2020/02/06 by Daniel Daza, Michael Cochez, Daza, Daniel +1 · 5 citations
Computer Science · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #Artificial intelligence #Computation and Language (cs.CL) #Computer science #Domain Adaptation and Few-Shot Learning #ENCODE #Embedding #FOS: Computer and information sciences #Generality #Graph #Information retrieval #Machine Learning (cs.LG) #Representation (politics) #Sargable #Search engine #Set (abstract data type) #Theoretical computer science #Topic Modeling #Web search query #cs.AI #cs.CL #cs.LG
paper · pdf · doi:10.48550/arxiv.2002.02406
published in arXiv (Cornell University) (Cornell University) · Presented at ICML 2020 - GRL+ Workshop
openalex publication_date 2020/02/06 · arxiv created 2020/06/24 · arxiv updated 2020/06/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Recent works on representation learning for Knowledge Graphs have moved beyond the problem of link prediction, to answering queries of an arbitrary structure. Existing methods are based on ad-hoc mechanisms that require training with a diverse set of query structures. We propose a more general architecture that employs a graph neural network to encode a graph representation of the query, where nodes correspond to entities and variables. The generality of our method allows it to encode a more diverse set of query types in comparison to previous work. Our method shows competitive performance against previous models for complex queries, and in contrast with these models, it can answer complex queries when trained for link prediction only. We show that the model learns entity embeddings that capture the notion of entity type without explicit supervision.