MSc Thesis Proposal of Regina Khalil:"Guided Rotational-based Graph Embeddings using Path-Ranking Methods for Error Detection in Noisy Knowledge Graphs "

 

Date: Monday, December 19th, 2022 

Time: 11:00 am – 12:30 pm 

Location: Essex Hall, Room 122 

 

Knowledge graphs (KGs) use triples to describe real-world facts. It has seen widespread use in intelligent analysis and applications. However, the automatic construction process of KGs unavoidably introduces possible noises and errors. Furthermore, KG-based tasks and applications assume that the knowledge in the KG is entirely correct, which leads to potential deviations. Error detection is critical in knowledge graphs, where errors are rare but significant. Various error detection methodologies, primarily path ranking (PR) and representation learning have been proposed to address this issue. Our method (EPRGE) is an improved version of an existing model, Path Ranking Guided Embedding (PRGE), in which they use path-ranking confidence scores to guide TransE embeddings. To improve PRGE, we use a rotational-based embedding model (RotatE) instead of TransE, which uses a self-adversarial negative sampling technique to train the model efficiently and effectively. EPRGE, unlike PRGE, avoids generating meaningless false triples during training by employing the self-adversarial negative sampling method. We compare various methods on two benchmark datasets, demonstrating the potential of our approach and providing enhanced insights on graph embeddings when dealing with noisy Knowledge Graphs. 

 

Keywords: Knowledge Graph, Knowledge Graph Embedding, Error Detection, Path Ranking

 

Internal Reader: Dr. Kalyani Selvarajah   

External Reader: Dr. Mohammad Hassanzadeh   

Advisor: Dr. Ziad Kobti