ICMLC 2027 will be held in Shenzhen, China on February 26-March 01, 2027. The ICMLC 2027 organizing committees invite you to submit the papers to special session. Each special session will be arranged for around 2 hours on Feb. 27 or 28's afternoon. Now the information on special session as following:

Prof. Hongqi Liu
Huazhong University of Science and Technology | 华中科技大学

Yongkang Yang
Huazhong University of Science and Technology | 华中科技大学

Fabin Cheng
Huazhong University of Science and Technology | 华中科技大学
Recent advances in machine learning and deep learning have significantly improved the ability of intelligent systems to extract knowledge from complex and high-dimensional data. However, conventional data-driven learning methods often face challenges related to limited labeled data, distribution shifts, insufficient interpretability, and poor generalization under changing operating conditions. These challenges are particularly prominent in industrial applications, where physical constraints, complex system dynamics, and heterogeneous sensor data must be considered.
Physics-guided machine learning provides a promising approach to addressing these limitations by integrating physical knowledge, mathematical models, and domain-specific constraints into data-driven learning frameworks. Such integration enables the development of more accurate, robust, interpretable, and data-efficient learning methods. Emerging approaches, including physics-informed neural networks, hybrid model-data learning, self-supervised representation learning, domain adaptation, and uncertainty-aware learning, offer new opportunities for intelligent fault diagnosis and complex industrial applications.
This Special Session aims to bring together researchers working on machine learning, scientific computing, intelligent fault diagnosis, and industrial artificial intelligence to explore advanced learning algorithms and computational frameworks that combine physical knowledge with data-driven intelligence.
The session particularly encourages methodological contributions addressing generalization, robustness, data efficiency, and interpretability, as well as innovative applications in industrial condition monitoring, fault diagnosis, and predictive maintenance. By bridging machine learning methodologies with real-world industrial challenges, this session seeks to promote interdisciplinary collaboration and advance trustworthy and generalizable intelligent learning systems.
* Call for Papers Topics.
Topics of interest include, but are not limited to:
The scopes as following:
• Physics-guided machine learning and deep learning
• Hybrid model-based and data-driven learning methods
• Self-supervised and few-shot representation learnings
• Domain adaptation and transfer learning under distribution shifts
• Graph neural networks and temporal learning for complex systems
• Explainable, robust, and uncertainty-aware machine learning
• Multimodal learning and heterogeneous data fusion
• Machine learning for intelligent fault diagnosis and prognostic
Welcome to submit more proposal on ICMLC 2027 special session, please download:
Proposals Submission Guidelines.
Learn more details or submit the proposal, please contact us:
Ms. Doris Ge

Email: icmlc@vip.126.com
Tel: +86-13709044746