Huawei Shen



Institute of Computing Technology

Chinese Academy of Sciences

  • Biography
  • Publications
  • Projects

I am now an associate professor in the Institute of Computing Technology, Chinese Academy of Sciences (ICT-CAS). I received my Ph.D degree from ICT-CAS in 2010, supervised by Prof. Xueqi Cheng. In 2014, I worked as a research scholar in Barabasi's CCNR lab at Northeastern University. My major research interests include complex network, social computing, and data mining. I am now leading a research group, focusing on analyzing social and information network. My recent research topic covers community detection, popularity prediction, influence maximization, user modeling, recommender system.

Selected Research
Collective credit allocation in science (PNAS, 2014)

Collaboration among researchers is an essential component of the modern scientific enterprise, playing a particularly important role in multidisciplinary research. However, we continue to wrestle with allocating credit to the coauthors of publications with multiple authors, because the relative contribution of each author is difficult to determine. At the same time, the scientific community runs an informal field-dependent credit allocation process that assigns credit in a collective fashion to each work. Here we develop a credit allocation algorithm that captures the coauthors’ contribution to a publication as perceived by the scientific community, reproducing the informal collective credit allocation of science. We validate the method by identifying the authors of Nobel-winning papers that are credited for the discovery, independent of their positions in the author list. The method can also compare the relative impact of researchers working in the same field, even if they did not publish together. The ability to accurately measure the relative credit of researchers could affect many aspects of credit allocation in science, potentially impacting hiring, funding, and promotion decisions.

Modeling and Predicting Popularity Dynamics via Reinforced Poisson Processes (AAAI, 2014)

An ability to predict the popularity dynamics of individual items within a complex evolving system has important implications in an array of areas. Here we propose a generative probabilistic framework using a reinforced Poisson process to explicitly model the process through which individual items gain their popularity. This model distinguishes itself from existing models via its capability of modeling the arrival process of popularity and its remarkable power at predicting the popularity of individual items. It possesses the flexibility of applying Bayesian treatment to further improve the predictive power using a conjugate prior. Extensive experiments on a longitudinal citation dataset demonstrate that this model consistently outperforms existing popularity prediction methods.

StaticGreedy: Solving the Scalability-Accuracy Dilemma in Influence Maximization (CIKM, 2013)

Influence maximization, defined as a problem of finding a set of seed nodes to trigger a maximized spread of influence, is crucial to viral marketing on social networks. For practical viral marketing on large scale social networks, it is required that influence maximization algorithms should have both guaranteed accuracy and high scalability. However, existing algorithms suffer a scalability-accuracy dilemma: conventional greedy algorithms guarantee the accuracy with expensive computation, while the scalable heuristic algorithms suffer from unstable accuracy. In this paper, we focus on solving this scalability-accuracy dilemma. We point out that the essential reason of the dilemma is the surprising fact that the submodularity, a key requirement of the objective function for a greedy algorithm to approximate the optimum, is not guaranteed in all conventional greedy algorithms in the literature of influence maximization. Therefore a greedy algorithm has to afford a huge number of Monte Carlo simulations to reduce the pain caused by unguaranteed submodularity. Motivated by this critical finding, we propose a static greedy algorithm, named StaticGreedy, to strictly guarantee the submodularity of influence spread function during the seed selection process. The proposed algorithm makes the computational expense dramatically reduced by two orders of magnitude without loss of accuracy. Moreover, we propose a dynamical update strategy which can speed up the StaticGreedy algorithm by 2-7 times on large scale social networks.

Exploring the structural regularities in networks (Physical Review E, 2011)

In this paper, we consider the problem of exploring structural regularities of networks by dividing the nodes of a network into groups such that the members of each group have similar patterns of connections to other groups. Specifically, we propose a general statistical model to describe network structure. In this model, a group is viewed as a hidden or unobserved quantity and it is learned by fitting the observed network data using the expectation-maximization algorithm. Compared with existing models, the most prominent strength of our model is the high flexibility. This strength enables it to possess the advantages of existing models and to overcome their shortcomings in a unified way. As a result, not only can broad types of structure be detected without prior knowledge of the type of intrinsic regularities existing in the target network, but also the type of identified structure can be directly learned from the network. Moreover, by differentiating outgoing edges from incoming edges, our model can detect several types of structural regularities beyond competing models. Tests on a number of real world and artificial networks demonstrate that our model outperforms the state-of-the-art model in shedding light on the structural regularities of networks, including the overlapping community structure, multipartite structure, and several other types of structure, which are beyond the capability of existing models.

Detect overlapping and hierarchical community structure in networks (Physica A, 2009)

Clustering and community structure is crucial for many network systems and the related dynamic processes. It has been shown that communities are usually overlapping and hierarchical. However, previous methods investigate these two properties of community structure separately. This paper proposes an algorithm (EAGLE) to detect both the overlapping and hierarchical properties of complex community structure together. This algorithm deals with the set of maximal cliques and adopts an agglomerative framework. The quality function of modularity is extended to evaluate the goodness of a cover. The examples of application to real world networks give excellent results.

Hornors and Awards
  • Outstanding Fellows of CAS Youth Innovation Promotion Association, (2015)
  • First Prize of Qian Weichang Chinese Information Processing Science and Technology Award (2014)
  • First Prize for the Chinese Society of Electronic Information Science and Technology Awards (2011)
  • CAS-ICT One-Hundred Research Stars Award (2011)
  • CAS-ICT Excellent Employee Award (2010, 2014)
  • Nominated as a candidate of CCF Oustanding Dissertaion (2011).
  • Special Prize of President Scholarship for Postgraduate Students (2010)
Academic Services
  • PC Co-Chair
    SMP 2017
    CSoNet 2015
  • Area Co-Chair
    NLPCC 2014
  • Workshop Co-Chair
    CIKM 2016
  • Senior PC
    SocInfo 2015
  • PC Member
    SIGIR 2017, IJCAI 2017, CIKM 2017, ICWSM 2017, WSDM 2017, ASONAM 2017, CIKM 2016, ICWSM 2016, ASONAM 2016, AIRS 2016, CompleNet 2016, CCF Big Data 2016, DSC 2016, MoI 2016, SocialSec 2016, SMP 2016, WSDM 2015, ASONAM 2015, NLPCC 2015, SMP 2015, WSDM 2014, WSDM 2013, IJCAI 2013, CSCW 2013, SCA 2012
  • Referee
    ACM TKDD, IEEE TKDE, IEEE TIST, Physical Review E, Phyisca A, Journal of Statistical Mechanics, Neurocomputing, Journal of Computer Science and Technology, Chinese Journal of Computer, Modern Physics Letters B, Journal of Statistical Physics
  • Artificial Intelligence, Web Data Mining
Journal papers
Conference papers
Chinese Publications
  • Junming Huang, Huawei Shen, Xueqi Cheng. Understanding information propagations via influence backbone analysis on social networks. Journal of Chinese Information Processing, 30(2): 74-82, 2016.
  • Chao Li, Tao Zhou, Junming Huang, Xueqi Cheng, Huawei Shen. Transfer with shared users: a cross-platform recommender system with transferred similarity. Journal of Chinese Information Processing, 30(2): 90-98, 2016.
  • Huadong Guo, Runsheng Chen, Zhiwei Xu, Jianjun Sun, Jun Bi, Lizhe Wang, Jianjun Luo, Huawei Shen, Dongxiao Gu, Dong Liang, Wenqing Shen, Xu Zhang, Hans Wolfgang Spiess, Thomas Lengauer. Big data in natural sciences, humanities and social sciences: review of the 6th exploratory round table conference. Bulletin of Chinese Academy of Sciences, 31(6): 707-716, 2016.
  • Yahui Liu, Xiaolong Jin, Huawei Shen, Xueqi Cheng. Rumor detection in social media. Communications of Chinese Association for Artificial Intelligence, 6(3): 18-22, 2016.
  • Xueqi Cheng, Bingjie Sun, Huawei Shen, Zhihua Yu. Research status and trends of diversified graph ranking. Bulletin of Chinese Academy of Sciences, 30(2): 248-256, 2015.
  • Yuanzhuo Wang, Jianye Yu, Wen Qiu, Huawei Shen, Xueqi Cheng, Chuang Lin. Evolutionary game model and analysis methods for network group behavior. Chinese Journal of Computers, 38(2):282-300, 2015.
  • Suqi Cheng, Huawei Shen, Guoqing Zhang, Xueqi Cheng. Survey of signed network research. Journal of Software, 2014,25(1):1−15.
  • Li Wang, Suqi Cheng, Huawei Shen, Xueqi Cheng. Structure inference and prediction in the co-evolution of social networks. Journal of Computer Research and Development, 50(12): 2492-2503, 2013.
  • Qiong Wu, Yue Liu, Huawei Shen, Jin Zhang, Hongbo Xu, Xueqi Cheng. A unified framework for cross-domain sentiment classification. Journal of Computer Research and Development, 50(8): 1683-1689, 2013.
  • Huawei Shen, Xueqi Cheng. Social computing in big data era. Information Technology Letter, 11(3): 15-23, 2013.
  • Huawei Shen, Xiaolong Jin, Fuxin Ren, Xueqi Cheng. Public opinion analysis in social media. Communications of the CCF, 8(4): 32-36, 2012.
  • Xueqi Cheng, Huawei Shen. Community structure of complex networks. Complex systems and complexity science, 8(1):57-70, 2011.
  • Xueqi Cheng, Huawei Shen. Community analysis in social information network. Communications of the CCF, 7(12): 12-20, 2011.
  • Huawei Shen, Xueqi Cheng, Haiqiang Chen, Yue Liu. Information bottleneck based community detection in network, Chinese Journal of Computers, 31(4):677-686, 2008.
  • You Chen, Huawei Shen, Yang Li, Xueqi Cheng. An efficient feature selection algorithm toward building lightweight intrusion detection system. Chinese Journal of Computers, 30(8):1398-1408, 2007.
Research Projects
NSFC Projects
  • Modeling and predicting popularity dynamics on online social networks (Grant No. 61472400), 2015.01-2018.12
  • Multiscale community analysis in heterogeneous networks (Grant No. 61202215), 2013.01-2015.12
  • Mining and analyzing the online social networks (Grant No. 61232010), 2013.01-2017.12
MOST Projects
  • Evoluation of social networks (Grant No. 2014AA015103), 863 Project, 2014.01-2016.12.
  • Foundational Theory of Network Data (Grant No. 2014CB340401), 863 Project, 2014.01-2018.12.
CAS Projects
  • Member of Lujiaxi International Innovation Team, 2017
  • Outstanding Member of CAS Youth Innovation Association, 2016.01-2018.12.
  • Member of CAS Youth Innovation Association, 2012.01-2015.12.