• Corpus ID: 236976234

Putting RDF2vec in Order

  title={Putting RDF2vec in Order},
  author={Jan Portisch and Heiko Paulheim},
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. 

Figures and Tables from this paper

Walk this Way! Entity Walks and Property Walks for RDF2vec

Two newavors of walk extraction coined e-walks and p-Walks are introduced, which put an emphasis on the structure or the neighborhood of an entity respec-tively, and thereby allow for creating embeddings which focus on similarity or relatedness.

Ontology Matching Through Absolute Orientation of Embedding Spaces

A novel structure-based mapping approach which is based on knowledge graph embeddings: the ontologies to be matched are embedded, and an approach known as absolute orientation is used to align the two embedding spaces.

Knowledge graph embedding for data mining vs. knowledge graph embedding for link prediction - two sides of the same coin?

This paper argues that both Knowledge Graph Embeddings tasks are actually related, and shows that the first family of approaches can also be used for the second task and vice versa, and provides a comparison of both families of approaches.

pyRDF2Vec: A Python Implementation and Extension of RDF2Vec

A Python software package that reimplements the well-known RDF2Vec algorithm along with several of its extensions, and best practices in terms of code styling, testing, and documentation were applied such that the package is future-proof as well as to facilitate external contributions.



Global RDF Vector Space Embeddings

This paper shows how the idea of global embeddings can be transferred to RDF embeddeddings, and shows that the results are competitive with traditional local techniques like RDF2Vec.

More is not Always Better: The Negative Impact of A-box Materialization on RDF2vec Knowledge Graph Embeddings

It is argued that despite the huge body of work devoted on completing missing information in knowledge graphs, such missing implicit information is actually a signal, not a defect, and it is demonstrated that the materialization before computing embeddings actually has a negative effect on the performance of RDF2vec.

Walk Extraction Strategies for Node Embeddings with RDF2Vec in Knowledge Graphs

This work proposes five different strategies to extract information complementary to basic random walks and shows 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.

RDF2Vec Light - A Lightweight Approachfor Knowledge Graph Embeddings

RDF2Vec Light is presented, a lightweight embedding approach based on RDF2 Vec which generates vectors for only a subset of entities which allows the application of embeddings of very large knowledge graphs in scenarios where such embedDings were not possible before due to a significantly lower runtime and significantly reduced hardware requirements.

RDF2Vec: RDF graph embeddings and their applications

RDF2Vec is presented, an approach that uses language modeling approaches for unsupervised feature extraction from sequences of words, and adapts them to RDF graphs that shows that the proposed entity embeddings outperform existing techniques, and that pre-computed 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

The RDF2Vec approach is extended, which leverages language modeling techniques for unsupervised feature extraction from sequences of entities, and sequences are generated by exploiting local information from graph substructures, harvested by graph walks, and learn latent numerical representations of entities in RDF graphs.

Two/Too Simple Adaptations of Word2Vec for Syntax Problems

We present two simple modifications to the models in the popular Word2Vec tool, in order to generate embeddings more suited to tasks involving syntax. The main issue with the original models is the

GEval: A Modular and Extensible Evaluation Framework for Graph Embedding Techniques

GEval, an evaluation framework to simplify the evaluation and the comparison of graph embedding techniques, is proposed by detailing its overall structure, the already implemented tasks, and how to extend it.

A Collection of Benchmark Datasets for Systematic Evaluations of Machine Learning on the Semantic Web

A collection of 22 benchmark datasets of different sizes can be used to conduct quantitative performance testing and systematic comparisons of approaches for machine learning on the Semantic Web.

KG-BERT: BERT for Knowledge Graph Completion

This work treats triples in knowledge graphs as textual sequences and proposes a novel framework named Knowledge Graph Bidirectional Encoder Representations from Transformer (KG-BERT) to model these triples.