Jiahuan Luo
Papers
1
Total Citations
3
H-Index
1
About
Jiahuan Luo is a researcher at the forefront of federated learning and neural architecture search (NAS), with a focus on enabling efficient, privacy-preserving collaboration across heterogeneous systems. Their most notable contribution, "Cross-Silo Federated Neural Architecture Search for Heterogeneous and Cooperative Systems" (2022), addresses a critical challenge in distributed machine learning: how to automatically design neural networks that can adapt to diverse computational and data constraints across different silos without centralizing sensitive data. This work pioneers a cross-silo federated NAS framework that balances model performance with communication efficiency, paving the way for real-world applications in healthcare, finance, and edge computing. While early in its citation trajectory (3 citations), the paper’s conceptual novelty and practical relevance signal growing influence. Luo’s research bridges the gap between automated machine learning and federated systems, offering scalable solutions for cooperative yet privacy-aware AI. Their work is particularly valuable for students and researchers exploring decentralized learning, as it provides a blueprint for integrating NAS into federated settings—a domain poised for explosive growth.
Research Focus
Key Achievements
Top Papers
- 1