Ying Ding | Katana Graph Solutions: Scalable Graph Search & Graph Mining
KGC 2021
•
21m
When knowledge graphs in your company get larger and larger, a scalable graph search is in high demand. In the current graph search solutions, scalability is still a big issue. Furthermore, with the fast development of deep learning on graphs, many companies rely on deep learning methods to mine insights from the ever-increasing knowledge graphs. But search and mining are usually not available in one package. This presentation will showcase the scalable solutions from Katana Graph which provide the end-to-end solutions for graph search and mining. It is ten times faster than the current market solutions and scales exponentially on graphs with billions or even trillions of nodes. It provides weighted k-shorted path searches and cutting edge graph deep learning methods (such as cluster-graph convolutional neural network, graph attention model, and graph transformer). Katana Graph is a start-up company founded by several faculty from University of Texas at Austin with the goal to provide the scalable graph search and deep graph mining in one click. In this presentation, we will showcase several use cases, such as searching and mining large scale knowledge graphs in drug discovery.
Up Next in KGC 2021
-
Olaf Hartig | RDF Star: Metadata For ...
The lack of a convenient way to capture annotations and statements about individual RDF triples has been a long standing issue for RDF. Such annotations are a native feature in other contemporary graph data models (e.g., edge properties in the Property Graph model). In recent years, the RDF* app...
-
Jan Hidders | A Report From The Prope...
The Property Graph Schema Working Group (PGSWG) is an informal working group that was set up in 2018 under the umbrella of LDBC, the Linked Data Benchmark Council, to support the formal working group that works on the SQL/PGQ and GQL, the upcoming ISO/IEC standards for managing property graphs. T...
-
Abhishek Mittal | Re-Imagining Regula...
Content Enrichment: Development and deployment of a 5-stage taxonomy. Applying the taxonomy to tag regulations and classify them for improved discovery & work assignment.
Smart Authoring: Leveraging advanced NLP and ML techniques to learn from the past content authoring for identification of ...
