On Multi-Relational Link Prediction with Bilinear Models

نویسندگان

  • Yanjie Wang
  • Rainer Gemulla
  • Hui Li
چکیده

We study bilinear embedding models for the task of multirelational link prediction and knowledge graph completion. Bilinear models belong to the most basic models for this task, they are comparably efficient to train and use, and they can provide good prediction performance. The main goal of this paper is to explore the expressiveness of and the connections between various bilinear models proposed in the literature. In particular, a substantial number of models can be represented as bilinear models with certain additional constraints enforced on the embeddings. We explore whether or not these constraints lead to universal models, which can in principle represent every set of relations, and whether or not there are subsumption relationships between various models. We report results of an independent experimental study that evaluates recent bilinear models in a common experimental setup. Finally, we provide evidence that relation-level ensembles of multiple bilinear models can achieve state-of-the art prediction performance.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Topic-Based Embeddings for Learning from Large Knowledge Graphs

We present a scalable probabilistic framework for learning from multi-relational data, given in form of entity-relation-entity triplets, with a potentially massive number of entities and relations (e.g., in multirelational networks, knowledge bases, etc.). We define each triplet via a relation-specific bilinear function of the embeddings of entities associated with it (these embeddings correspo...

متن کامل

Embedding Entities and Relations for Learning and Inference in Knowledge Bases

We consider learning representations of entities and relations in KBs using the neural-embedding approach. We show that most existing models, including NTN (Socher et al., 2013) and TransE (Bordes et al., 2013b), can be generalized under a unified learning framework, where entities are low-dimensional vectors learned from a neural network and relations are bilinear and/or linear mapping functio...

متن کامل

Ing and Inference in Knowledge Bases

We consider learning representations of entities and relations in KBs using the neural-embedding approach. We show that most existing models, including NTN (Socher et al., 2013) and TransE (Bordes et al., 2013b), can be generalized under a unified learning framework, where entities are low-dimensional vectors learned from a neural network and relations are bilinear and/or linear mapping functio...

متن کامل

Hierarchical Probabilistic Matrix Factorization with Network Topology for Multi-relational Social Network

Link prediction in multi-relational social networks has attracted much attention. For instance, we may care the chance of two users being friends based on their contacts of other patterns, e.g., SMS and phone calls. In previous work, matrix factorization models are typically applied in single-relational networks; however, two challenges arise to extend it into multi-relational networks. First, ...

متن کامل

A graphical model for multi-relational social network analysis

In this paper, we propose a graphical model for multi-relational social network analysis based on latent variable models. Latent variable models are one of the successful approaches for social network analysis. These models assume a latent variable for each entity and then the probability distribution over relationships between entities is modeled via a function over latent variables. Here, we ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:
  • CoRR

دوره abs/1709.04808  شماره 

صفحات  -

تاریخ انتشار 2017