Integration of knowledge and data in machine learning

TL;DR

This paper reviews how integrating knowledge embedding and discovery enhances machine learning models, fostering scientific understanding and uncovering new principles through a closed loop of knowledge generation and application.

Contribution

It provides a comprehensive summary of existing methods, highlights research gaps, and discusses future opportunities in integrating knowledge and data in machine learning.

Findings

Knowledge embedding eliminates barriers between knowledge and data.

Knowledge discovery extracts new scientific knowledge from observations.

Combining both methods improves model robustness and uncovers unknown principles.

Abstract

Scientific research's mandate is to comprehend and explore the world, as well as to improve it based on experience and knowledge. Knowledge embedding and knowledge discovery are two significant methods of integrating knowledge and data. Through knowledge embedding, the barriers between knowledge and data can be eliminated, and machine learning models with physical common sense can be established. Meanwhile, humans' understanding of the world is always limited, and knowledge discovery takes advantage of machine learning to extract new knowledge from observations. Knowledge discovery can not only assist researchers to better grasp the nature of physics, but it can also support them in conducting knowledge embedding research. A closed loop of knowledge generation and usage are formed by combining knowledge embedding with knowledge discovery, which can improve the robustness and accuracy of models and uncover previously unknown scientific principles. This study summarizes and analyzes extant literature, as well as identifies research gaps and future opportunities.