Why this workshop?

Search engines such as Google, Bing and intelligent assistants such as IBM Watson, Siri and Cortana have demonstrated tremendous benefits to users from consuming data from the knowledge graphs. There are several well-known knowledge graphs such as DBpedia, Wikidata and Schema.org in the consumer space, but very little attention has been given to knowledge graphs in non-consumer space. One such key area where more and more applications are making use of the structured data in the form of knowledge graphs is in the Industrial businesses such as manufacturing, oil and gas, power, aviation and mining. Industrial knowledge graphs can play an important role in creating Artificial Intelligence applications in the Industrial space. There is less focus on such Industrial knowledge graphs in the main track of research conferences. Our goal is to use this workshop as an ideal platform to bridge this gap and bring together researchers and practitioners in the areas of Web Science, knowledge graphs along with Industry subject matter experts.

The aim of this workshop is to bring together people from diverse backgrounds to define and shape the vision of an Industrial knowledge graph by focusing on the following goals:

  • Discussion on the nature of knowledge graphs in an Industrial setting
  • Identify the similarities and differences between consumer oriented and Industrial knowledge graphs
  • Applications of knowledge graph in Industrial setting
  • Provide a platform for discussion among researchers in Web Science, Industrial subject matter experts and knowledge graphs
  • Identify future challenges


The workshop is from 1:00pm to 5:00pm on June 25, 2017. Paper presentations will be for 20 minutes with 15 minutes for presentation and 5 minutes for discussion.

Location: 2nd Floor, Board Room, Franklin Plaza. 4 4th Street, Troy NY 12180 USA. https://goo.gl/maps/FQKJNGzD7PF2

Registration: If you are planning to attend only the workshop, please contact Kathy Fontaine (fontak@rpi.edu) and request her to send you a workshop only registration link. If you plan to attend the entire WebSci'17 conference, please register here: https://websci.tw.rpi.edu/Register.html

1:00 - 1:10 Opening and welcome
1:10 - 2:10 Keynote Talk: Prof. Craig Knoblock (USC). Extracting, Aligning, and Linking Data to Build Knowledge Graphs
2:10 - 2:30 Agniva Banerjee, Raka Dalal, Sudip Mittal and Karuna Joshi. Generating Digital Twin models using Knowledge Graphs for Industrial Production Lines
2:30 - 3:00 Coffe Break
3:00 - 3:30 Invited Talk: Arun Subramaniyan (VP-Data & Analytics, GE Oil & Gas). Title TBD
3:30 - 3:50 Roopteja Muppalla, Sarasi Lalithsena, Tanvi Banerjee and Amit Sheth. A Knowledge Graph Framework for Detecting Traffic Events Using Stationary Cameras
3:50 - 4:10 Sabbir Rashid, Amar Viswanathan, Ian Gross, Elisa Kendall and Deborah McGuinness. Leveraging Semantics for Large-Scale Knowledge Graph Evaluation
4:10 - 4:20 Haklae Kim. Enterprise Knowledge Graph for Consumer Electronics
4:20 - 5:00 Panel Discussion: Industrial Knowledge Graphs: Opportunities and Challenges

Panel Members: Craig Knoblock, University of Southern California; Andy Crapo, GE Global Research; Achille Fokoue, IBM T.J Watson; Evren Sirin, Stardog; Arun Subramaniyan, GE Oil & Gas

Moderator: Justin McHugh, GE Global Research

Keynote Talk: Extracting, Aligning, and Linking Data to Build Knowledge Graphs

There is a huge amount of data spread across the web and stored in databases that we can use to build knowledge graphs. However, exploiting this data to build knowledge graphs is difficult due to the heterogeneity of the sources, scale in the amount of data, and noise in the data. In this talk I will present our approach to building knowledge graphs, including acquiring data from online sources, extracting information from those sources, aligning and linking the data across sources, and building and querying the knowledge graphs at scale. We applied our approach, implemented in a system called DIG, to a number of challenging real-world problems including combating human trafficking by analyzing web ads, identifying illegal arms sales from online marketplaces, and predicting cyber attacks using data extracted from both the open and dark web.

Craig Knoblock is a Research Professor of both Computer Science and Spatial Sciences at the University of Southern California (USC), Research Director at the Information Sciences Institute, and Associate Director of the Informatics Program at USC. He received his Bachelor of Science degree from Syracuse University and his Master’s and Ph.D. from Carnegie Mellon University in computer science. His research focuses on techniques for describing, acquiring, and exploiting the semantics of data. He has worked extensively on source modeling, schema and ontology alignment, entity and record linkage, data cleaning and normalization, extracting data from the Web, and combining these techniques to build knowledge graphs. He has published more than 250 journal articles, book chapters, and conference papers on these topics. Dr. Knoblock is a Fellow of the Association for the Advancement of Artificial Intelligence (AAAI), a Distinguished Scientist of the Association of Computing Machinery (ACM), a Senior Member of IEEE, past President and Trustee of the International Joint Conference on Artificial Intelligence (IJCAI), and winner of the 2014 Robert S. Engelmore Award.

Call for Papers

Topics of interest include, but not limited to:

  • Creation of Industrial knowledge graphs (including handling noisy and incomplete information)
  • Curation of Industrial knowledge graphs (including collaborative maintenance of knowledge graphs)
  • Innovative methods for Industrial experts to query knowledge graphs
  • Innovative methods for Industrial experts to interact with knowledge graphs (e.g., chatbots, voice interfaces)
  • Applications of Industrial knowledge graphs
  • Tools for Industrial experts to populate knowledge graphs
  • Similarities and differences with consumer knowledge graphs such as Google knowledge graph, DBpedia etc.
  • Access control mechanisms for Industrial knowledge graphs
  • Other topics such as reasoning, scalability, privacy etc. as applicable in an Industrial setting
  • Unique challenges faced with and opportunities presented by Industrial knowledge graphs
*** We also encourage submissions related to other types of non-consumer knowledge graphs such as government and enterprise ***

Submission types

  • Full papers up to 6 pages maximum
  • Short (including vision, system) papers up to 4 pages maximum
  • Poster and Demo papers up to 2 page maximum

Submission Instructions

All submissions must be written in English. PDF submissions must be formatted according to the official ACM Proceedings template (http://www.acm.org/publications/proceedings-template). Submit your papers via EasyChair at https://easychair.org/conferences/?conf=industrialkg2017.

Important Dates

Abstract Submission: May 3, 2017 (encouraged but not mandatory)
Full Paper Submission: May 10, 2017
Notifications: June 3, 2017
Camera-Ready Versions: June 9, 2017


Organizing Committee

Program Committee

  • Adila Krisnadhi, Wright State University, USA
  • Alfredo Gabaldon, GE Global Research, USA
  • Craig Knoblock, University of Southern California, USA
  • Freddy Lécué , Accenture Technology Labs, Ireland
  • Geeth R De Mel, IBM Research Center, UK
  • Geetha Manjunath, NIRAMAI, India
  • Jay Pujara, University of California, Santa Cruz, USA
  • Jennifer Sleeman, University of Maryland, Baltimore County, USA
  • Pavan Kapanipathi, IBM T.J Watson Research Center, USA
  • Prajit Das, University of Maryland, Baltimore County, USA
  • Sören Auer, University of Bonn, Germany
  • Steve Gustafson, Maana, USA
  • Zareen Syed, IBM T.J Watson Research Center, USA

Get in touch!