Walk this Way! Entity Walks and Property Walks for RDF2vec

TL;DR

This paper introduces two new walk strategies, e-walks and p-walks, for RDF2vec knowledge graph embeddings, emphasizing structure and neighborhood to improve entity similarity and relatedness representations.

Contribution

It presents novel walk extraction methods for RDF2vec that focus on structural and neighborhood information, enhancing embedding quality.

Findings

Multiple RDF2vec variants evaluated with promising results.

Walk strategies improve focus on similarity and relatedness.

Preliminary evaluation shows potential benefits of new walk types.

Abstract

RDF2vec is a knowledge graph embedding mechanism which first extracts sequences from knowledge graphs by performing random walks, then feeds those into the word embedding algorithm word2vec for computing vector representations for entities. In this poster, we introduce two new flavors of walk extraction coined e-walks and p-walks, which put an emphasis on the structure or the neighborhood of an entity respectively, and thereby allow for creating embeddings which focus on similarity or relatedness. By combining the walk strategies with order-aware and classic RDF2vec, as well as CBOW and skip-gram word2vec embeddings, we conduct a preliminary evaluation with a total of 12 RDF2vec variants.