蒲元昊, Yuanhao Pu

蒲元昊, Yuanhao Pu

he/his

Data Science Ph.D student

Welcome to Yuanhao Pu’s homepage!

Pu Yuanhao is currently a (4th-year) full-time Ph.D. student in School of Artificial Intelligence & Data Science (formerly named as School of Data Science), University of Science and Technology of China (USTC), under the supervison of Prof.Defu Lian. He got his B.S. degree from School of Mathematical Sciences, University of Science and Technology of China (USTC) in Jun. 2021.

His research interest mainly focus on Machine Learning Theories and its applications on Recommender Systems, especially Bayes-Consistency properties for theoretical understandings of model design.

Recent Updates

  • Today: Today is a brand new day!😊
  • 2024.11.17: Our work on understanding the H-consistency of the two-tower model hypothesis space has been accepted by KDD2025!✨😆
  • 2024.05.02: Our work on designing a metric-consistent and generalizable squared-form loss has been accepted by ICML2024!✨😆
  • 2024.03.26: Our extension work on designing an automated and low-rank shallow autoencoder has been accepted by TORS!🌟😉

Educations

  • 2021.9-till now: Ph.D., School of Artificial Intelligence & Data Science, University of Science and Technology of China (majoring in Data Science (Computer Science and Technology), transferred from M.Eng. of Computer Technology with a successive postgraduate-doctoral program in Sep. 2023)

  • 2017.9-2021.6: B.S., School of Mathematical Sciences, University of Science and Technology of China (majoring in Probablilty & Statistics)

Publications

  1. Yuanhao Pu, Defu Lian, Xiaolong Chen, Jin Chen, Ze Liu, Enhong Chen. Understanding the Effect of Loss Functions on the Generalization of Recommendations. Proceedings of the 31st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2025), accepted, 2025.

  2. Yuanhao Pu, Xiaolong Chen, Xu Huang, Jin Chen, Defu Lian*, Enhong Chen. Learning-Efficient Yet Generalizable Collaborative Filtering for Item Recommendation. Proceedings of the 41st International Conference on Machine Learning(ICML 2024), PMLR 235:41183-41203, 2024.

  3. Yuanhao Pu, Rui Fan, Jin Chen, Zhihao Zhu, Defu Lian*, Enhong Chen. Automated Sparse and Low-Rank Shallow Autoencoders for Recommendation. ACM Transactions on Recommender Systems (TORS), accepted, 2024.

  4. Ruimeng Li, Yuanhao Pu, Zhaoyi Li, Chenwang Wu, Hong Xie*, Defu Lian. Invariant Representation Learning via Decoupling Style and Spurious Features. Machine Learning Journal (MLJ), accepted, 2024.

  5. Jin Chen, Zheng Liu, Xu Huang, Chenwang Wu, Qi Liu, Gangwei Jiang, Yuanhao Pu, Yuxuan Lei, Xiaolong Chen, Xingmei Wang, Defu Lian, Enhong Chen. When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunities. World Wide Web (WWWJ) 27, 42 (2024).

  6. Rui Fan, Yuanhao Pu, Jin Chen, Zhihao Zhu, Defu Lian* and Enhong Chen. AutoS2AE: Automate to Regularize Sparse Shallow Autoencoders for Recommendation. The 32nd Web Conference (WWW 2023), pp. 1032-1042, Apr. 2023.

  7. Qi Liu, Xingyuan Tang, Jianqiang Huang, Xiangqian Yu, Haoran Jin, Jin Chen, Yuanhao Pu, Defu Lian, Tan Qu, Zhe Wang, Jia Cheng, Jun Lei. Efficient Transfer Learning Framework for Cross-Domain Click-Through Rate Prediction. arXiv preprint arXiv:2408.16238, 2024.