RDF2Vec: RDF Graph Embeddings for Data Mining

By Petar Ristoski, Heiko Paulheim. 2016

537 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Modeling Relational Data with Graph Convolutional Networks (2017, methodology): “2011; de Vries and de Rooij 2015), RDF2Vec (Ristoski and Paulheim 2016), and R-GCN (this work).”
The Geometry of Distributed Representations for Better Alignment, Attenuated Bias, and Improved Interpretability (2020, unknown): “Representations of knowledge graphs [78] are made in a similar manner.”
Knowledge Graphs (2020, unknown): “Along these lines, RDF2Vec [109] performs biased random walks on the graph and records the paths traversed as “sentences”, which are then fed as input into the word2vec [83] model.”
Bootstrapping Entity Alignment with Knowledge Graph Embedding (2018, methodology): “Besides, type information, local structure of entities and global patterns are explored in [Krompaß et al. , 2015; Ristoski and Paulheim, 2016; Cochez et al. , 2017].”
Composition-based Multi-Relational Graph Convolutional Networks (2019, methodology): “Node and Graph Classiﬁcation: For node classiﬁcation, following Schlichtkrull et al. (2017), we compare with Feat (Paulheim & Fümkranz, 2012), WL (Shervashidze et al., 2011), and RDF2Vec (Ristoski & Paulheim, 2016).”
Deep learning for noise-tolerant RDFS reasoning (2019, methodology): “The authors report similar embedding quality as RDF2Vec but with the ability to incorporate larger portions of the graph.”
Cross-Lingual Entity Alignment via Joint Attribute-Preserving Embedding (2017, methodology): “RDF2Vec [19] uses local information of KB structures to generate sequences of entities and employs language modeling approaches to learn entity embeddings for machine learning tasks.”
Representation Learning for Dynamic Graphs: A Survey (2019, background): “6), Sankar et al. (2018) propose DySAT: a fully attentive model for DTDGs. Consider a DTDG as {G1, . . . ,GT }. DySAT applies the attention-based GCN model of Veličković et al. (2018) to each Gt and obtains z(1)v, .”
Common Sense or World Knowledge? Investigating Adapter-Based Knowledge Injection into Pretrained Transformers (2020, methodology): “Following established previous work (Perozzi et al., 2014; Ristoski and Paulheim, 2016), we induce a synthetic corpus from ConceptNet by randomly traversing its graph.”
Relational Representation Learning for Dynamic (Knowledge) Graphs: A Survey (2019, background): “While some initial steps have been taken to extend these approaches to other types of graphs [192], the best way of extending these approaches to the case of attributed graphs and knowledge graphs (KGs) is still not clear.”
Relational Graph Attention Networks (2018, methodology): “Table 2: (a) Entity classiﬁcation results accuracy (mean and standard deviation over 10 seeds) for FEAT (Paulheim and Fümkranz, 2012), WL (Shervashidze et al., 2011; de Vries and de Rooij, 2015), RDF2Vec (Ristoski and Paulheim, 2016) and RGCN (Schlichtkrull et al., 2018), and (mean and standard devi”
Griffin: Towards a Graph-Centric Relational Database Foundation Model (2025, unknown): “Some methods that convert structured data into unstructured embeddings can still retain structural information (Grover & Leskovec, 2016), such as EmbDi (Cappuzzo et al., 2020) and RDF2Vec (Ristoski & Paulheim, 2016).”