Modelling Relational Data using Bayesian Clustered Tensor Factorization

By Ilya Sutskever, Ruslan Salakhutdinov, Josh Tenenbaum. 2009

278 citations recorded by the source corpus.

Subfields: Probabilistic & Bayesian Methods

How researchers see this paper

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

In Probabilistic & Bayesian Methods

Citations in the corpus

Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank (2013, methodology): “The idea to relate inputs through three way interactions, parameterized by a tensor have been proposed for relation classification (Sutskever et al., 2009; Jenatton et al., 2012), extending Restricted Boltzmann machines (Ranzato and Hinton, 2010) and as a special layer for speech recognition (Yu et ”
Knowledge Graph Embedding by Translating on Hyperplanes (2014, background): “Bilinear Model (Jenatton et al. 2012; Sutskever, Tenenbaum , and Salakhutdinov 2009) models second-order correlations between entity embeddings by a quadratic form: h W r t.”
Learning Entity and Relation Embeddings for Knowledge Graph Completion (2015, methodology): “LFM model (Jenatton et al. 2012; Sutskever, Tenenbaum, and Salakhutdinov 2009) considers second-order correlations between entity embeddings using a quadratic form, and defines a bilinear score function f r (h, t) = h M r t. Neural Tensor Network (NTN).”
Irreflexive and Hierarchical Relations as Translations (2013, methodology): “…the stochastic block-model allowing to automatically infer the number of latent clusters; Kok & Domingos (2007) introduced clustering in Markov-Logic networks; Sutskever et al. (2009) used a non-parametric Bayesian clustering of entities embedding in a collective matrix factorization formulation.”
Complex Embeddings for Simple Link Prediction (2016, methodology): “…prediction problem, antisymmetry of relations was quickly seen as a problem and asymmetric extensions of tensors were studied, mostly by either considering independent embeddings (Sutskever, 2009) or considering relations as matrices instead of vectors in the RESCAL model (Nickel et al., 2011).”
Embedding Entities and Relations for Learning and Inference in Knowledge Bases (2014, background): “…representations of entities and relations, including tensor/matrix factorization (Singh & Gordon, 2008; Nickel et al., 2011; 2012), Bayesian clustering framework (Kemp et al., 2006; Sutskever et al., 2009), and neural networks (Paccanaro & Hinton, 2001; Bordes et al., 2013a;b; Socher et al., 2013).”
A Review of Relational Machine Learning for Knowledge Graphs (2015, methodology): “s on a number of small benchmark datasets compared to Markov Logic Networks (with structure learning) [70], the Inﬁnite (Hidden) Relational model [71, 72], and Bayesian Clustered Tensor Factorization [73]. Moreover, RESCAL has been used for link prediction on entire knowledge graphs such as YAGO and”
Knowledge Graph Embedding via Dynamic Mapping Matrix (2015, background): “LFM model (Jenatton et al. 2012; Sutskever et al. 2009) encodes each entity into a vector and sets a matrix for every relation.”
Exploiting compositionality to explore a large space of model structures (2012, methodology): “The BCTF model makes it clearer that the clusters of Senators and votes are not independent, but can be seen as occupying different points in a low-dimensional representation.”
GAKE: Graph Aware Knowledge Embedding (2016, methodology): “…base embedding, such as general linear based models, such as SE (Bordes et al., 2011), bilinear based models, like LFM (Jenatton et al., 2012; Sutskever et al., 2009), neural network based models, like SLM (Socher et al., 2013), NTN (Socher et al., 2013), and translation based models (Bordes…”
Reasoning With Neural Tensor Networks for Knowledge Base Completion (2013, methodology): “The fourth model [11, 9] fixes the issue of weak entity vector interaction through a relation-specific bilinear form.”
A Three-Way Model for Collective Learning on Multi-Relational Data (2011, methodology): “Recently, (Sutskever et al., 2009) introduced the Bayesian Clustered Tensor Factorization (BCTF) and applied it to relational data.”
Data Fusion by Matrix Factorization (2013, background): “There is an abundance of work on matrix factorization models that consider a single dyadic relation matrix or multiple relation matrices between the same two types of objects [10], [21], [24], [26], [27], [28] that are subsumed in our approach.”
Semantically Smooth Knowledge Graph Embedding (2015, background): “The third group embeds factorized representations of entities and relations into a nonparametric Bayesian clustering framework, so as to obtain more interpretable embed-dings (Kemp et al., 2006; Sutskever et al., 2009).”
Unachievable Region in Precision-Recall Space and Its Effect on Empirical Evaluation (2012, methodology): “, by subsampling the negative examples (Natarajan et al., 2011; Sutskever et al., 2010)) increases the minimum AUCPR by approximately 0.”