🐎 I am moving my website to https://viterbi-web.usc.edu/~yzhao010/, and this site is no longer maintained. You will be redirected automatically in 3 seconds.
Next Steps. 🐎 I will join USC as an Assistant Professor of Computer Science in August 2023 (more details on intern/visitor, graduate student, and postdoc recruitment to follow.)
Contact me by Email (yzhao010 [AT] usc.edu) or WeChat @ yzhao062. Of course, please add my WeChat only for good reasons, e.g., collaboration, visiting, joining the group, etc.
Short Bio. I got my Ph.D. in 4 years at Carnegie Mellon University (CMU). My research accelerates and automates unsupervised ML: (1) how to speed up large-scale learning tasks with ML systems and (2) how to automate unsupervised ML model selection and hyperparameter optimization. I build AI/ML applications in finance, healthcare, and security.
Open-source Contribution. I have led to more than 10 ML open-source initiatives, receiving 16,000 GitHub stars (top 0.002%: ranked 800 out of 40M GitHub users) and >15M downloads.
Social Media. I wrote more than 300 articles (in Chinese) with 220,000 followers on Zhihu (知乎) (200 million+ users). My articles have got more than 20,000,000 time read. See my Zhihu (微调).
Ph.D. time. At CMU, I worked with Prof. Leman Akoglu, Prof. Zhihao Jia, and Prof. George H. Chen. I was a member of CMU automated learning systems group (Catalyst). I collaborated with Prof. Jure Leskovec at Stanford and Prof. Philip S. Yu at UIC.
Ph.D., 2019-2023
Carnegie Mellon University
M.S., 2015-2017
University of Toronto
B.S., 2015
University of Cincinnati
High School Diploma, 2010
Shanxi Experimental Secondary School 山西省实验中学
May 2023: I defended my thesis!!! See the photo :)
Apr 2023: Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networks will appear in ICML 2023. Congrats to Peng Xu and Lin Zhang!
Feb 2023: Weakly Supervised Anomaly Detection: A Survey is out! [code]
See my Google Scholar, DBLP, ORCID, and ResearchGate.
[w23a] Weakly Supervised Anomaly Detection: A Survey, with Minqi Jiang, Chaochuan Hou, Ao Zheng, Xiyang Hu, Songqiao Han, Hailiang Huang, Xiangnan He, Philip S. Yu. Preprint.
[w22f] Diffusion Models: A Comprehensive Survey of Methods and Applications, with Ling Yang, Zhilong Zhang, Yang Song, Shenda Hong, Runsheng Xu, Yingxia Shao, Wentao Zhang, Bin Cui, and Ming-Hsuan Yang. Preprint.
[w22e] Hyperparameter Optimization for Unsupervised Outlier Detection, with Leman Akoglu. Preprint.
Professional Positions
Designed weakly supervised anomaly detection algorithms.
Supervised by Dr. Guoqing Zheng and Dr. Subhabrata (Subho) Mukherjee.
Designed new GNN systems and models.
Supervised by Prof. Jure Leskovec.
Designed new machine learning systems and models in healthcare.
Supervised by Dr. Cao (Danica) Xiao (IQVIA) and Prof. Jimeng Sun (UIUC).
Applied research in people analytics with machine learning.
Supervised by Prof. Anthony Bonner and the project is partly supported by Mitacs-Accelerate Research and Development Funding (IT07884).
Teaching Positions
I am a teaching assistant for the following courses:
The main duties include grading assignments and giving lectures on selected topics.
To find more of my open-source initiatives, see my GitHub. Popular ones: