Title: Evolving Meaning for supervised learning in complex biomedical domains using knowledge graphs
Speaker: Rita Sousa, LASIGE – DI/FCUL
When: Wednesday, May 19th, 17h45
Short summary: Knowledge graphs represent an unparalleled opportunity for machine learning, given their ability to provide meaningful context to data through semantic representations. Knowledge graphs provide multiple perspectives over an entity, describing it using different properties or multiple portions of the graph. State-of-the-art semantic representations are static and consider all semantic aspects, ignoring that some may be irrelevant to the downstream learning task. This Ph.D. project aims to discover suitable semantic representations of knowledge graph entities adapted to specific supervised learning tasks. The developed approaches will be applied to two bioinformatics tasks, prediction of protein interactions and gene-disease associations.
Short Bio: Rita completed the MSc in bioinformatics at FCUL in 2019, where her master thesis was focused on improving knowledge graph-based representations for protein-protein interaction prediction. She is currently in the 2nd year of the Ph.D. in Informatics under the supervision of Cátia Pesquita and Sara Silva. Her research areas include Biomedical knowledge Graphs, Semantic Similarity, Graph Embeddings, and Data Mining.