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

Ristoski, Petar; Vries, Gerben Klaas Dirk de; Paulheim, Heiko

doi:10.1007/978-3-319-46547-0_20

Cited by 65 publications

(67 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Datasets We evaluate our model on four datasets 3 in Resource Description Framework (RDF) format (Ristoski, de Vries, and Paulheim 2016): AIFB, MUTAG, BGS, and AM. Relations in these datasets need not necessarily encode directed subject-object relations, but are also used to encode the presence, or absence, of a specific feature for a given entity.…”

Section: Entity Classification Experimentsmentioning

confidence: 99%

“…The exact statistics of the datasets can be found in Table 1. For a more detailed description of the datasets the reader is referred to Ristoski, de Vries, and Paulheim (2016). We remove relations that were used to create entity labels: employs and affiliation for AIFB, isMutagenic for MUTAG, hasLithogenesis for BGS, and objectCategory and material for AM.…”

Section: Entity Classification Experimentsmentioning

confidence: 99%

See 1 more Smart Citation

Modeling Relational Data with Graph Convolutional Networks

Schlichtkrull

Kipf

Bloem

et al. 2018

Lecture Notes in Computer Science

3,566

2,259

View full text Add to dashboard Cite

Knowledge graphs enable a wide variety of applications, including question answering and information retrieval. Despite the great effort invested in their creation and maintenance, even the largest (e.g., Yago, DBPedia or Wikidata) remain incomplete. We introduce Relational Graph Convolutional Networks (R-GCNs) and apply them to two standard knowledge base completion tasks: Link prediction (recovery of missing facts, i.e. subject-predicate-object triples) and entity classification (recovery of missing entity attributes). R-GCNs are related to a recent class of neural networks operating on graphs, and are developed specifically to deal with the highly multi-relational data characteristic of realistic knowledge bases. We demonstrate the effectiveness of R-GCNs as a stand-alone model for entity classification. We further show that factorization models for link prediction such as DistMult can be significantly improved by enriching them with an encoder model to accumulate evidence over multiple inference steps in the relational graph, demonstrating a large improvement of 29.8% on FB15k-237 over a decoder-only baseline.

show abstract

Section: Entity Classification Experimentsmentioning

confidence: 99%

Section: Entity Classification Experimentsmentioning

confidence: 99%

Modeling Relational Data with Graph Convolutional Networks

Schlichtkrull

Kipf

Bloem

et al. 2018

Lecture Notes in Computer Science

3,566

2,259

View full text Add to dashboard Cite

show abstract

“…We use the entity embeddings on ve di erent datasets from di erent domains, for the tasks of classi cation and regression [34].…”

Section: Datasetsmentioning

confidence: 99%

Biased graph walks for RDF graph embeddings

Cochez

Ristoski

Ponzetto

et al. 2017

Proceedings of the 7th International Conference on Web Intelligence, Mining and Semantics

Self Cite

View full text Add to dashboard Cite

Knowledge Graphs have been recognized as a valuable source for background information in many data mining, information retrieval, natural language processing, and knowledge extraction tasks. However, obtaining a suitable feature vector representation from RDF graphs is a challenging task. In this paper, we extend the RDF2Vec approach, which leverages language modeling techniques for unsupervised feature extraction from sequences of entities. We generate sequences by exploiting local information from graph substructures, harvested by graph walks, and learn latent numerical representations of entities in RDF graphs. We extend the way we compute feature vector representations by comparing twelve di erent edge weighting functions for performing biased walks on the RDF graph, in order to generate higher quality graph embeddings. We evaluate our approach using di erent machine learning, as well as entity and document modeling benchmark data sets, and show that the naive RDF2Vec approach can be improved by exploiting Biased Graph Walks.

show abstract

“…More details about the evaluation datasets and how the datasets were generated are presented in [28].…”

Section: Datasetsmentioning

confidence: 99%

RDF2Vec: RDF Graph Embeddings for Data Mining

Ristoski

Paulheim

2016

Lecture Notes in Computer Science

Self Cite

308

266

View full text Add to dashboard Cite

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.

show abstract

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

Cited by 65 publications

References 14 publications

Modeling Relational Data with Graph Convolutional Networks

Modeling Relational Data with Graph Convolutional Networks

Biased graph walks for RDF graph embeddings

RDF2Vec: RDF Graph Embeddings for Data Mining

Contact Info

Product

Resources

About