Special Session on Causal Inference and Machine Learning (CIML-2023)
Overview
Causal inference is a fundamental research topic that provides interpretation, prediction, decision-making and control. A series of problems like stability, interpretability, and fairness in traditional statistical machine learning models can be effectively solved by leveraging causal inference principles. Currently, many research questions still await further investigation by new causal inference theories and algorithms, such as the direction discrimination of causal equivalence classes, the control of false discovery rate on high-dimensional data, the detection of hidden variables on incomplete observation data, and the learning of hidden variable causality, as well as issues like root cause analysis and debiased recommendation. The goal of this special session is to conduct the comprehensive systematic reviews on causality, the corresponding packages/codes of causal inference, and applications of causality in the industry. Especially, we encourage submissions of the state-of-the-art causality-aware research and use cases in natural language understanding and recommender systems.
Scope
The coverage of the CIML-2023 includes, but is not limited to, the following topics:
- Theoretical research on causal inference for machine learning
- Research on interpretability and stability based on causal inference
- Research on software engineering and requirements engineering based on causal inference
- New causal inference datasets, toolboxes
- Causality-assisted methodology for multi-modality learning
- Applications and use cases of causal inference in computer vision, natural language processing, recommendations, healthcare informatics etc.
- Research on the construction and application of event logic graph in industrial field
Organizers
Dr. Bo Huang
School of Electrical and Electronic Engineering, Shanghai University of Engineering Science, Shanghai, China
Email: huangbosues@sues.edu.cn
Dr. Liang Tao
School of Science and Technology, Hong Kong Metropolitan University, Hong Kong, China
Email: ltao@hkmu.edu.hk
Ling Yin
School of Electrical and Electronic Engineering, Shanghai University of Engineering Science, Shanghai, China
Email: lyin@sues.edu.cn