• Corpus ID: 221397130

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

@article{Iana2020MoreIN,
  title={More is not Always Better: The Negative Impact of A-box Materialization on RDF2vec Knowledge Graph Embeddings},
  author={Andreea Iana and Heiko Paulheim},
  journal={ArXiv},
  year={2020},
  volume={abs/2009.00318}
}
RDF2vec is an embedding technique for representing knowledge graph entities in a continuous vector space. In this paper, we investigate the effect of materializing implicit A-box axioms induced by subproperties, as well as symmetric and transitive properties. While it might be a reasonable assumption that such a materialization before computing embeddings might lead to better embeddings, we conduct a set of experiments on DBpedia which demonstrate that the materialization actually has a… 

Figures and Tables from this paper

Putting RDF2vec in Order

It is shown that using a word2vec variant which respects order yields considerable performance gains especially on tasks where entities of different classes are involved.

Discovering alignment relations with Graph Convolutional Networks: A biomedical case study

It is proposed to match nodes within a knowledge graph by (i) learning node embeddings with Graph Convolutional Networks such that similar nodes have low distances in the embedding space, and (ii) clustering nodes based on their embedDings, in order to suggest alignment relations between nodes of a same cluster.

Knowledge Graph Embeddings for News Article Tag Recommendation

This paper introduces the Newsadoo tag recommendation system, which consists of three components: item-based similarity, knowledge graph similarity, and actuality, and describes the knowledge graph component in more detail.

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.

References

SHOWING 1-10 OF 18 REFERENCES

Towards Exploiting Implicit Human Feedback for Improving RDF2vec Embeddings

RDF2vec utilizing transition probabilities between pages in Wikipedia are used as a proxy for the human feedback for the importance of an edge and it is shown that in some scenarios, RDF1vec utilizing those transition probabilities can outperform both RDF 2vec based on random walks as well as the usage of graph internal edge weights.

KGvec2go – Knowledge Graph Embeddings as a Service

KGvec2go, a Web API for accessing and consuming graph embeddings in a light-weight fashion in downstream applications, is presented and it is shown that the trained models have semantic value by evaluating them on multiple semantic benchmarks.

Support and Centrality: Learning Weights for Knowledge Graph Embedding Models

A data-driven approach to measure the information content of each triple with respect to the whole knowledge graph by using rule mining and PageRank is proposed and shown how to compute triple-specific weights to improve the performance of three KG embedding models (TransE, TransR and HolE).

Extracting entity-specific substructures for RDF graph embeddings

This work proposes specificity as an accurate measure of identifying most relevant, entity-specific, nodes and edges in Knowledge Graphs and develops a scalable method based on bidirectional random walks to compute specificity.

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.

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.

RDF2Vec: RDF Graph Embeddings for Data Mining

RDF2Vec is presented, an approach that uses language modeling approaches for unsupervised feature extraction from sequences of words, and adapts them to RDF graphs, and shows that feature vector representations of general knowledge graphs such as DBpedia and Wikidata can be easily reused for different tasks.

A Configurable Evaluation Framework for Node Embedding Techniques

This work presents the design and implementation of a ready to use evaluation framework to simplify the node embedding technique testing phase and provides tests range from ML tasks, semantic tasks to semantic analogies.

Knowledge Graphs on the Web - an Overview

This chapter provides an overview and comparison of those publicly available knowledge graphs, and gives insights into their contents, size, coverage, and overlap.

Serving DBpedia with DOLCE - More than Just Adding a Cherry on Top

It is shown that by aligning the DBpedia ontology to the foundational ontology DOLCE-Zero, and by combining reasoning and clustering of the reasoning results, errors affecting millions of statements can be identified at a minimal workload for the knowledge base designer.