Worth of knowledge in deep learning
This work provides a tool for researchers and practitioners to assess and improve informed machine learning, though it appears incremental in applying interpretable ML concepts to knowledge evaluation.
The authors tackled the problem of evaluating the worth of prior knowledge in deep learning to address issues like data dependence and generalization, presenting a model-agnostic framework that elucidates complex data-knowledge relationships such as dependence, synergy, and substitution effects.
Knowledge constitutes the accumulated understanding and experience that humans use to gain insight into the world. In deep learning, prior knowledge is essential for mitigating shortcomings of data-driven models, such as data dependence, generalization ability, and compliance with constraints. To enable efficient evaluation of the worth of knowledge, we present a framework inspired by interpretable machine learning. Through quantitative experiments, we assess the influence of data volume and estimation range on the worth of knowledge. Our findings elucidate the complex relationship between data and knowledge, including dependence, synergistic, and substitution effects. Our model-agnostic framework can be applied to a variety of common network architectures, providing a comprehensive understanding of the role of prior knowledge in deep learning models. It can also be used to improve the performance of informed machine learning, as well as distinguish improper prior knowledge.