Yuntao Du (杜云滔)

Yuntao Du (杜云滔)

Zhejiang University

I am a third-year graduate student in computer science at Zhejiang University, advised by Prof. Yunjun Gao.

I have been very fortunate to work with Prof. Zhikun Zhang at Stanford University , with Prof. Christian S. Jensen at Aalborg University , with Prof. Baihua Zheng at Singapore Management University , with Dr. Jianxun Lian and Dr. Xing Xie at Microsoft Research Asia .

My goal is to build reliable models with a focus on their explainability (to facilitate human understanding), data privacy (to preserve users’ privacy), and robustness (to data noise), which guarantee their trustworthiness in critical real-world applications. I have published more than 10 papers at the top international conferences such as VLDB, KDD, SIGIR and ICDE.

🔥 News

  • 2023.01: One paper is accepted by WWW on explainable collaborative filtering!
  • 2022.12: One paper is accepted by ICDE on federated learning acceleration!
  • 2022.05: One paper is accepted by SIGKDD on trajectory similarity learning!
  • 2022.04: One paper is accepted by TKDE on cold-start recommendation!
  • 2022.03: Two papers are accepted by SIGIR on knowledge-aware/robust recommender systems!

📝 Selected Publications (FULL list)

🔐 Data Privacy

VLDB 2023
sym

LDPTrace: Locally Differentially Private Trajectory Synthesis
Yuntao Du, Yujia Hu, Zhikun Zhang, Ziquan Fang, Lu Chen, Baihua Zheng, Yunjun Gao

Project | GitHub | Datasets

  • LDPTrace is the first trajectory synthesis solution with local differential privacy guarantee. 👣 🕹️ 🔒

📊 Data Mining

WWW 2023
sym

Towards Explainable Collaborative Filtering with Taste Clusters Learning
Yuntao Du, Jianxun Lian, Jing Yao, Xiting Wang, Mingqi Wu, Lu Chen, Yunjun Gao, Xing Xie

Blog |

  • ECF is the first cluster-based explainable collaborative filtering method.
  • ECF has been deployed on Xbox for game recommendation. 🎮 ⛏️ 🚀
SIGIR 2022
sym

HAKG: Hierarchy-Aware Knowledge Gated Network for Recommendation
Yuntao Du, Xinjun Zhu, Lu Chen, Baihua Zheng, Yunjun Gao

PWC

Blog |

  • HAKG is the hyperbolic knowledge-aware recommendation model.
  • HAKG achieves SOTA results on many public datasets. 📈 💫 🔝

✍🏻 Professional Services

I am/was a program committee member for the following conferences/workshops:

  • The AAAI Conference on Artificial Intelligence (AAAI) 2023.
  • ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) 2023.

I am/was invited reviewers for the following journals:

  • ACM Transactions on Recommender Systems (TORS)

🌟 Honors and Awards

  • 2022.10 National Scholarship (Top 1%)
  • 2022.04 SIGIR Student Travel Grant
  • 2021.10 Tencent Scholarship (Top 1%)
  • 2021.10 National Scholarship (Top 1%)
  • 2019.10 Excellent Undergraduate Student (Top 1%)

📖 Educations

  • 2020.09 - 2023.06, Master, Department of Computer Science and Technology, Zhejiang University, Hangzhou, China
  • 2015.09 - 2020.06, Undergraduate, School of Data Science and Engineering, East China Normal Univeristy, Shanghai, China.

💬 Invited Talks

  • 2023.01, Explainble Clustering and Cluster-based Collaborative Filtering, Social Computing Group, MSRA internal talk | [Slides]
  • 2022.04, HAKG: Hierarchy-Aware Knowledge Gated Network for Recommendation, SIGIR 2022 | [Slides]
  • 2022.04, Self-Guided Learning to Denoise for Robust Recommendation, SIGIR 2022 | [Slides]

💻 Internships