Hello, I'm Wenjie Hu

I am a master at Zhejiang University.

My research focuses on Time Series Modeling and Graph Embedding.

About Me My Research

About me


Welcome! My name is Wenjie Hu and I am a master of Computer Science and Technology at Zhejiang University. My research interests lie in mining deep knowledge from large-scale data, which focus on Time Series Modeling and Graph Embedding. I obtained my bachelor degree from Harbin Institute of Technology in 2017, and master degree from Zhejiang University in 2020, advised by Yang Yang. During my master career, I have published one paper and conducted an internship in State Grid of China. For more detailed personal information, please refer to my resume.

Download Resume

My Services


Data Engineering

Develop big data products, unleash your business sense, and discover the value of data.

Algorithm Engineering

Provide big data analysis and modeling solutions, and incubating industry solutions to expand business frontiers.

Website Engineering

Improve the web interface across all products, develop web interfaces, and improve the service architecture and the system performance

Recent Research


  • Graph embedding, also known as network representation learning, aims to learn the low-dimensional representations of vertexes in a network, while structure and inherent properties of the graph is preserved.

    Our research mainly focuses on learning representations for social networks. Social networks are scale-free: vertex degrees of a social network follow a heavy-tailed distribution. Is it possible to reconstruct a scale-free network according to the learned vertex embedding? We first theoretically analyze the difficulty of embedding and reconstructing a scale-free network in the Euclidean space, by converting our problem to the sphere packing problem. Then, we propose the "degree penalty" principle for designing scale-free property preserving network embedding algorithm: punishing the proximity between high-degree vertexes. We introduce two implementations of our principle by utilizing the spectral techniques and a skip-gram model respectively (Feng et al., AAAI'18).

    Read more

Full Publication List


  • *Rui Feng, *Yang Yang, Wenjie Hu, Fei Wu, and Yueting Zhuang. Representation Learning for Scale-free Networks. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI'18), 2018, pages 282-289 (*: equal contribution). [PDF] [Code]
  • Wenjie Hu, Yang Yang, Zilong You, Zongtao Liu and Xiang Ren. Modeling Combinatorial Evolution in Time Series Prediction. In *** (arXiv), 1905.05006[cs.LG]. [PDF] [Code]
  • Wenjie Hu, Yang Yang, Liang Wu, Zongtao Liu, Zhanlin Sun and Bingshen Yao. Capturing Evolution Genes for Time Series Data. In *** (arXiv), 1905.05004[cs.LG]. [PDF] [Code]
  • ***, ***, ***, Wenjie Hu and ***. Time2Graph: Revisiting Time Series Modeling with Dynamic Shapelets. In *** (***), 2019, pages ***. [PDF] [Code]

My Works


The following is a list of my projects, some of which offer the address of github repository

Activities


  • 2018.3
    -
    now

    State Grid of China · HuaYun Group

    Internship · Algorithm Engineer

    Develop algorithms and tools for predicting the trends and anomalies of clock error in watt-hour meters

  • 2018.8
    -
    2018.9

    Pudong·Baidu Smart Finance Geek Competition

    Competition · Captain

    We won the second place in the hackathon, competing with the top universities in China

  • 2015.7
    -
    2015.9

    Alibaba · YunOS

    Internship · Front-End Development

    Develop the official website of YunOS (version 4.0)

Testimonials


Contact me


有朋自远方来,不亦说乎

It's great to have friends coming from afar.

Leave me a message

Friendly Links