Masterclass: Graph Embedding Techniques - Matrix Factorization to Deep Learning
KGC 2023 | Masterclasses
•
1h 30m
Graph embeddings can be used for a variety of applications, including recommendation, fraud detection, and other machine learning tasks. In this work, we aim to walk through various different embedding techniques, starting with spectral approaches, moving towards graph neural networks, and finally newer, inductive techniques such as NodePiece. Throughout the tutorial, we will be implementing algorithms using the (open-source) TigerGraph Machine Learning Workbench, a tool for easily training machine learning algorithms on large-scale graph datasets. Using a variety of datasets, we will discuss the pros and cons of each technique, demonstrate them working, and examine future directions for the field of graph embedding research from the lens of industry.
Up Next in KGC 2023 | Masterclasses
-
Masterclass: The Open KG Curriculum
This master class will contain international experts on knowledge engineering and will detail their experiences, lessons learned, and best practices in how they have and currently teach their students and educate their workforce on knowledge graph concepts. The masterclass will be implemented as ...
-
Masterclass: SPARQL, SHACL and XSLT3
XSLT3 is a powerful tool for transformations, one that's often underutilized in the RDF space. However, the combination of SPARQL, SHACL and XSLT3 together provides a comprehensive tool for transformation of semantic content that can complement existing capabilities such as SPARQL UPDATE, enablin...
-
Masterclass: Graphs with Relational T...
The tussle between graph databases vs. relational databases is misplaced and hinders wider adoption of graph databases. Many graph databases bring tremendous value, but at the cost of the bread and butter data management issues that relational databases are extremely good at. If the two can co-ex...
