Yue Zhao
Avatar of Yue Zhao
Assistant Professor
Thomas Lord Department of Computer Science

University of Southern California

Los Angeles, CA, USA
Email:
Google Scholar | Short Bio | GitHub | Twitter | LinkedIn | 知乎 (微调) | 小红书 | 微信

Biography & Openings. Copy/paste from my short Bio if needed :) See lab openings at ASAP Lab (Openings).

Research Interests. I build reproducible, automated, and scalable machine learning (ML) and data mining (DM) benchmarks, algorithms, and systems, with a focus on but not limited to anomaly detection, graph neural networks, ML systems, and healthcare for AI.

  1. Benchmark various learning algorithms for fair evaluation and new insights.
  2. Automate ML by model selection and hyperparameter optimization.
  3. Design large-scale ML systems for real-world applications.
  4. Develop open-source ML tools to support applications in healthcare, finance, security, and more.

Research Keywords: (1) ML and DM: Anomaly/Outlier/Out-of-Distribution (OOD) Detection, Unsupervised ML, Graph Neural Networks (2) Open Systems: ML Systems, Automated ML, Decentralized Learning(3) Applications: AI for Science, e.g., healthcare, security, and finance.

Open-source ML . I created PyOD (used by NASA, Tesla, Morgan Stanley, and more) - the most popular library for anomaly detection in 2017. Also, I have led more than 10 ML open-source initiatives, receiving 20,000 GitHub stars (top 0.002%) and >20M downloads. Popular ones: PyOD, PyGOD, TDC, ADBench

Social Platforms. I am active on Twitter, LinkedIn, and 中文平台 知乎 (微调), 小红书 (微调). I have more than 250,000 followers on all social platforms in combination. 我有一系列北美在读CS PhD找实习和全职的微信群 (不是PhD申请群)，以及一个2025年CS教职/教授申请群 (24年底申请，25年入职)。可以添加微信yzhao010入群。

✈ News and Travel

[Mar 2024] We get more than 5,000 GPU hours on A100 and equivalent from NSF and Google.

[Mar 2024] Selected to be a Google Cloud Research Innovators!

[Jan 2024] Being part of an impactful cross-institution work TrustLLM: Trustworthiness in Large Language Models! See paper and code.

[Dec 2023] Selected to be part of the 2024 AAAI New Faculty Highlights! I will present Towards Reproducible, Automated, and Scalable Anomaly Detection.

🏅 Awards and Grants