TRIPODS Winter School & Workshop- Jure Leskovec
Abstract– Answering complex logical queries on large-scale knowledge graphs is a fundamental yet challenging task. In this I will give an overview of using vector space embeddings for performing logical reasoning in knowledge graphs. First, I will talk about knowledge graph completion method that predicts relations between a pair of entities by: Considering the Relational Context of each entity by capturing the relation types adjacent to the entity and modeled through a novel edge-based message passing scheme; Considering the Relational Paths capturing all paths between the two entities; And, adaptively integrating the Relational Context and Relational Path through a learnable attention mechanism. Second, we will also discuss QUERY2BOX, an embedding-based framework for reasoning over arbitrary queries with and, or and existential operators in massive and incomplete KGs. Our main insight is that queries can be embedded as boxes (i.e., hyper-rectangles), where a set of points inside the box corresponds to a set of answer entities of the query. We show that conjunctions can be naturally represented as intersections of boxes and also prove a negative result that handling disjunctions would require embedding with dimension proportional to the number of KG entities.