Bin Chen   (陈斌)

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. My research interests include but are not limited to TKG reasoning, MultiModal learning, IP geolocation, and Trustworthy Neural Networks, etc.

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: binchen4110 AT gmail Dot com

Google Scholar  /  Github  /  CV

🔥 Recent News

  • [2024/06]   🎉🎉🎉1 paper is accepted by TSINGHUA SCIENCE AND TECHNOLOGY.🎉🎉🎉!!!
  • [2024/06]   1 paper has been submitted to EMNLP 2024.
  • [2024/02]   🎉🎉🎉Happy Chinese Loong Year🎉🎉🎉!!!
  • [2023/12]   China People's Net AI Algorithm Competition (Runner-up).
  • [2023/10]   2 papers are accepted by AAAI 2024(Poster).
  • [2023/09]   Academic Scholarship, Outstanding Graduate Students.

  • Publications
    RIPGeo: Robust Street-Level IP Geolocation [Link], Oral
    Wenxin Tai, Bin Chen, Ting Zhong, Yong Wang, Kai Chen, Fan Zhou
    Best Student Paper Award
    MDM, 2023, CCF-C.

    Area: IP Geolocation, Robustness, and Adversarial Training.

    We present RipGeo for robust street-level IP geolocation. Furthermore, considering the widespread noise in measurement data, we propose two novel self-supervised perturbational training strategies to enhance the generalization and robustness of the model. Besides, a multi-task learning framework is introduced to solve the homogenized representation problem caused by perturbational training.

    TrustGeo: Uncertainty-Aware Dynamic Graph Learning for Trustworthy IP Geolocation [Link], Oral
    Wenxin Tai, Bin Chen, Fan Zhou Ting Zhong, Goce Trajcevski, Yong Wang, Kai Chen
    KDD, 2023, CCF-A.

    Area: IP Geolocation, Generalizability, and Uncertainty Learning.

    We present TrustGeo for trustworthy street-level IP geolocation. We incorporate the sources of uncertainty in the learning process of the model to improve prediction accuracy and generalization.

    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: TKG reasoning, Graph Attention Network, and Explainability.

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

    Shallow Diffusion for Fast Speech Enhancement (Student Abstract) [Link], Oral
    Yue Lei, Bin Chen, Wenxin Tai, Ting Zhong, Fan Zhou
    AAAI, 2024, CCF-A.

    Area: Speech Enhancement and Diffusion Models.

    We propose SDFEN to address the inefficiency problem while enhancing the quality of generated samples by reducing the iterative steps in the reverse process of diffusion method. Specifically, a shallow diffusion strategy is introduced to initiate the reverse process with an adaptive time step to accelerate inference.

    Under Review

  • [2024/06]   1 paper has been submitted to EMNLP 2024.
  • [2024/05]   1 paper is under 2nd round of revision in TSINGHUA SCIENCE AND TECHNOLOGY.

  • Competitions and Awards

  • 2023  Artificial Intelligence Challenge Runner-up (Social Media Fake News Detection Track), hosted by www.people.com.cn. [Link]
  • 2023  Best Student Paper Award of the 24th IEEE International Conference on Mobile Data Management (MDM).

  • Academic Service

  • Reviewer: SIGIR 2024;   WWW 2024;   KDD 2024;   IEEE TKDE.
  • IEEE Student Member.

  • Teaching Experience

  • 2023   Teaching Assistant, with Prof. He, at UESTC.

  •  
      Web Site Hit Counter unique visitors since Feburary 2023

    © 2024 Bin Chen | Powered by Jon Barron | updating time 2024-01-13