Search

Skip to Search Results
  • Fall 2021

    Ranganathan, Varun

    notoriously incomplete, giving rise to a large crop of reasoning tools for the task of Link Prediction, aimed at finding missing links in the graph based on structural regularities in the graph. Among the many LP methods, those based on embeddings have become prevalent in the literature. In particular, multi

    \HOPLOP, whose main predicate is to perform ``traversals'' on the embedding space instead of the KG itself. We show how to train and tune our method, and report on experiments with different representative embedding-based LP methods on many benchmarks, showing that \HOPLOP improves each LP method on its

1 - 1 of 1