First International Workshop on

Scaling Knowledge Graphs for Industry

Co-located with 20th International Conference on Semantic Systems (SEMANTICS) - Amsterdam, Sept. 17-19, 2024

Workshop on 17 September 2024

Knowledge Graphs have been used in industrial settings for many years -- for data integration or/and storage, democratization of data-access, easy data-exchange, information retrieval tasks, etc. However, we identify the lack of scalable solutions as the main blocker for uptake in more use cases.

In this workshop, we want to foster discussion on making knowledge graph systems work at industrial scale. We explicitly do not want to limit this discussion to how much data we can store and query (this is already pretty much working), but we would also like to address other scalability aspects such as knowledge modeling (scaling the design of KGs or ontologies), processing, streaming, and ingestion of large amounts of information into a knowledge graph systems.

We invite to join our workshop Knowledge Graph practitioners and researchers who would like to discuss what is the state of the art with KG adoption, what hampers it, what industries are more natural for KGs and why, and what we can do to further promote the scaling of KGs in industry.

KEYNOTE SPEAKERS

Felix Sasaki

Felix Sasaki is Chief Expert for Knowledge Graphs and Semantic Technology to the Business AI Unit at SAP. He owns a PhD exploring linguistic data modeling and has worked at the World Wide Web Consortium (W3C) on standardization in the realm of data and language, at the DFKI (German Research Center for Artificial Intelligence) within German and European research projects on language technology, and in various German companies on data and knowledge architecture. In late 2021, Felix joined SAP where he drives the architecture of semantically powered AI.

Talk: Knowledge Graphs for Business AI

Agenda

10:30 - 10:40: Welcome
Evgeny Kharlamov and Michael Cochez

10:40 - 10:55

Title: Scaling Semantic Graph Data Management

Authors: Renato Iannella, Triples

10:55 - 11:10

Title: Enhanced and Scalable RDF Validation Techniques for Dataspaces

Authors: Paul Moosmann, Fraunhofer

11:10 - 11:30

Title: EU Projects take on Scaling Data Ingestion to Processing with enRichMyData's and GraphMassivizer

Authors: Evgeny Kharlamov, Martino Pulici on enRichMyData and Mikel Mendibe, Antonios Klironomos on GraphMassivizer, Bosch Center for AI

11:30 - 11:45

Title: Scaling Financial Data with KGs

Authors: Haleh Dizaji, Uni Klagenfurt

11:45 - 12:00

Title: Scaling Scientific Knowledge Discovery in Industry with Neuro-Symbolic AI

Authors: Wilma Schmidt, Bosch Center for AI

12:00 - 13:00: Lunch

13:00 – 14:30 Panel:

Topic: Reality Check for Industrial KGs - Dream vs Reality

Panelists:

Amazon - Alon Halevy, Senior Principal Applied Scientist
eccenca - Stefan Reinhardt, Chief Sales Officer
Metaphacts - Thomas Kaminski, Knowledge Graphs Solutions Engineer
SAP - Felix Sasaki, Chief Expert for KG and Semantic Technology
Siemens - Martin Sjarov, Data Engineer
Triply - Evelien Lantman, CEO

Moderators:

Bosch - Evgeny Kharlamov, Senior Expert
VU Amsterdam - Michael Cochez, Assistant Professor

Abstract: (click to expand)

Panel vision:

We would like to bring together researchers and industry representatives: (1) technology providers (of semantic solutions) such as SAP and (2) semantic technology consumers such as Siemens. We claim that is still a gap between what research and technology providers offer to industry today and the actual industrial needs or the technology consumers do not have enough understanding of what the existing semantic technology can actually offer thus the uptake of semantics in industry is not at the satisfactory scale. During the panel we plan to discuss whether such gap indeed exists and how to mitigate it.

Panel format:

Each panelist gives a 5 min pitch with the view on the panel's topic
Then, we will have 1h for question answering and discussions (questions from panelists to each other, questions from the audience, questions from the moderators).

14:30 - 15:00: Coffee break

15:00 - 15:45: Keynote 1: by Felix Sasaki, Chief Expert for KG and Semantic Technology, SAP

Title: Knowledge Graphs for Business AI (click to expand to see the abstract)

Abstract: We will discuss how SAP uses knowledge graphs to build generative AI solutions and dive into the first knowledge graph solution developed for one of the generative AI scenarios. We will explain how knowledge graphs are used in concrete, but still experimental use cases and how we advance the state-of-the-art technologies to combine LLMs and knowledge graphs. We will also touch upon our vision on evolving knowledge graphs for all generative AI solutions at SAP

15:45- 16:00

Title: Knowledge Graphs for AI: From RAG to Graph RAG

Authors: Tuana Celik, Deepset

16:00 - 16:15

Title: Running 100,000,000,000+ triples in production with TriplyDB

Authors: Wouter Beek, Triply

16:15 - 16:30: Coffee break

Topics

The topics of interest of our workshop include but are not limited to the following:

Scalable processing of large Knowledge Graphs
Knowledge Graphs meet Streaming Data
Time series in Knowledge Graphs
Data imputation in Knowledge graphs
Scaling machine learning with KGs
Scaling reasoning with KGs
Knowledge search and discovery
...

The topics of interest of our workshop include but are not limited to the following:

Scalable processing of large Knowledge Graphs
Knowledge Graphs meet Streaming Data
Time series in Knowledge Graphs
Data imputation in Knowledge graphs
Scaling machine learning with KGs
Scaling reasoning with KGs
Knowledge search and discovery
...

Organizers

Michael Cochez, Vrije Universiteit, Amsterdam, Netherlands

Evgeny Kharlamov, Bosch Center for AI / University of Oslo, Germany

Radu Prodan, Alpen-Adria-University Klagenfurt, Austria