Temporal Scope Prediction using Graph Neural Networks

Project description

A knowledge graph is a data structure designed to encapsulate knowledge through interconnected nodes and edges. Nodes encapsulate descriptions of entities, while edges represent the relationships between these entities.  With its ability to express nuanced semantics, knowledge graphs empower AI applications to execute various use cases such as question answering, semantic search, recommendations, language understanding, and advanced analytics. Temporal knowledge graphs are graphs that have temporal features and are considered ever-evolving or dynamic knowledge graphs.  Consider an example,  Obama was awarded noble prize in 2015. This information can be captured as an event in a knowledge graph (Obama, awarded, noble-peace-prize, 2015). This project involved the use of existing Graph Neural Network-based techniques to generate temporal knowledge graph embeddings and use them in downstream applications for temporal scope prediction tasks.    

Note: You need to register interest in projects from different supervisors (not a number of projects with the one supervisor).
You must also contact each supervisor directly to discuss both the project details and your suitability to undertake the project.