Not all Embeddings are created Equal: Extracting Entity-specific Substructures for RDF Graph Embedding
This work addresses the issue of biased representations in knowledge graphs for entity recommendation, though it is incremental as it builds on existing random walk methods.
The paper tackled the problem of extracting relevant substructures for RDF graph embeddings by proposing specificity as a measure to identify entity-specific nodes and edges, and showed that this approach outperforms state-of-the-art methods in entity recommendation tasks on DBpedia.
Knowledge Graphs (KGs) are becoming essential to information systems that require access to structured data. Several approaches have been recently proposed, for obtaining vector representations of KGs suitable for Machine Learning tasks, based on identifying and extracting relevant graph substructures using uniform and biased random walks. However, such approaches lead to representations comprising mostly "popular", instead of "relevant", entities in the KG. In KGs, in which different types of entities often exist (such as in Linked Open Data), a given target entity may have its own distinct set of most "relevant" nodes and edges. We propose specificity as an accurate measure of identifying most relevant, entity-specific, nodes and edges. We develop a scalable method based on bidirectional random walks to compute specificity. Our experimental evaluation results show that specificity-based biased random walks extract more "meaningful" (in terms of size and relevance) RDF substructures compared to the state-of-the-art and, the graph embedding learned from the extracted substructures, outperform existing techniques in the task of entity recommendation in DBpedia.