Kai Yang      

Currently, I am a second-year master student at University of Electronic Science and Technology of China(UESTC), supervised by Prof. Fan Zhou and Prof. Ting Zhong. In addition, I have been an IEEE student Member since 2023. My research interests include but are not limited to Trustworthy AI, Spatial-temporal Recommendation System.

Before that, I obtained the bachelor's degree in School of Information and Software Engineering from University of Electronic Science and Technology of China (UESTC) in 2022.

Email: kaiyang.cs AT outlook.com  /  Google Scholar  /  Github

πŸ”₯ Recent News

  • [2024/04]   Conference ICASSP2024 Presentation in Seoul, South Korea.
  • [2024/03]   1 paper is accepted by SIGIR 2024.
  • [2024/02]   πŸŽ‰πŸŽ‰πŸŽ‰Happy Chinese Loong YearπŸŽ‰πŸŽ‰πŸŽ‰!!!
  • [2023/12]   China People's Net AI Algorithm Competition(3rd).
  • [2023/12]   China Shenzhen Stock Exchange Scholarship.
  • [2023/11]   1 paper is accepted by ICASSP 2024.
  • [2023/10]   2 papers are accepted by AAAI 2024(Poster).

  • πŸ“š Publications
    ExNext: Self-Explainable Next POI Recommendation[Link]
    Kai Yang, Yi Yang, Qiang Gao, Ting Zhong, Yong Wang, Fan Zhou
    SIGIR, 2024, CCF-A.

    Area: POI Recommendation, Trustworthy, and Information Theory

    We introduce a novel framework called ExNext for Point of Interest (POI) recommendation in LBSNs, which focuses on improving the trustworthiness of recommender systems by enhancing both accuracy and explainability. Our framework utilizes information theory to learn a compact representation that balances knowledge compression with retaining relevant information.

    EXGeo: Exploring Self-Explainable Street-Level IP Geolocation with Graph Information Bottleneck[Link]
    Kai Yang, Wenxin Tai, Zhenhui Li, Ting Zhong, Guangqiang Yin, Yong Wang, Fan Zhou
    ICASSP, 2024, CCF-B.

    Area: Geolocation, Explainability, and Information Bottleneck Theory.

    We endow the geolocation model with explainability through variational IB theory, which aims at striking a balance between knowledge compression (provid-ing concise explanations) and preserving pertinent information (offering informative representations).

    TCGeo: Improving IP Geolocation With Target-Centric IP Graph (Student Abstract)[Link]
    Kai Yang, Jiayang Li, Wenxin Tai, Zhenhui Li, Ting Zhong, Guangqiang Yin, Yong Wang, Fan Zhou
    AAAI, 2024, CCF-A.

    Area: Geolocation, Sparsity, and Graph Neural Network.

    We provide a new view of geolocation through mitigating sparsity, which aims at enhancing contextual information utilization in social graph and network topology.

    LSGAT: Interpreting Temporal Knowledge Graph Reasoning (Student Abstract)[Link]
    Bin Chen, Kai Yang, Wenxin Tai, Zhangtao Cheng, Leyuan Liu, Ting Zhong, Fan Zhou
    AAAI, 2024, CCF-A.

    Area: Event Prediction, Explainability, and Temporal Knowledge Graph.

    We provide an innovative method of event prediction, which not only exhibits remarkable precision in entity predictions but also enhances interpretability by identifying pivotal historical events influencing event predictions.

    Under Review

  • [2024/3]   Our work has been submitted to IEEE Transactions on Networking.

  • Conference Presentation

  • 2024   The 49th IEEE International Conference on Acoustics, Speech, & Signal Processing (ICASSP) will be held in Seoul, Korea.

  • Academic Service

  • Reviewer: ICLR 2024;   AAAI 2024;   KDD 2024;   IEEE TKDE.
  • IEEE Student Member.

  • Teaching Experience

  • 2022   Teaching Assistant, with Prof. Wang, at UESTC.

  •  
      Web Site Hit Counter unique visitors since November 2023

    Β© 2024 Kai Yang | Powered by Jon Barron and Patton Yu | updating time 2024-05-01