Nettsider med emneord «knowledge graphs»

In this thesis, you will investigate how modern structure-aware machine learning techniques can be applied to practical challenges usually approached using classic symbolic AI techniques. Specifically, you will develop novel algorithms based on graph neural networks (GNNs) for anomaly detection in knowledge graphs, and test them against existing approaches in synthetic and real-life settings.

The types of MSc theses that I could offer fall within three categories:

1. Project specific: the focus is here is in management/analytics of domain specific data (e.g. company information), this means the thesis will focus on specific datasets and will try to obtain insights in various forms from the datasets
2. DataGraft related: the focus here will be to develop/validate generic technology, mostly related to big data scalable solutions for working with large datasets; tasks will be more software design/engineering in nature
3. Data exchange related: the focus here will be to develop/validate technology specifically related to data exchange; tasks will be technologically exploratory, involve some design/engineering work