@article {1812, title = {A Review of Relational Machine Learning for Knowledge Graphs}, journal = {Proceedings of the IEEE}, volume = {104}, year = {2016}, month = {Jan-01-2016}, pages = {11 - 33}, abstract = {

Relational machine learning studies methods for the statistical analysis of relational, or graph-structured, data. In this paper, we provide a review of how such statistical models can be {\textquotedblleft}trained{\textquotedblright} on large knowledge graphs, and then used to predict new facts about the world (which is equivalent to predicting new edges in the graph). In particular, we discuss two fundamentally different kinds of statistical relational models, both of which can scale to massive data sets. The first is based on latent feature models such as tensor factorization and multiway neural networks. The second is based on mining observable patterns in the graph. We also show how to combine these latent and observable models to get improved modeling power at decreased computational cost. Finally, we discuss how such statistical models of graphs can be combined with text-based information extraction methods for automatically constructing knowledge graphs from the Web. To this end, we also discuss Google{\textquoteright}s knowledge vault project as an example of such combination.

}, issn = {0018-9219}, doi = {10.1109/JPROC.2015.2483592}, url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=7358050}, author = {Maximilian Nickel and Kevin Murphy and Tresp, Volker and Gabrilovich, Evgeniy} } @article {694, title = {A Review of Relational Machine Learning for Knowledge Graphs: From Multi-Relational Link Prediction to Automated Knowledge Graph Construction}, number = {028}, year = {2015}, month = {03/2015}, abstract = {

Relational machine learning studies methods for the statistical analysis of relational, or graph-structured, data. In this paper, we provide a review of how such statistical models can be {\textquotedblleft}trained{\textquotedblright} on large knowledge graphs, and then used to predict new facts about the world (which is equivalent to predicting new edges in the graph). In particular, we discuss two different kinds of statistical relational models, both of which can scale to massive datasets. The first is based on tensor factorization methods and related latent variable models. The second is based on mining observable patterns in the graph. We also show how to combine these latent and observable models to get improved modeling power at decreased computational cost. Finally, we discuss how such statistical models of graphs can be combined with text-based information extraction methods for automatically constructing knowledge graphs from the Web. In particular, we discuss Google{\textquoteright}s Knowledge Vault project.

}, author = {Maximilian Nickel and Kevin Murphy and Volker Tresp and Evgeniy Gabrilovich} } @inbook {918, title = {Querying Factorized Probabilistic Triple Databases}, booktitle = {The Semantic Web {\textendash} ISWC 2014}, series = {Lecture Notes in Computer Science}, volume = {8797}, year = {2014}, pages = {114-129}, publisher = {Springer International Publishing}, organization = {Springer International Publishing}, isbn = {978-3-319-11914-4}, doi = {10.1007/978-3-319-11915-1_8}, url = {http://dx.doi.org/10.1007/978-3-319-11915-1_8}, author = {Krompa{\ss}, Denis and Maximilian Nickel and Volker Tresp} } @inbook {920, title = {Reducing the Rank in Relational Factorization Models by Including Observable Patterns}, booktitle = {Advances in Neural Information Processing Systems 27}, year = {2014}, pages = {1179{\textendash}1187}, publisher = {Curran Associates, Inc.}, organization = {Curran Associates, Inc.}, abstract = {
Tensor factorization has become a popular method for learning from multi-relational data. In this context, the rank of the factorization is an important parameter that determines runtime as well as generalization ability. To identify conditions under which factorization is an efficient approach for learning from relational data,we derive upper and lower bounds on the rank required to recover adjacency tensors.Based on our findings, we propose a novel additive tensor factorization modelto learn from latent and observable patterns on multi-relational data and present
a scalable algorithm for computing the factorization. We show experimentallyboth that the proposed additive model does improve the predictive performanceover pure latent variable methods and that it also reduces the required rank {\textemdash} andtherefore runtime and memory complexity {\textemdash} significantly.
}, url = {http://papers.nips.cc/paper/5448-reducing-the-rank-in-relational-factorization-models-by-including-observable-patterns.pdf}, author = {Maximilian Nickel and Jiang, Xueyan and Volker Tresp} }