A Three-Way Model for Collective Learning on Multi-Relational Data

By Maximilian Nickel, Volker Tresp, Hans-Peter Kriegel. 2011

2,524 citations recorded by the source corpus.

Subfields: Representation & Self-Supervised Learning

How researchers see this paper

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

In Representation & Self-Supervised Learning

Citations in the corpus

Knowledge Enhanced Contextual Word Representations (2019, methodology): “…distance models (Bordes et al., 2013; Wang et al., 2014b; Lin et al., 2015; Xiao et al., 2016) which use a distance-based scoring function, and linear models (Nickel et al., 2011; Yang et al., 2014; Trouillon et al., 2016; Dettmers et al., 2018) which use a similarity-based scoring function.”
RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems (2018, methodology): “ge graph embedding methods, including translational distance models [3, 13] and semantic matching models [14,18](WewillcontinuethediscussiononKGEmethodsinSection 3.6.3). In Ripple Network, similar to [19], we use a three-way tensor factorization method to define the likelihood function for KGE: p(G|”
Learning Entity and Relation Embeddings for Knowledge Graph Completion (2015, methodology): “In experiments we will also compare with RESCAL, a collective matrix factorization model presented in (Nickel, Tresp, and Kriegel 2011; 2012).”
Modeling polypharmacy side effects with graph convolutional networks (2018, methodology): “Wethusevaluatetheperformanceof Decagon against the following multirelational link prediction approaches: • RESCAL tensor decomposition (Nickel et al. , 2011): This is a tensor factorization approach that takes a multirelational structure into account.”
Connecting Language and Knowledge Bases with Embedding Models for Relation Extraction (2013, methodology): “in (Nickel et al., 2011; Bordes et al., 2011; Bordes et al., 2012)): we chose in this work to use the approach of (Bordes et al.”
A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications (2017, background): “(5) + O(community detection) + (community proximity constraint) ULGE [2] W ¼ ZD 1ZT , where Z ¼ argminzT i 1¼1;zi 0 Pm j¼1 kXi ujk 2 2zij þ g Pm j¼1 z 2 ij a ¼ argminkaTX Fpk2F þ akak 2 F whereFp is the top p eigenvectors ofW LLE [102] KNN,W ¼ argmin P i kXi P j WijXjk 2 y ¼ argmin P i kyi P j Wijyj”
Modeling Relational Data with Graph Convolutional Networks (2017, methodology): “Our encoder-decoder approach to link prediction relies on DistMult (Yang et al. 2014) in the decoder, a special and simpler case of the RESCAL factorization (Nickel, Tresp, and Kriegel 2011), more effective than the original RESCAL in the context of multi-relational knowledge bases.”
Complex Embeddings for Simple Link Prediction (2016, methodology): “However, dealing with anti-symmetric relations has so far almost always implied an explosion of the number of parameters (Nickel et al., 2011; Socher et al., 2013) (see Table 1), making models prone to overﬁtting.”
Embedding Entities and Relations for Learning and Inference in Knowledge Bases (2014, background): “Tensor factorization (e.g. (Nickel et al., 2011; 2012)) and neural-embedding-based models (e.g. (Bordes et al., 2013a;b; Socher et al., 2013)) are two popular kinds of approaches that learn to encode relational information using low-dimensional representations of entities and relations.”
Commonsense Knowledge Base Completion (2016, methodology): “Our methods are similar to past work on KBC (Mintz et al., 2009; Nickel et al., 2011; Lao et al., 2011; Nickel et al., 2012; Riedel et al., 2013; Gardner et al., 2014; West et al., 2014), particularly methods based on distributed representations and neural networks (Socher et al., 2013; Bordes et…”
Pretrained Encyclopedia: Weakly Supervised Knowledge-Pretrained Language Model (2019, neutral): “Our evaluation strategy is similar to previous work on knowledge base completion (Nickel et al., 2011; Bordes et al., 2013).”
Representing Text for Joint Embedding of Text and Knowledge Bases (2015, methodology): “The third model D IST M ULT , is a special form of a bilinear model like RESCAL (Nickel et al., 2011), where the non-diagonal entries in the relation matrices are assumed to be zero.”
StarSpace: Embed All The Things! (2017, methodology): “TransE was shown to out-perform RESCAL (Nickel, Tresp, and Kriegel 2011), RFM (Jenatton et al. 2012), SE (Bordes et al. 2011) and SME (Bordes et al. 2014) and is considered a standard benchmark method.”
Traversing Knowledge Graphs in Vector Space (2015, methodology): “A common vector space model for knowledge base completion is the bilinear model (Nickel et al., 2011).”