The Knowledge Graph for End-to-End Learning on Heterogeneous Knowledge

Research output: Contribution to ConferencePosterAcademic

45 Downloads (Pure)

Abstract

In modern machine learning,raw data is the preferred input for our models. Where a decade ago data scientists were still engineering features, manually picking out the details we thought salient, they now prefer the data in their raw form. As long as we can assume that all relevant and irrelevant information is present in the input data, we can design deep models that build up intermediate representations to sift out relevant features. However, these models are often domain specific and tailored to the task at hand, and therefore unsuited for learning on heterogeneous knowledge: information of different types and from different domains. If we can develop methods that operate on this form of knowledge, we can dispense with a great deal more ad-hoc feature engineering and train deep models end-to-end in many more domains. To accomplish this, we first need a data model capable of expressing heterogeneous knowledge naturally in various domains, in as usable a form as possible, and satisfying as many use cases as possible. We argue that the knowledge graph is a suitable candidate for this data model. We further discuss some of the promises and challenges of this approach, and how we are currently broadening our efforts to multi-modal knowledge graphs.
Original languageEnglish
Publication statusPublished - 19 Mar 2018
EventICT Open 2018: The interface for Dutch ICT research - Flint Theatre, Amersfoort, Netherlands
Duration: 19 Mar 201820 Mar 2018
http://www.ictopen.nl/

Conference

ConferenceICT Open 2018
Abbreviated titleICT Open
Country/TerritoryNetherlands
CityAmersfoort
Period19/03/1820/03/18
Internet address

Keywords

  • Knowledge Graphs
  • End-to-End Learning
  • Heterogeneous Knowledge
  • Multimodal Embeddings

Fingerprint

Dive into the research topics of 'The Knowledge Graph for End-to-End Learning on Heterogeneous Knowledge'. Together they form a unique fingerprint.

Cite this