Causal Inspired Trustworthy Machine Learning
Kun Kuang · 2023
In causality-based trustworthy machine learning, finding mechanisms from data-driven correlation analysis to causal inference and constructing a machine learning framework from correlation-driven to causality-driven are two significant challenges. To address these challenges, we propose a series of innovations, including data-driven causal inference mechanisms, causality-inspired interpretable and stable learning frameworks, causality-based generalizable graph neural network learning frameworks, and other fundamental theories and key technologies. To further support the development of the field, we make the corresponding codes and resources public in the open-source community, including the big data causal inference framework based on instrumental variables (https://github.com/causal-machine-learning-lab/mliv) and the large-scale graph neural network computing and edge-cloud collaborative learning platform (https://github.com/luoxi-model/luoxi_models).