Document Type

Conference Proceeding

Subject Area(s)

artificial intelligence


Learning the underlying patterns in data goes beyondinstance-based generalization to external knowledge repre-sented in structured graphs or networks. Deep learning thatprimarily constitutes neural computing stream in AI hasshown significant advances in probabilistically learning la-tent patterns using a multi-layered network of computationalnodes (i.e., neurons/hidden units). Structured knowledge thatunderlies symbolic computing approaches and often supportsreasoning, has also seen significant growth in recent years,in the form of broad-based (e.g., DBPedia, Yago) and do-main, industry or application specific knowledge graphs. Acommon substrate with careful integration of the two willraise opportunities to develop neuro-symbolic learning ap-proaches for AI, where conceptual and probabilistic repre-sentations are combined. As the incorporation of externalknowledge will aid in supervising the learning of features forthe model, deep infusion of representational knowledge fromknowledge graphs within hidden layers will further enhancethe learning process. Although much work remains, we be-lieve that knowledge graphs will play an increasing role in de-veloping hybrid neuro-symbolic intelligent systems (bottom-up deep learning with top-down symbolic computing) as wellas in building explainable AI systems for which knowledgegraphs will provide scaffolding for punctuating neural com-puting. In this position paper, we describe our motivation forsuch a neuro-symbolic approach and framework that com-bines knowledge graph and neural networks.

APA Citation

Kursuncu, U., Gaur, M., & Sheth, A. (2020). Knowledge infused learning (K-IL): Towards deep incorporation of knowledge in deep learning. Proceedings of the AAAI 2020 Spring Symposium on Combining Machine Learning and Knowledge Engineering in Practice (AAAI-MAKE).