Walk Extraction Strategies for Node Embeddings with RDF2Vec in Knowledge Graphs
This work addresses the need for effective unsupervised node representation techniques in knowledge graphs, offering incremental improvements over existing methods.
The authors tackled the problem of generating node embeddings in knowledge graphs by showing that the Weisfeiler-Lehman kernel does not improve walk embeddings and proposing five alternative walk extraction strategies, with the n-gram strategy performing best on average in node classification tasks.
As KGs are symbolic constructs, specialized techniques have to be applied in order to make them compatible with data mining techniques. RDF2Vec is an unsupervised technique that can create task-agnostic numerical representations of the nodes in a KG by extending successful language modelling techniques. The original work proposed the Weisfeiler-Lehman (WL) kernel to improve the quality of the representations. However, in this work, we show both formally and empirically that the WL kernel does little to improve walk embeddings in the context of a single KG. As an alternative to the WL kernel, we propose five different strategies to extract information complementary to basic random walks. We compare these walks on several benchmark datasets to show that the \emph{n-gram} strategy performs best on average on node classification tasks and that tuning the walk strategy can result in improved predictive performances.