Knowledge Infused Learning (K-IL): Towards Deep Incorporation of Knowledge in Deep Learning

By Ugur Kursuncu, Manas Gaur, Amit P. Sheth. 2019

68 citations recorded by the source corpus.

Learning the underlying patterns in data goes beyond instance-based generalization to external knowledge represented in structured graphs or networks. Deep learning that primarily constitutes neural computing stream in AI has shown significant advances in probabilistically learning latent patterns using a multi-layered network of computational nodes (i.e., neurons/hidden units). Structured knowledge that underlies symbolic computing approaches and often supports reasoning, has also seen significant growth in recent years, in the form of broad-based (e.g., DBPedia, Yago) and domain, industry or application specific knowledge graphs. A common substrate with careful integration of the two will raise opportunities to develop neuro-symbolic learning approaches for AI, where conceptual and probabilistic representations are combined. As the incorporation of external knowledge will aid in supervising the learning of features for the model, deep infusion of representational knowledge from knowledge graphs within hidden layers will further enhance the learning process. Although much work remains, we believe that knowledge graphs will play an increasing role in developing hybrid neuro-symbolic intelligent systems (bottom-up deep learning with top-down symbolic computing) as well as in building explainable AI systems for which knowledge graphs will provide scaffolding for punctuating neural computing. In this position paper, we describe our motivation for such a neuro-symbolic approach and framework that combines knowledge graph and neural networks.

Subfields: Artificial Intelligence, Representation & Self-Supervised Learning, Knowledge Graphs & Representation

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 Representation & Self-Supervised Learning

In Knowledge Graphs & Representation

Citations in the corpus

Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges (2021, background): “Going beyond PDEs to other types of complex constraints that encode prior knowledge, Kursuncu et al. (2020) proposed the concept of knowledge infused deep learning, where the learning of a deep neural network is guided by domain knowledge represented as a knowledge graph.”
Shades of Knowledge-Infused Learning for Enhancing Deep Learning (2019, background): “Kursuncu et al.7,8 detailed an initial approach for the Knowledge Infusion Layer for the scenario, which takes place just before the output layer.”