Data Management Seminar: Synergy of Graph Data Management and Machine Learning in Explainability and Query Answering

Content

Abstract: Graph data, e.g., social and biological networks, financial transactions, knowledge graphs, and transportation systems are pervasive in the natural world, where nodes are entities with features, and edges denote relations  among  them.  Machine  learning  and  recently, graph  neural  networks become ubiquitous,  e.g.,  in cheminformatics,  bioinformatics, fraud  detection,  question answering, and recommendation  over knowledge  graphs. In  this  talk, I  shall  introduce  our  ongoing  works  about  the synergy of graph data management and graph machine learning in the context of graph neural network explainability and  query  answering.  In  the  first  direction, I  shall  discuss  how  data  management techniques can assist  in  generating  user-friendly,  configurable,  queryable, and  robust explanations for graph neural networks.  In the second direction, I  shall  provide an overview of our  user-friendly, deep learning-based, scalable techniques and systems for querying knowledge graphs.