Sijie MA's Homepage

Hi! I’m Sijie MA

I’m a junior undergraduate student majoring in Computer Science and Technology at South China University of Technology. With a strong interest in the intersection of machine learning and optimization, I’m currently focused on Meta Black-Box Optimization (MetaBBO).

I feel incredibly lucky to be recommended by Prof. Yuejiao Gong and to work under the guidance of Zeyuan Ma and Hongshu Guo. As a member of the GMC-DRL group, I’m diving deep into the theory and practice of meta-learning, striving to build systems that adapt, generalize, and optimize across tasks.

News

Mar 20, 2025	🎉 Our paper has been accepted to GECCO 2025! 🚀
Jan 13, 2025	Winter vacation has started. Get ready with a final sprint for the 2025 GECCO conference!🏃‍♂️
Jan 13, 2025	Build My Own Website!

Publications

Gecco

Reinforcement Learning-based Self-adaptive Differential Evolution through Automated Landscape Feature Learning

Hongshu Guo , Sijie Ma, Zechuan Huang, Yuzhi Hu, Zeyuan Ma, Xinglin Zhang, and Yue-Jiao Gong^*

arXiv preprint arXiv:2503.18061, Mar 2025

Abs arXiv Code

Recently, Meta-Black-Box-Optimization (MetaBBO) methods significantly enhance the performance of traditional black-box optimizers through meta-learning flexible and generalizable meta-level policies that excel in dynamic algorithm configuration (DAC) tasks within the low-level optimization, reducing the expertise required to adapt optimizers for novel optimization tasks. Though promising, existing MetaBBO methods heavily rely on human-crafted feature extraction approach to secure learning effectiveness. To address this issue, this paper introduces a novel MetaBBO method that supports automated feature learning during the meta-learning process, termed as RLDE-AFL, which integrates a learnable feature extraction module into a reinforcement learning-based DE method to learn both the feature encoding and meta-level policy. Specifically, we design an attention-based neural network with mantissa-exponent based embedding to transform the solution populations and corresponding objective values during the low-level optimization into expressive landscape features. We further incorporate a comprehensive algorithm configuration space including diverse DE operators into a reinforcement learning-aided DAC paradigm to unleash the behavior diversity and performance of the proposed RLDE-AFL. Extensive benchmark results show that co-training the proposed feature learning module and DAC policy contributes to the superior optimization performance of RLDE-AFL to several advanced DE methods and recent MetaBBO baselines over both synthetic and realistic BBO scenarios.