Informed Machine Learning – A Taxonomy and Survey of Integrating Prior Knowledge into Learning Systems

By Laura von Rueden, S. Mayer, Katharina Beckh, B. Georgiev, Sven Giesselbach, R. Heese, Birgit Kirsch, Julius Pfrommer, Annika Pick, Rajkumar Ramamurthy and 4 more. IEEE Transactions on Knowledge and Data Engineering, 2019

876 citations recorded by the source corpus.

Despite its great success, machine learning can have its limits when dealing with insufficient training data. A potential solution is the additional integration of prior knowledge into the training process which leads to the notion of informed machine learning. In this paper, we present a structured overview of various approaches in this field. We provide a definition and propose a concept for informed machine learning which illustrates its building blocks and distinguishes it from conventional machine learning. We introduce a taxonomy that serves as a classification framework for informed machine learning approaches. It considers the source of knowledge, its representation, and its integration into the machine learning pipeline. Based on this taxonomy, we survey related research and describe how different knowledge representations such as algebraic equations, logic rules, or simulation results can be used in learning systems. This evaluation of numerous papers on the basis of our taxonomy uncovers key methods in the field of informed machine learning.

Subfields: Artificial Intelligence, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/2b49156cf855dbb39768ae0ba7d7cb9263d17e5c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Statistical and Nonlinear Physics

Citations in the corpus

Integrating Scientific Knowledge with Machine Learning for Engineering and Environmental Systems (2020, background): “This distinguishes our survey from other works that focus on more general knowledge integration into machine learning [7, 277] and works covering physics integration into ML in specific domains (e.”
Characterizing possible failure modes in physics-informed neural networks (2021, background): “In this vein, there have been a number of ML approaches to incorporate scientific knowledge into such problems while keeping the automatic, data-driven estimates of the solution [2, 17, 33, 39].”