Wei Zeng

Wei Zeng


Zeng Wei, born in 1985, Ph.D., associate professor, master’s tutor, was awarded the title of “Outstanding Student of Chengdian University” by Electronic Science and Technology University in 2014 (the highest honor of students of University of Electronic Science and Technology of China). He has been a reviewer for IEEE Transaction on Multimedia, Engineering Applications of Artificial Intelligence (EAAI), Scientific Reports, etc., and has received the “Outstanding Contribution in Reviewing” award from EAAI Journal. He has published more than 20 academic papers, applied for 5 patents, presided over 2 Sino-Swiss science and technology cooperation projects, presided over one National Natural Youth Fund, and presided over one National Natural Science Foundation project, and jointly reported the final assembly with CLP 10 Project 1, hosted a number of horizontal projects.

Educational background

September 2011-July 2015, PhD, Computer Software and Theory, University of Electronic Science and Technology of China

September 2008-June 2011, Master of Computer Software and Theory, University of Electronic Science and Technology of China

September 2004-June 2008, Bachelor of Software Engineering, University of Electronic Science and Technology of China

Research work experience

July 2014-September 2014, University of Fribourg, Switzerland, Personalized Referral Technology, Assistant Researcher

October 2012-September 2013, University of Fribourg, Switzerland, Personalized Referral Technology, Assistant Researcher

November 2011-June 2012, Hong Kong Baptist University, Personalized Referral Technology, Assistant Researcher

Research areas

The main research directions of my research group include: personalized recommendation technology, theoretical research and application of point process and application of big data technology in the financial field.

  1. Personalized recommendation technology. Aiming at the sparseness and cold start of the recommendation system, a local random walk algorithm and a matrix decomposition algorithm based on social network are proposed respectively. For the problem that the recommendation algorithm is less efficient, the topology of the recommended network is studied, and the information core and information are proposed. The recommendation algorithm of the skeleton; for the data sparsity problem of the multi-dimensional scoring recommendation system, the recommendation algorithm based on the scoring implicit component and the recommendation algorithm based on the migration learning are respectively proposed; the application of deep learning in the recommendation system is proposed, and the hybrid neural network is proposed. The recommended algorithm for the network. Related research results are published in Expert Systems with Applications, ICDM, Scientific Reports, Knowledge and Information Systems, IEEE Transactions on Cybernetics, and the like.
  2. Theoretical research and application of the point process. The application of Poisson process, survival analysis and Hawkes process in user modeling is studied, and the influence of price factors, social factors and user preference factors on user regression time is considered. The fault diagnosis and prediction of electronic equipment based on point process is studied and applied to the avionics system of a large aircraft.
  3. The application of big data technology in the financial field. In order to solve the problem of bank risk customer identification, deep learning is used to automatically identify and diagnose risk customers, and predict customers’ default behavior in advance. In view of the difficulty in marketing of bank customers, combined with a variety of personalized recommendation techniques, and using migration learning methods, we design a personalized marketing plan for each bank customer. Relevant research results were published in such journals as Big Data.

Academic achievements

  1. Junhua Chen, Wei Zeng, Junming Shao, Ge Fan, Preference Modeling by Exploiting Latent Components of Ratings, Knowledge and Information Systems, 2018/4/26, 1-27.
  2. Wei Zeng, Meiling Fang, Junming Shao, Mingsheng Shang, Uncovering the essential links in online commercial networks, Scientific Reports , 2016/9/29, 6, 34292.
  3. Wei Zeng, An Zeng, Hao Liu, Ming-Sheng Shang, Tao Zhou, Uncovering the information core in recommender systems, Scientific Report, 2014/8/21, 4, 6140.
  4. Junming Shao, Chongming Gao, Wei Zeng, Jingkuan Song, Qinli Yang, Synchronization-Inspired Co-Clustering and Its Application to Gene Expression Data, ICDM’17, 2017/11/18, 1075-1080.
  5. Wei Zeng, An Zeng, Hao Liu, Ming-Sheng Shang, Yi-Cheng Zhang, Similarity from multi-dimensional scaling: Solving the accuracy and diversity dilemma in information filtering, PloS one, 2014/10/24, 9, e111005.
  6. Wei Zeng, An Zeng, Ming-Sheng Shang, Yi-Cheng Zhang, Information filtering in sparse online systems: recommendation via semi-local diffusion, PloS one, 2013/11/18, 11, e79354.
  7. Wei Zeng, An Zeng, Ming-Sheng Shang, Yi-Cheng Zhang, Membership in social networks and the application in information filtering, Eur. Phys. J. B, 2013/8/14, 86, 375.
  8. Li Chen, Wei Zeng, Quan Yuan, A unified framework for recommending items, groups and friends in social media environment via mutual resource fusion, Expert Systems with Applications, 2013/6/15, 8, 2889-2903.
  9. Wei Zeng, Li Chen, Heterogeneous data fusion via matrix factorization for augmenting item, group and friend recommendations, Proceedings of the 28th Annual ACM Symposium on Applied Computing, 2013/3/18, 237-244.
  10. Wei Zeng, Yu-Xiao Zhu, Linyuan Lü, Tao Zhou, Negative ratings play a positive role in information filtering, Physica A: Statistical Mechanics and its Applications, 2011/11/1, 390, 23-24.

Research topic

  1. National Natural Science Foundation of China,61872062,Research and Application of Point Process in User Behavior Modeling,2019.01-2022.12,750,000,host.
  2. National Natural Science Foundation Youth Project,61502078,Information Core Mining and Its Application Research in Pushing Security System,2016.01-2018.12,247,000,host.
  3. General equipment “13th Five-Year” equipment pre-research sharing technology, intelligent equipment diagnosis and evaluation technology based on big data,2018.01-2021.12,2,240,000,host(Joint declaration with CLP 10).
  4. National key research and development plan, multimodal spatial and temporal object analysis and visualization,2016YFB0502303,2016.07-2021.06,2000000,Main research(5).
  5. Swiss National Science Foundation, On the diversity Problem of Recommender Systems, EG57-092011,2012.12–2013.12,30,000 Swiss francs,completed,host.
  6. Swiss National Science Foundation,Sino Swiss Science and Technology Cooperation Program Follow-up Grants,TE-70382,2014.07–2014.09,10,000 Swiss francs,completed,host.
  7. Basic Business of Central Universities, recommend system information core mining,2015.09-2017.09,200,000,completed,host.
  8. Basic Business of Central Universities, Recommendation System Information Skeleton and Information Core Research,2019.01-2020.12,60,000,host.
  9. PetroChina Chuanqing Chuanqing Underground Operation Company, fracturing construction wellbore dynamic simulation system, 2016.12-2017.12,200,000,host.
  10. Tibet Military Region General Hospital, computer prediction model project for acute plateau incidence and mental decline in acute high altitude group,2016.06-2016.09,30,000,host.

Teaching research

Academic norms and essay writing, undergraduate students