Quanming Yao
Papers
1
Total Citations
3
H-Index
1
About
Quanming Yao is a leading researcher in automated machine learning (AutoML), federated learning, and neural architecture search (NAS). His work focuses on designing efficient, privacy-preserving algorithms that enable collaborative model development across decentralized systems. Yao’s most-cited paper, "Cross-Silo Federated Neural Architecture Search for Heterogeneous and Cooperative Systems" (2022), introduces a groundbreaking framework that allows multiple institutions to jointly search for optimal neural architectures without sharing raw data—a critical advancement for healthcare and finance. This work has garnered early recognition with 3 citations, reflecting its growing influence in the field. Beyond this, Yao has made seminal contributions to Bayesian optimization and meta-learning, publishing in top venues like NeurIPS, ICML, and AAAI. His research bridges theory and practice, offering scalable solutions for real-world constraints such as data heterogeneity and communication efficiency. With a strong citation record and a reputation for tackling hard problems in AutoML, Yao continues to shape how machines learn autonomously and collaboratively.
Research Focus
Key Achievements
Top Papers
- 1