Assistant Professor of Computer Science
Education
- 2023, Doctoral Degree, Information Systems, Carnegie-Mellon University
- 2016, Master's Degree, Computer Science, University of Toronto
- 2015, Bachelor's Degree, Computer Engineering, University of Cincinnati
Biography
Dr. Yue Zhao is an Assistant Professor of Computer Science at the University of Southern California and a faculty member of the USC Machine Learning Center. He leads the FORTIS Lab (Foundations Of Robust Trustworthy Intelligent Systems), where his research spans multiple levels of AI innovation. Dr. Zhao focuses on ensuring robustness and trustworthiness in AI principles, leveraging structured knowledge through graph learning, advancing applications in generative AI and AI for Science (AI4Science), and developing scalable and open-source AI systems. His work has applications across diverse domains, including healthcare, finance, molecular science, and political science. Dr. Zhao has authored over 50 papers in top-tier venues and is celebrated for his contributions to open-source ML systems, such as PyOD, PyGOD, TDC, and TrustLLM, which collectively gain over 20,000 GitHub stars and 25 million downloads. His innovative projects have been utilized by prestigious organizations, including NASA, Morgan Stanley, and the U.S. Senate Committee on Homeland Security & Governmental Affairs. Dr. Zhao has received numerous awards, including the Capital One Research Awards, AAAI New Faculty Highlights Award, Google Cloud Research Innovators, Norton Fellowship, Meta AI4AI Research Award, and the CMU Presidential Fellowship. He also serves as an associate editor for IEEE Transactions on Neural Networks and Learning Systems (TNNLS), an action editor for the Journal of Data-centric Machine Learning Research (DMLR), and an area chair for most top ML conferences.
Research Summary
My research focuses on building trustworthy, scalable, and generative AI systems by addressing challenges across multiple levels: from ensuring robustness and trustworthiness in AI principles, leveraging structured knowledge through graph learning, advancing applications in generative AI and AI for Science (AI4Science), to developing scalable and open-source AI systems. These efforts create interconnected, impactful solutions for domains such as healthcare, finance, molecular science, and political forecasting.
Robust and Trustworthy AI Across Domains (Principle): Developing reliable AI systems to detect outliers, anomalies, and out-of-distribution (OOD) data, ensuring trust, fairness, and transparency in diverse areas like finance, healthcare, and political science. This foundational focus underpins all other levels of AI research and applications.
Keywords: OOD Detection, Outlier Detection, Anomaly Detection, Trustworthiness
Graph Learning for Structured Knowledge and Decision-Making (Structure): Applying graph-based models to extract insights from interconnected data, enabling tasks such as graph OOD detection, neural architecture search (NAS), and anomaly detection. These methods drive applications in molecular science, financial risk modeling, and healthcare.
Keywords: GNNs, Graph Open Set Learning, Graph Anomaly Detection, Graph OOD Detection
Generative AI and Foundation Models for AI4Science (Application): Leveraging generative AI, LLMs, and foundation models to solve scientific and societal challenges. Applications include synthetic clinical trials, drug discovery, and political forecasting, with contributions like DrugAgent and AI-driven digital twins.
Keywords: LLMs, Foundation Models, AI4Science, Drug Discovery, LLMs for Political Science
Scalable and Open-Source AI Systems (System): Building scalable tools and frameworks for tasks like model selection, hyperparameter optimization, and anomaly detection. As the creator of PyOD (25M+ downloads, used by NASA, Tesla, etc.), I lead 10+ open-source projects, including PyGOD, TDC, and ADBench, which collectively boast 20,000+ GitHub stars, accelerating AI adoption and impact.
Keywords: Automated ML, Distributed Systems, Open-source AI, Scalability
Awards
- 2024 Amazon Amazon Research Awards
- 2024 Google Google Cloud Research Innovators
- 2024 Capital One Research Awards
