Graph Mining: Discovering Context-Sensitive Impact and Influence in Complex Systems

Project introduction

Successfully tackling many urgent challenges in socio-economically critical domains (such as sustainability, public health, and biology) requires obtaining a deeper understanding of complex relationships and interactions among a diverse spectrum of entities and agents in different contexts.
While some of the relationships (e.g., co-location of energy production facilities and water delivery networks in the energy domain and scheduled flights between two cities in the study of epidemics) in these domains are explicitly known, the knowledge of these explicit relationships is often far from sufficient to enable decision making. What is required instead is an understanding of whether and (if so) in what contexts these entities impact each other.
The goal of this project is to establish the theoretical, algorithmic, and computational foundations of big data-driven Context-Sensitive Impact Discovery (CSID) in complex systems.

Publications

  1. Ian Goetting, Elisabeth Baseman, Huiping Cao: Causal Relationships amongst Sensors in the Trinity Supercomputer: work in progress. In Proceedings of the First Workshop on Machine Learning for Computing Systems. Co-located with The 27th International Symposium on High-Performance Parallel and Distributed Computing (HPDC’18).
    [PDF] [PDF file in ACM library]
  2. Chuan Hu, Huiping Cao, Qixu Gong: Sub-Gibbs Sampling: a New Strategy for Inferring LDA.
    In Proc. of Intl. Conf. on Data Mining (ICDM 2017), 907-912. (Overall acceptance rate: 19.9%).
    [PDF] [http://doi.ieeecomputersociety.org/10.1109/ICDM.2017.113. ]
    The github repository code for this paper will be published soon.
  3. Chuan Hu, Huiping Cao: Aspect-Level Influence Discovery from Graphs.
    IEEE Trans. Knowl. Data Eng. 28(7): 1635-1649 (2016).
    [PDF] [http://dx.doi.org/10.1109/TKDE.2016.2538223]
    The source code for this paper can be downloaded from this github repository.
  4. Chuan Hu and Huiping Cao: Discovering Time-evolving Influence from Dynamic Heterogeneous Graphs.
    In Proc. of IEEE International Conference on Big Data 2015, 2253-2262.
    [PDF] [http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7364014].
    The source code for this paper can be downloaded from this github repository.
  5. Chuan Hu, Huiping Cao, Chaomin Ke: Detecting Influence Relationships from Graphs.
    In Proc. of SIAM Data Mining, SDM 2014:821-829.
    This Link has the paper, source code, data sets, and technical report.
    The source code for this paper can also be downloaded from this github repository.
  6. Yangpai Liu, Huiping Cao, Yifan Hao, Peng Han, Xinda Zeng: Discovering Context-aware Influential Objects.
    In Proc. of SIAM Data Mining, SDM 2012:780-791. (Acceptance rate: 27%)
    [http://siam.omnibooksonline.com/2012datamining/data/papers/237.pdf]

People involved in this project

  • Dr. Jiannong Xu, Biology, jxu@nmsu.edu, faculty collaborator
  • Dr. David Dubois, Plant and Environmental Sciences, faculty collaborator
  • Dr. Colby Brungard, Plant and Environmental Sciences, faculty collaborator
  • Dr. Chuan Hu, Computer Science, graduate student (graduated in May 2017)
  • Dr. Dong Pei, Biolgoy, graduate student (graduated in May 2017)
  • Dr. Jinjin Jiang, Biology, graduate student (graduated in May 2017)
  • Mr. Nathan Lopez-Brody, Plant and Environmental Sciences, Master’s student (graduated in May 2017)
  • Mr. Brett Pelkey, Computer Science, undergraduate student (graduated in May 2017)
  • Mr. Josue Gutierrez, Mechanical Engineering, undergraduate student

Thanks

This work has been supported by NSF# 1633330. nfs-logo