Large-scale factorization of type-constrained multi-relational data

Abstract

Abstract-The statistical modeling of large multi-relational datasets has increasingly gained attention in recent years. Typical applications involve large knowledge bases like DBpedia, Freebase, YAGO and the recently introduced Google Knowledge Graph that contain millions of entities, hundreds and thousands of relations, and billions of relational tuples. Collective factorization methods have been shown to scale up to these large multirelational datasets, in particular in form of tensor approaches that can exploit the highly scalable alternating least squares (ALS) algorithms for calculating the factors. In this paper we extend the recently proposed state-of-the-art RESCAL tensor factorization to consider relational type-constraints. Relational type-constraints explicitly define the logic of relations by excluding entities from the subject or object role. In addition we will show that in absence of prior knowledge about type-constraints, local closedworld assumptions can be approximated for each relation by ignoring unobserved subject or object entities in a relation. In our experiments on representative large datasets (Cora, DBpedia), that contain up to millions of entities and hundreds of typeconstrained relations, we show that the proposed approach is scalable. It further significantly outperforms RESCAL without type-constraints in both, runtime and prediction quality.

Regularizing Knowledge Graph Embeddings via Equivalence and Inversion Axioms

“…We consider a fragment extracted following the indications from Krompass et al (2014), by considering relations in the music domain 3 . The axioms we used in experiments are simple common-sense rules, and are listed in Tab.…”

Knowledge Completion for Generics using Guided Tensor Factorization

“…Recent work on incorporating entity type and relation schema in tensor factorization (Krompaß et al, 2014(Krompaß et al, , 2015Xie et al, 2016b) has focused on factual databases about named entities, which, as discussed earlier, have very different characteristics than generics tensors. Nimishakavi et al (2016) use entity type information as a matrix in the context of non-negative RESCAL for schema induction on medical research documents.…”

Type-Constrained Representation Learning in Knowledge Graphs

“…-To the best of our knowledge, these latent variable models are the only ones which have been applied to large KGs with more than 1 million entities, thereby proving their scalability [5,8,19,7,10]. -All of these models have been published at well respected conferences and are the basis for the most recent research activities in the field of statistical modeling of KGs (see Section 6).…”

“…Supporting KG cleaning, completion and construction via machine learning is one of the core challenges. In this context, Representation Learning in form of latent variable methods has successfully been applied to KG data [19,20,5,10,7]. These models learn latent embeddings for entities and relation-types from the data that can then be used as representations of their semantics.…”

“…that the marriedTo relation-type should relate only instances of the class Person. In recent work [10,7], it has been shown that RESCAL, a much studied latent variable approach, benefits greatly from prior knowledge about the semantics of relation-types. In this work we will study the impact of prior knowledge about the semantics of relation-types in the state of the art representative latent variable models TransE [5], RESCAL [18] and the multiway neural network approach used in the Google Knowledge Vault project [8].…”