RelativeNAS: Relative Neural Architecture Search via Slow-Fast Learning
IEEE Transactions on Neural Networks and Learning Systems, 2021
About
I am a PhD candidate in the School of Computer Science at the University of Leeds, UK. My research explores how deep learning models can be combined, adapted, and reused across different vision tasks.
Beyond research, I am interested in technology, investment, and understanding complex systems through multidisciplinary mental models. I enjoy exploring how insights from different fields can be brought together to better explain real-world problems and inform decision-making.
Research
Journal Articles
Efficient Evolutionary Neural Architecture Search by Modular Inheritable Crossover
Swarm and Evolutionary Computation, 2021
Conference Papers
Efficient Evolutionary Neural Architecture Search (NAS) by Modular Inheritable Crossover
International Conference on Bio-inspired Computing: Theories and Applications (BIC-TA), 2019
Patents
A Neural Architecture Search Method and System Based on Evolutionary Learning
International Patent · PCT/CN2020/136950, 2022
Experience
Jul 2020 – Jul 2021
Research Assistant
Southern University of Science and Technology, Shenzhen, China
Developed neural architecture search algorithms, collaborated with industry partners on lightweight neural architectures for constrained chip hardware, and implemented evolutionary optimization pipelines in PyTorch.
Education
Oct 2021 – Jul 2026 (expected)
Doctor of Philosophy
University of Leeds, Leeds, UK
I am under the supervision of Dr. Nabi Omidvar and Prof. Netta Cohen. My research interests include deep model fusion and multi-task learning.
Sep 2016 – Jun 2020
Bachelor of Engineering
Southern University of Science and Technology, Shenzhen, China
My major is Computer Science and Technology. This is where I first got into deep learning and doing projects related to neural architecture search with evolutionary algorithms.