Putting RDF2vec in Order
This addresses a shortcoming in knowledge graph embeddings for tasks with diverse entity classes, but it is incremental as it builds on existing methods.
The paper tackled the problem of RDF2vec's context-agnostic nature by using an order-aware word2vec variant, resulting in considerable performance gains, especially on tasks involving entities of different classes.
The RDF2vec method for creating node embeddings on knowledge graphs is based on word2vec, which, in turn, is agnostic towards the position of context words. In this paper, we argue that this might be a shortcoming when training RDF2vec, and show that using a word2vec variant which respects order yields considerable performance gains especially on tasks where entities of different classes are involved.