RDF2Vec: RDF Graph Embeddings for Data Mining

Abstract

Abstract. Linked Open Data has been recognized as a valuable source for background information in data mining. However, most data mining tools require features in propositional form, i.e., a vector of nominal or numerical features associated with an instance, while Linked Open Data sources are graphs by nature. In this paper, we present RDF2Vec, an approach that uses language modeling approaches for unsupervised feature extraction from sequences of words, and adapts them to RDF graphs. We generate sequences by leveraging local information from graph substructures, harvested by Weisfeiler-Lehman Subtree RDF Graph Kernels and graph walks, and learn latent numerical representations of entities in RDF graphs. Our evaluation shows that such vector representations outperform existing techniques for the propositionalization of RDF graphs on a variety of different predictive machine learning tasks, and that feature vector representations of general knowledge graphs such as DBpedia and Wikidata can be easily reused for different tasks.

Biased graph walks for RDF graph embeddings

“…Our results in [36] have shown that random walks are a feasible and, in contrast to other techniques such as kernels, also a well scalable approach for extracting sequences.…”

“…We will introduce both brie y. A more elaborated discussion can be found from the original RDF2Vec paper [36].…”

“…In [36], we have introduced RDF2Vec, a generic method for embedding entities in knowledge graphs into lower-dimensional vector spaces. e approach adapts neural language modeling techniques, speci cally word2vec, which takes sequences of words to embed words into vector spaces [20,21].…”

The knowledge graph as the default data model for learning on heterogeneous knowledge

“…RDF2Vec [29] is a method which generates feature vectors of a given size, and does so efficiently, even for large graphs. This means that, in principle, even when faced with a machine learning problem on the scale of the web, we can reduce the problem to a set of feature vectors of, say, 500 dimensions, after which we can solve the problem on commodity hardware.…”

Towards Lexical Chains for Knowledge-Graph-basedWord Embeddings

“…The corpora that the algorithms are trained on can contain either natural language text (e.g. Wikipedia or newswire articles) or artificiallygenerated pseudo corpora, such as the output of the Random Walk on Graphs algorithm, when run to select sequences of nodes from a knowledge graph (KG) -see (Goikoetxea et al, 2015) and (Ristoski and Paulheim, 2016). We denote the pseudo corpus generated via Random Walk on Graphs algorithm as Pseudo Corpus RWG.…”