Multi-Source Network Fusion and Analysis (MSNFA 2021)


With the popularity of social network applications, social network analysis technology has been widely used in areas, such as business intelligence and public security. Since social information can be acquired from different social platforms and applications, multi-source social data analysis has attracted much attention. Fusing social information from different sources and types is a more accurate and effective way to understand and analyses the behavior of users and groups. While focusing on different social platforms and applications, the fusion analysis of different types of data draws more and more scholars’ attention, especially the rich social relationship information in Multimodal data, such as video, text and image data. Most real-world applications can be served as multi-layer networks (multiplex networks) and heterogeneous information networks and so on, which include different networks based on different sources and types. The multi-source network analysis is an accurate and effective way to comprehensively analyses social networks. Meanwhile, multi-source information network fusion and analysis face some challenges, such as how to construct multi-source networks from text and video, how to fuse different networks without loss of information, how to learn the embedding of node or edge from different networks, and how to align different networks.
The emphasis of this workshop shall be analysis approaches and applications based on multi-source, multi-view and multi-model networks. The previous four workshops have been successfully held in Changsha(2016), Shenzhen(2017), Guangzhou(2018), Hangzhou(2019) and Hongkong(2020). 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-source networks fusion and analysis. Contributions that push the state of the art in all facets of multi-source network are encouraged and welcomed.


Topics of interest include but not limited to:

1. The Construction of Network from different types of data (e.g. Text and Video) 
2. Network Alignment
3. Multi-source network analysis (e.g., Role detection, Node influence and Evolution of network) 
4. Cross-Network Information diffusion
5. The Application of Graph Neural Networks for Multi-source networks
6. Multi-source network Embedding
7. The Community detection for Multi-source network
8. The Link Prediction for Multi-source network
9. Data mining based on Heterogeneous Information Network
10. Parallel computing for Multi-source network 
11. Multi-source network analysis based applications for profiling, social network analysis and multimedia 
12. Semantic mining on Multi-source network
13. Fusion Analysis of Knowledge Graph Oriented


All submissions should be in English. All submissions must be prepared in the IEEE camera-ready format and submitted through the system the same as ICDSC 2021. Only submissions in PDF format are accepted. Research paper submissions are limited to 10 pages. A paper submitted to MSNFA 2021 cannot be under review for any other conference or journal during the entire period that it is considered for MSNFA 2021, 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: Submit paper:


Full paper due: June 30, 2021, extend to July 15, 2021
Acceptance notification: July 30, 2021, extend to August 31, 2021
Camera-ready copy: August 15, 2021, extend to September 7, 2021
Conference Date: October 9-11, 2021



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

Program Committee

Jiuming Huang, National University of Defense Technology, China
Fuzheng Zhuang,Institute of Computing Technology, Chinese Academy of Sciences, China 
Xi Zhang, Beijing University of Posts and Telecommunications, China 
Ting Bai, Beijing University of Posts and Telecommunications, China
Hongxin Hu, Clemson University, USA
Shenghua Liu, Institute of Computing Technology, Chinese Academy of Sciences, China 
Zhaohui Peng, Shandong University, China 
Ning Yang, Sichuan University, China 
Senzhang Wang, Beihang University, China 
Xin Li, Beijing Institute of Technology, China
Yunpeng Xiao, Chongqing University of Posts and Telecommunications, China
Yunlei Zhang, North China Institute of Science and Technology, China