I am a fifth year Ph.D. candidate of Computer Science in University of Southern California. My advisor is Prof. Yan Liu and Prof. Cyrus Shahabi . Before that, I received the B. Eng degree from Computer Science and Technology Department in Zhejiang University in 2012, under the supervision of Prof. Zhihua Zhang.

My research lies in machine learning and data analytics. I'm generally interested in learning from large-scale spatiotemporal data with applications in computational sustainability and social science. I have expertise in spatio-temporal analysis, tensor methods, and non-convex optimization. My work has been applied to climate informatics, mobile recommender system and social media anomaly detection. For more information see the links below and my CV.

Contact Info

  • E-mail: qiyu [at] usc [dot] edu.
  • Address: 328 PHE, University of Southern Cal.


Tensor Learning for Spatiotemporal Analysis

A scalable framework for analyzing spatiotemporal data

Large-scale spatiotemporal data such as climate measurements, location-based social networks have complex structures. In this project, we develop a scalable framework based on low-rank tensor learning to analyze them. We propose a series of algorithms ranging from offline, online to memory efficient learning to solve the problem. We show that our framework can produce accurate predictions in a scalable way and discover interesting patterns in spatiotemporal data.

ICML 2016 ICML 2015 NIPS 2014

Spatiotemporal Models for Traffic Prediction

A spatiotemporal approach to predict road network traffic

Given a series of road network snapshots, we propose a latent space model to capture its topological and temporal properties. We present an incremental online algorithm which sequentially and adaptively learns the spatiotemporal patterns. Our framework enables real-time traffic prediction on a large volumne of Los Angeles traffic sensor data.

SDM 2017 KDD 2016

Social Media Group Anomaly Detection

A probabilistic model to detect anomalous groups in social media

Traditional anomaly detection techniques focus on individual point anomalies. With the recent popularity of social media, new types of anomalous behaviors arise. We study the collective behavior of individuals and detect group anomalies. We take a generative approach by proposing a hierarchical Bayes model. Our approach provides a robust and interpretable way of discovering latent groups and detecting group anomalies.

KDD Exploration 2016 TKDD 2015 KDD 2014


  • Socratic Learning
    Rose Yu*, Paroma Varma*, Dan Iter, Chris De Sa, Christopher Re
    preprint arXiv:1610.08123 , 2016
    [Paper] [Blog]
  • Conferences

  • Deep Learning: A Generic Approach for Extreme Condition Traffic Forecasting
    Rose Yu*, Yaguang Li*, Ugur Demiryurek, Cyrus Shahabi, Yan Liu.
    SIAM International Conference on Data Mining (SDM), 2017
  • Learning from Multiway Data: Simple and Efficient Tensor Regression
    Rose Yu, Yan Liu.
    International Conference on Machine Learning (ICML), 2016
    [Paper] [Slide] [BibTex]
  • Latent Space Model for Road Networks to Predict Time-Varying Traffic
    Dingxiong Deng, Cyrus Shahabi, Ugur Demiryurek, Linhong Zhu, Rose Yu, Yan Liu
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2016
  • Geographic Segmentation via Latent Poisson Factor Model
    Rose Yu, Andrew Gelfand, Suju Rajan, Cyrus Shahabi, Yan Liu.
    ACM International Conference on Web Search and Data Mining (WSDM), 2016
    [Paper] [BibTex]
  • Accelerated Online Low-Rank Tensor Learning for Multivariate Spatio-Temporal Streams
    Rose Yu, Dehua Cheng, Yan Liu.
    International Conference on Machine Learning (ICML), 2015
    [Code] [Paper] [Supplementary] [Video] [Slide] [BibTex]
  • Fast Multivariate Spatio-temporal Analysis via Low Rank Tensor Learning
    Rose Yu*, Mohammad Taha Bahadori*, Yan Liu. (*Equal Contributions)
    Advances in Neural Information Processing Systems (NIPS), 2014 Spotlight
    [Code] [Paper] [Supplementary] [BibTex]
  • GLAD: Group Anomaly Detection in Social Media Analysis
    Rose Yu, Xinran He, Yan Liu.
    ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2014
    [ACM Dataset] [Slide] [Paper-Extended Version] [BibTex]
  • A Feasible Nonconvex Relaxation Approach to Feature Selection
    Cuixia Gao, Naiyan Wang, Qi Yu, Zhihua Zhang.
    AAAI Conference on Artificial Intelligence (AAAI), 2011
    [Paper] [BibTex]

  • Dark Pixel Detection: A Novel Single Image Dehaze Approach
    Qi Yu*, Zhihao Ding*, RongRong, Zhenyue Zhang, Donghui Wang.
    Image and Vision Computing New Zealand (IVCNZ), 2011
    [Paper] [BibTex]
  • Journals

  • Spatio-Temporal Analysis of Social Media Data
    Rose Yu, Yan Liu.
    Encyclopedia of GIS , 2016
  • A Survey on Social Media Anomaly Detection
    Rose Yu, Huida Qiu, Zhen Wen, Ching-Yung Lin, Yan Liu
    ACM SIGKDD Explorations , 2016
  • GLAD: Group Anomaly Detection in Social Media Analysis (journal version)
    Rose Yu, Xinran He, Yan Liu.
    ACM Transactions on Knowledge Discovery in Data (TKDD), 2015