2015/06/03 by Kelvin Guu, Guu, Kelvin, J. J. Miller +3 · 2 citations
Computer Science · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Databases (cs.DB) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (stat.ML) #Topic Modeling
paper · pdf · doi:10.48550/arxiv.1506.01094
openalex publication_date 2015/06/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01
Path queries on a knowledge graph can be used to answer compositional questions such as "What languages are spoken by people living in Lisbon?". However, knowledge graphs often have missing facts (edges) which disrupts path queries. Recent models for knowledge base completion impute missing facts by embedding knowledge graphs in vector spaces. We show that these models can be recursively applied to answer path queries, but that they suffer from cascading errors. This motivates a new "compositional" training objective, which dramatically improves all models' ability to answer path queries, in some cases more than doubling accuracy. On a standard knowledge base completion task, we also demonstrate that compositional training acts as a novel form of structural regularization, reliably improving performance across all base models (reducing errors by up to 43%) and achieving new state-of-the-art results.