Special Session on Data-Driven Learning and Optimization

Special Session Chairs

• Prof. Jie Tian, Shandong Womens University, Jinan, China

• Prof. Lin Wang, University of Jinan, Jinan, China

• Prof. Junqing Li, Yunnan Normal University, Kunming, China

• A/Prof. Xilu Wang, University of Surrey, London, UK

Introduction

With the rapid development of big data and artificial intelligence technologies, data-driven learning has demonstrated remarkable capabilities in embedding domain knowledge and is profoundly transforming fields such as intelligent manufacturing, financial technology, and biomedical science. However, as data volume continues to grow and model structures become increasingly complex, the computational resources required for training and inference are rising sharply. Challenges such as optimization cost, response efficiency, adaptability, and security control are becoming critical bottlenecks that limit further advancements. Against this backdrop, how to achieve efficient, scalable, and controllable optimization while maintaining the advantages of data-driven learning has emerged as a key research focus for both academia and industry. Innovations in optimization techniques not only enhance the practicality and generality of data-driven models but also accelerate the deployment of intelligent systems in diverse real-world scenarios.

This forum aims to bring together leading scholars and practitioners in the field of data-driven learning and optimization to share cutting-edge research, methodological innovations, and application experiences. By focusing on core challenges and emerging opportunities, we seek to foster in-depth interdisciplinary communication and collaboration, driving the systematic development and future evolution of data-driven model optimization.

We warmly invite you to submit your work and join us in exploring the latest advancements in this dynamic field. 

Keywords

Federated Learning; Data-Driven Optimization; Bayesian optimization；Recommendation Systems; Deep Learning; Large Language Models; Knowledge Graph；Distributed optimization

Topics of Interest

Topics include but are not limited to:

•Theoretical analysis and optimization of deep learning models

•Data-driven strategy optimization in reinforcement learning

•Optimization strategies for multimodal data fusion

•Data-driven meta-heuristic algorithm optimization

•Distributed data-driven optimization algorithms

•Optimization of data-driven learning in biomedical and healthcare applications

•Data-driven risk prediction and optimization in financial technology

•Data-driven production optimization in intelligent manufacturing

•Adaptive data preprocessing methods based on data-driven learning

•Optimization of personalized learning paths in education through data-driven approaches

•Optimization of data-driven learning in medical image diagnostics