Xinran He

Xinran He

Ph.D. Candidate

Computer Science Department
Viterbi School of Engineering
University of Southern California

Office: PHE 316

About me

I am Xinran He, PhD candidate in the Computer Science Department, of University of Southern California. I am under co-advising of two professors: Prof. Yan Liu and Prof. David Kempe. I work on Machine Learning and Data Mining under supervision of Prof. Yan Liu and I work on Theoretical Computer Science with Prof. David Kempe. [CV]

Research Interest

My primary research interest lies in social network analysis and social media analysis. I am interested in both solving real-world problem in social network with machine learning and data mining techniques and provide theoretic analysis of behaviors on social network with tools such as game theory. I am particular interested in diffusion phenomena on social netowrk, including influence maximization, network inference and competitive diffusion.


Conferences & Workshops


Palash Goyal, Nitin Kamra, Xinran He and Yan Liu, DynGEM: Deep Embedding Method for Dynamic Graphs, To appear in the 3rd Representation Learning for Graphs Workshop (ReLiG 2017) with IJCAI'17.

Xinran He and Yan Liu, Not Enough Data? Joint Inferring Multiple Diffusion Networks via Network Generation Priors, WSDM'17.[PDF]


Xinran He, Ke Xu, David Kempe and Yan Liu, Learning Influence Functions from Incomplete Observations, NIPS'16.[PDF] [Full version on arXiv]

Xinran He and David Kempe, Robust Influence Maximization, KDD'16.[PDF] [Slides] [Full version on arXiv]


Xinran He, Theodoros Rekatsinas, James Foulds, Lise Getoor and Yan Liu, HawkesTopic: A Joint Model for Network Inference and Topic Modeling from Text-Based Cascades, ICML'15.[PDF] [Slides]

Xinran He*, Dehua Cheng* and Yan Liu, Model Selection for Topic Models via Spectral Decomposition, AISTATS'15. (*Two authors contribute equally to this work) [PDF]

Xiaodong Chen, Guojie Song, Xinran He and Kunqing Xie, On Influential Nodes Tracking in Dynamic Social Networks, SDM'15.


Xinran He and David Kempe, Stability of Influence Maximization, Unpublished Manuscript.[arXiv Erratum] 

Deeply indebted to Debmalya Mandal, Jean Pouget-Abadie and Yaron Singer, we realized that the main theorem in our KDD'14 paper is incorrect. In an attempt to fix the record, we post an article as an erratum on arXiv. We would like readers to only cite and use this version (which will remain an unpublished note) instead of the incorrect conference version.

Rose Yu, Xinran He and Yan Liu, GLAD: Group Anomaly Detection in Social Media Analysis, KDD'14.[PDF]

Xinran He, Junfeng Pan, Ou Jin, Tianbing Xu, Bo Liu, Tao Xu, Yanxin Shi, Antoine Atallah, Ralf Herbrich, Stuart Bowers and Joaquin Quinonero Candela, Practical Lessons from Predicting Clicks on Ads at Facebook, ADKDD'14.[PDF]


Xinran He and David Kempe, Price of Anarchy for the N-player Competitive Cascade Game with Submodular Activation Functions, WINE'13.[PDF] [Slides]


Xinran He, Guojie Song, Wei Chen, and Qingye Jiang, Influence Blocking Maximization in Social Networks under the Competitive Linear Threshold Model, SDM'12.[Conference Version] [Full Version] 



Tong Zhao, Guojie Song, and Xinran He, Inferring Diffusion Networks with Life Stage Heterogeneity, SCIENCE CHINA Information Sciences, 2017.[PDF]


Guojie Song, Yuanhao Li, Xiaodong Cheng and Xinran He, Influential Node Tracking on Dynamic Social Network: An Interchange Greedy Approach, IEEE Transactions on Knowledge and Data Engineering (TKDE), 2016.[PDF]


Rose Yu, Xinran He and Yan Liu, GLAD: Group Anomaly Detection in Social Media Analysis (journal version), ACM Transactions on Knowledge Discovery in Data (TKDD), 2015.[PDF]


Ph.D. Candidate, Computer Science Department, University of Southern California (2012 - present)

B.S. in Intelligence Science and Technology, Peking University (2008 - 2012)

    G.P.A.:3.74/4.0, Ranked 2/49

B.A. in Psychology (double major), Peking University (2009 - 2012)


Working Experience

Fulltime intern, Class-o-MATIC team, Google Mountain View (June 2016 - Aug 2016)

    Mentor: Alexander Toshev

    Area: Deep learning, computer vision, image classification

    Project: Explore attributes and regularization-based approaches to improve accuracy in few-shot image classification.

Fulltime intern, Sibyl team, Google Mountain View (June 2015 - Aug 2015)

    Mentor: Heng-Tze Cheng

    Area: Deep learning, large-scale machine learning, online advertisement

    Project: Combining neural network and sparse lnear model to improve CTR prediction.

Independent contractor, Ads ranking team, Facebook (Sep 2013 - Jan 2014)

    Mentor: Junfeng Pan

    Area: Online advertisement, data mining, machine learning

Fulltime intern, Ads ranking team, Facebook Menlo Park (June 2013 - Aug 2013)

    Mentor: Tianshi Gao, Junfeng Pan

    Area: Online advertisement, data mining, machine learning

    Project: Customize loss function for gradient boosting machine in Ads ranking.
                 Use logistic regression with stochastic gradient descent in Ads ranking.

Fulltime intern, Advertisement Relevance Team, Microsoft Search Technology Center Asia (Feb 2012 - May 2012)

    Mentor: Denvy Deng

    Area: Search advertisement, data mining

    Project: Adopt Probase, a knowledge base, to generate features for advertisement relevance ranking.