Abstract
RDF2vec is a knowledge graph embedding mechanism which first extracts sequences from knowledge graphs by performing random walks, then feeds those into the word embedding algorithm word2vec for computing vector representations for entities. In this poster, we introduce two new flavors of walk extraction coined e-walks and p-walks, which put an emphasis on the structure or the neighborhood of an entity respectively, and thereby allow for creating embeddings which focus on similarity or relatedness. By combining the walk strategies with order-aware and classic RDF2vec, as well as CBOW and skip-gram word2vec embeddings, we conduct a preliminary evaluation with a total of 12 RDF2vec variants.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
We generated 500 walks per node with a depth of 4, i.e., we perform 4 node hops. All embeddings are trained with a dimensionality of 200. The experiments were performed with jRDF2vec (https://github.com/dwslab/jRDF2Vec), which implements all the different variants used in this paper.
- 2.
- 3.
- 4.
For solving an analogy task like Paris is to France like Berlin is to X, X must be similar to France, as well as related to Berlin.
References
Cochez, M., Ristoski, P., Ponzetto, S.P., Paulheim, H.: Biased graph walks for RDF graph embeddings. In: WIMS, pp. 1–12 (2017)
Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. NIPS 26 (2013)
Pellegrino, M.A., Altabba, A., Garofalo, M., Ristoski, P., Cochez, M.: GEval: a modular and extensible evaluation framework for graph embedding techniques. In: Harth, A., et al. (eds.) ESWC 2020. LNCS, vol. 12123, pp. 565–582. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-49461-2_33
Portisch, J., Heist, N., Paulheim, H.: Knowledge graph embedding for data mining vs. knowledge graph embedding for link prediction–two sides of the same coin? Semantic Web (to appear) (2022)
Portisch, J., Hladik, M., Paulheim, H.: KGvec2go–knowledge graph embeddings as a service. In: LREC 2020, pp. 5641–5647. ELRA (2020)
Portisch, J., Paulheim, H.: Putting RDF2Vec in order. In: ISWC 2021 Posters and Demos (2021)
Ristoski, P., Paulheim, H.: RDF2Vec: RDF graph embeddings for data mining. In: Groth, P., et al. (eds.) ISWC 2016. LNCS, vol. 9981, pp. 498–514. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46523-4_30
Vandewiele, G., et al.: Walk extraction strategies for node embeddings with RDF2Vec in knowledge graphs. In: Workshop on Machine Learning and Knowledge Graphs (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Portisch, J., Paulheim, H. (2022). Walk This Way!. In: Groth, P., et al. The Semantic Web: ESWC 2022 Satellite Events. ESWC 2022. Lecture Notes in Computer Science, vol 13384. Springer, Cham. https://doi.org/10.1007/978-3-031-11609-4_25
Download citation
DOI: https://doi.org/10.1007/978-3-031-11609-4_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-11608-7
Online ISBN: 978-3-031-11609-4
eBook Packages: Computer ScienceComputer Science (R0)