organizing Women in Machine Learning Workshop (WiML 2016) in Barcelona, Spain!
Research
Deep Sequential Models for Spatiotemporal Dynamics
Expressive models for learning complex spatiotemporal dynamics
Our physical world is intrinsically spatiotemporal. We design deep learning models that bridge the expressiveness of neural networks and the rich spatiotemporal structures from the data, addressing fundamental challenges of high-dimensionality, high-order correlation, non-linear dynamics and multi-resolution dependencies.
Read More
- Long Range Sequence Generation via Multiresolution Adversarial Training Yukai Liu, Rose Yu, Stephan Zheng, Yisong Yue. [Paper]
- Neural Lander: Stable Drone Landing Control using Learned Dynamics Guanya Shi, Xichen Shi, Michael O'Connell, Rose Yu, Kamyar Azizzadenesheli, Anima Anandkumar, Yisong Yue, Soon-Jo Chung. [Paper] [Demo]
- Long-term Forecasting using Tensor-Train RNNs Rose Yu, Stephan Zheng,Anima Anandkumar, Yisong Yue. [Paper] [Code]
- Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting Yaguang Li, Rose Yu, Cyrus Shahabi,Yan Liu. International Conference on Learning Representations (ICLR), 2018 [Paper] [Code]
Deep Generative Models for Spatiotemporal Graphs
Structured learning models for spatiotemporal graphs
A graphical model can conveniently encode high-level structures. The nodes of the graph typically represent the problem components, and the edges capture their spatiotemporal interactions. We aim to study a novel deep learning framework with a primary focus on combining graphical models with black-box deep neural networks.
Read More
- A Neural Framework for Learning DAG to DAG Translation M. Clara De Paolis Kaluza, Saeed Amizadeh, Rose Yu. [Paper]
- Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting Yaguang Li, Rose Yu, Cyrus Shahabi,Yan Liu. International Conference on Learning Representations (ICLR), 2018 [Paper] [Code]
Interpretable Tensor Models for Spatiotemporal Analysis
High-order tensor models with interpretable factors for domain scientists
Providing interpretable insights for domain scientists is one of the core missions in data-driven decision making. We leverage the efficiency and simplicity of tensor factor models to uncover the hidden spatiotemporal patterns from the data.
Read More
- Learning Tensor Latent Features Sung-En Chang, Xun Zheng, Ian E.H. Yen, Pradeep Ravikumar, Rose Yu. [Paper]
- Multi-resolution Tensor Learning for Large-Scale Spatial Data Stephan Zheng, Rose Yu, Yisong Yue. [Paper]
- Tensor Regression Meets Gaussian Processes Rose Yu, Guangyu Li, Yan Liu. International Conference on Artificial Intelligence and Statistics (AISTATS), 2018 [Paper]
Preprints
Conferences