Haokai Lu




Howdy! I recently obtained my Ph.D. in the Computer Science & Engineering Department at Texas A&M University, advised by Prof. James Caverlee. I'm broadly interested in the area of data mining, machine learning and recommender systems. Specifically, my research focuses on developing machine learning methods and algorithms for user modeling and personalization in social media.

Previously, I was at the Computer Engineering & Systems Group and worked with Prof. Peng Li. I obtained my Bachelor's degree from Southeast University in China before coming to TAMU.

I am now working at Google as a software engineer.

Publications

  • Learning Geo-Social User Topical Profiles with Bayesian Hierarchical User Factorization. (acceptance rate: 21%) [pdf]
    The 41st International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2018.
    H. Lu, W. Niu and J. Caverlee.

  • Neural Personalized Ranking for Image Recommendation. (acceptance rate: 16%) [pdf]
    The 11th ACM International Conference on Web Search and Data Mining (WSDM), 2018.
    W. Niu, J. Caverlee and H. Lu.

  • Location-Sensitive User Profiling Using Crowdsourced Labels. (acceptance rate: 25%) [pdf]
    Thirty-Second AAAI Conference on Artificial Intelligence (AAAI), 2018.
    W. Niu, J. Caverlee and H. Lu.

  • What Are You Known For? Learning User Topical Profiles with Implicit and Explicit Footprints. (acceptance rate: 22%) [pdf]
    The 40th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2017.
    C. Cao, H. Ge, H. Lu, X. Hu and J. Caverlee.

  • Discovering What You're Known For: A Contextual Poisson Factorization Approach. (acceptance rate: 18%) [pdf]
    The 10th ACM Conference on Recommender Systems (RecSys), 2016.
    H. Lu, J. Caverlee and W. Niu.

  • TAPER: A Contextual Tensor-Based Approach for Personalized Expert Recommendation. (best paper nominee) [pdf]
    The 10th ACM Conference on Recommender Systems (RecSys), 2016.
    H. Ge, J. Caverlee and H. Lu.

  • Community-Based Geospatial Tag Estimation. (acceptance rate: 14%) [pdf]
    The IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), 2016.
    W. Niu, J. Caverlee, H. Lu and K. Kamath.

  • BiasWatch: A Lightweight System for Discovering and Tracking Topic-Sensitive Opinion Bias in Social Media. (acceptance rate: 18%) [pdf]
    The 24th ACM International on Conference on Information and Knowledge Management (CIKM), 2015.
    H. Lu, J. Caverlee and W. Niu.

  • Exploiting Geo-Spatial Preference for Personalized Expert Recommendation. (acceptance rate: 21%) [pdf]
    The 9th ACM Conference on Recommender Systems (RecSys), 2015.
    H. Lu and J. Caverlee.

  • Linking brain behavior to underlying cellular mechanisms via large-scale brain modeling and simulation. [pdf]
    Neurocomputing, 2012.
    Y. Zhang, B. Yan, M. Wang, J. Hu, H. Lu and P. Li.

  • Stochastic projective methods for simulating stiff chemical reacting systems. [pdf]
    Computer Physics Communications, 2012.
    H. Lu and P. Li.

Industry Experience

  • Software engineering intern, Adwords Express quality team, Google, Mountain View, USA, May 2016 - Aug 2016.
    Area: deep learning, multi-class classification
    Project: exploring deep neural networks for Adwords Express keyword prediction.

Teaching

Technical Talks

  • Learning Geo-Social User Topical Profiles with Bayesian Hierarchical User Factorization. SIGIR, Ann Arbor, 2018.
  • Discovering What You're Known For: A Contextual Poisson Factorization Approach. RecSys, Boston, 2016.
  • BiasWatch: A Lightweight System for Discovering and Tracking Topic-Sensitive Opinion Bias in Social Media. CIKM, Melbourne, 2015.
  • Exploiting Geo-Spatial Preference for Personalized Expert Recommendation. RecSys, Vienna, 2015.

Professional Services

  • Journal Reviewer: Transactions on Knowledge and Data Engineering, IEEE Transactions on Services Computing, Information Retrieval Journal
  • Conference Reviewer: ASONAM'16
  • External Reviewer: WWW'(16, 15), WSDM'(18, 17, 16), KDD'(16, 15), SIGIR'15, ICWSM'15, SDM'15, IJCAI'15, ICDM'14