Yiqun DIAO

I am a PhD student in School of Computing, National University of Singapore.

My research interests lie in federated learning, open-set learning and data stream learning.

Google Scholar  /  Email  /  CV

• National University of Singapore (NUS), Singapore Aug 2021 - present

  PhD student in Computer Science, advised by Prof. Bingsheng He

• Shanghai Jiao Tong University (SJTU), China Sep 2017 - Jun 2021

  Bachelor in Computer Science and Technology (GPA: 4.08/4.3, Rank: 1/149)

  Selected in Zhiyuan Honors Program of Engineering (Top 5%)

• The University of Texas at Austin (UT Austin), USAAug 2019 - Dec 2019

  Exchange student (GPA: 4.0/4.0)

1. Zhaomin Wu, Junyi Hou, Yiqun Diao, and Bingsheng He. Federated Transformer: Scalable Vertical Federated Learning on Practical Fuzzily Linked Data. NeurIPS 2024, 2024.
2. Qinbin Li, Junyuan Hong, Chulin Xie, Junyi Hou, Yiqun Diao, Zhun Wang, Dan Hendrycks, Zhangyang Wang, Bo Li, Bingsheng He, and Dawn Song. The NeurIPS 2024 LLM Privacy Challenge. NeurIPS 2024 Competition Track, 2024.
3. Yiqun Diao, Yutong Yang, Qinbin Li, Bingsheng He, and Mian Lu. OEBench: Investigating Open Environment Challenges in Real-World Relational Data Streams. 50th International Conference on Very Large Databases (VLDB), 2024.
4. Yiqun Diao, Qinbin Li, and Bingsheng He. Exploiting Label Skews in Federated Learning with Model Concatenation. The 38th Annual AAAI Conference on Artificial Intelligence (AAAI), 2024.
5. Yiqun Diao, Qinbin Li, and Bingsheng He. Towards Addressing Label Skews in One-Shot Federated Learning. The Eleventh International Conference on Learning Representations (ICLR), 2023.
6. Qinbin Li*, Yiqun Diao*, Quan Chen, and Bingsheng He. Federated learning on non-iid data silos: An experimental study. IEEE International Conference on Data Engineering (ICDE), 2022. (* denotes equal contributions) Google Scholar: 1000+ citations; Github NIID-Bench: 560+ stars
7. Lixin Yang, Jiasen Li, Wenqiang Xu, Yiqun Diao, and Cewu Lu. Bihand:Recovering hand mesh with multi-stage bisected hourglass networks. British Machine Vision Conference (BMVC), 2020.

Main Develpoer of
• NIID-Bench: A benchmark for non-IID data problem in federated learning. 550+ Github stars.
• OEBench: A benchmark for open environment challenges in real-world relational data streams.
• PyOE: A Python library for data stream machine learning

Teaching Assistant for
• Big Data System for Data Science NUS, Spring 2022
• Linear Algebra SJTU, Fall 2020
• Computational, Mathematical & Statistical Foundations of Machine Learning SJTU, Summer 2020

• Internship at Microsoft Feb 2021 - Jul 2021
• Internship at 4Paradigm Dec 2022 - May 2023

• Reviewer for CVPR, NeurIPS, ICLR, ECML/PKDD
• External reviewer for ICDE

For sports, I like running, swimming and badminton. I also like literatures and films with realism style.