Multi-view Network Fusion and Analysis


  Data fusion is the key step for big data analysis. Particularly, in social media big data, users usually participate in different social media platforms. Merging data from different sources is an effective way to depict user’s behavior comprehensively. Moreover, users in a single data source are usually interconnected with each other to form a relational network. Multiple data sources depict user behavior from different views, thus forming a multi-view network. For example, the same users can appear in many social media platforms. Linkedin profiles user’s career information, Twitter and Sina Weibo provide user’s living information, and StackOverfolw provides user’s professional information. Most real-world applications can be modeled with multi-view network which include different networks based on different views. The multi-view network analysis is an effective way to solve the problem of data fusion. Meanwhile, multi-view network fusion and analysis face some challenges, such as how to merge different networks into a unified network, how to identify the same object from different networks, and how to align different networks.
  The emphasis of this workshop shall be analysis approaches and applications based on multi-view network. This workshop shall help to bring together people from these different areas and present an opportunity for researchers and practitioners to share new techniques for multi-view network fusion and analysis. Contributions that push the state of the art in all facets of multi-view network are encouraged and welcomed.


  Topics of interest include but not limited to:

1.Multi-view network fusion from big data
2.Semantic mining on Multi-view network
3.Data mining methods (e.g., clustering, classification and recommendation) for Multi-view network
4.Network Alignment
5.Anchor link prediction between different networks
6.Data mining based on Heterogeneous Information Network (e.g., knowledge graph)
7.Multi-view network analysis (e.g., Community detection and evolution of network)
8.Parallel computing for Multi-view network
9.Multi-view Network analysis based applications for profiling, social network analysis and multimedia
10.Multi-view Network Learning and Representationg
11.The key player identification and multi-network link analysis algorithms (e.g., information diffusion, PageRank and HITs)


  All submissions should be in English. All submissions must be prepared in the IEEE camera-ready format and submitted through the system same as ICDSC 2017. Only submissions in PDF format are accepted. Research paper submissions are limited to 10 pages. A paper submitted to MuNFA 2017 cannot be under review for any other conference or journal during the entire period that it is considered for MuNFA 2017, and must be substantially different from any previously published work. Submissions are reviewed in a single-blind manner.Please note that all submissions must strictly adhere to the IEEE templates as provided in

   Submission Link


  Full paper due: April 3, 2017, extended to April 10,2017
  Acceptance notification:April 20, 2017,extended to April 27, 2017
  Camera-ready copy:April 30, 2017,extended to May 12, 2017
  Conference Date: June 26, 2017



Bin WuBeijing University of Posts and Telecommunications, China
Chuan ShiBeijing University of Posts and Telecommunications, China
Xiaoli Li Institute for Infocomm Research , A*STAR, Singapore


Jiuming Huang National University of Defense Technology, China
Fuzheng Zhuang, Institute of Computing Technology, Chinese Academy of Sciences, China
Xi ZhangBeijing University of Posts and Telecommunications, China
Hongxin HuClemson University, USA
Shenghua LiuInstitute of Computing Technology, Chinese Academy of Sciences, China
Zhaohui PengShandong University, China
Ning YangSichuan University, China
Senzhang WangBeihang University, China
Xin LiBeijing Institute of Technology, China