RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space

By Zhiqing Sun, Zhihong Deng, Jian-Yun Nie, Jian Tang. 2018

2,814 citations recorded by the source corpus.

We study the problem of learning representations of entities and relations in knowledge graphs for predicting missing links. The success of such a task heavily relies on the ability of modeling and inferring the patterns of (or between) the relations. In this paper, we present a new approach for knowledge graph embedding called RotatE, which is able to model and infer various relation patterns including: symmetry/antisymmetry, inversion, and composition. Specifically, the RotatE model defines each relation as a rotation from the source entity to the target entity in the complex vector space. In addition, we propose a novel self-adversarial negative sampling technique for efficiently and effectively training the RotatE model. Experimental results on multiple benchmark knowledge graphs show that the proposed RotatE model is not only scalable, but also able to infer and model various relation patterns and significantly outperform existing state-of-the-art models for link prediction.

Subfields: Artificial Intelligence, Management Science and Operations Research

How researchers see this paper

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

In Artificial Intelligence

In Management Science and Operations Research

Citations in the corpus

Composition-based Multi-Relational Graph Convolutional Networks (2019, methodology): “The scores of baseline methods are taken directly from the previous papers (Sun et al., 2019; Cai & Wang, 2018; Shang et al., 2019; Balažević et al., 2019; Jiang et al., 2019; Ye et al., 2019).”
DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphs (2019, background): “The results are taken from [21, 41] and [35]”
A Survey on Knowledge Graphs: Representation, Acquisition, and Applications (2020, methodology): “With the introduction of rotational Hadmard product, RotatE [19] can also capture inversion and composition patterns as well as symmetry and antisymmetry.”
Knowledge Graphs (2020, neutral): “Recently, RotatE [510]”
Are Pretrained Language Models Symbolic Reasoners over Knowledge? (2020, background): “In the knowledge base domain, prior work (Sun et al., 2019; Zhang et al., 2020) has shown that models that are able to learn symbolic rules are superior to ones that are not.”
Measuring Social Bias in Knowledge Graph Embeddings (2019, methodology): “Many transformation functions have been proposed, including TransE (Bordes et al., 2013), ComplEx (Trouillon et al., 2016) and RotatE (Sun et al., 2019).”
Knowledge Graph Alignment Network with Gated Multi-hop Neighborhood Aggregation (2019, methodology): “Representation learning models encode KGs into vector spaces, where relation semantics of entities can be assessed by the learned embedding operations, such as the relation-speciﬁc translation (Bordes et al. 2013) or rotation (Sun et al. 2019).”
MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding (2020, methodology): “Examples include social networks [14, 29], physical systems [2, 10], traffic networks [18, 34], citation networks [1, 14, 16], recommender systems [26, 35], knowledge graphs [3, 24], and so on.”
HittER: Hierarchical Transformers for Knowledge Graph Embeddings (2020, methodology): “, 2015), numerous complicated transformations in various spaces have been hence proposed (Trouillon et al., 2016; Ebisu and Ichise, 2018; Sun et al., 2018; Zhang et al., 2019a; Chami et al., 2020; Tang et al., 2020).”
Inductive Relation Prediction by Subgraph Reasoning (2019, methodology): “For all the methods we use the implementation and hyperparameters provided by Sun et al. (2019) which gives state-of-the-art results on all methods.”
Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction (2019, methodology): “We evaluate our proposed models on three commonly used knowledge graph datasets—WN18RR (Toutanova and Chen 2015), FB15k-237 (Dettmers et al. 2018), and YAGO3-10 (Mahdisoltani, Biega, and Suchanek 2013).”
Recurrent Event Network: Autoregressive Structure Inference over Temporal Knowledge Graphs (2019, methodology): “We use the code for RotatE 11 .”
Revisiting Evaluation of Knowledge Base Completion Models (2020, methodology): “In this work, we will primarily study DistMult [Yang et al., 2015] due to its simplicity and popularity, and RotatE [Sun et al., 2019a] and Tucker [Balaževi´c et al., 2019] because of their state-of-the-art performance.”
A benchmarking study of embedding-based entity alignment for knowledge graphs (2020, positive): “To fill this gap, we evaluate three translational models TransH [90], TransR [52] and TransD [35], two deep models ProjE [75] and ConvE [14], as well as three semantic matching models HolE [63], SimplE [39] and RotatE [79] in terms of entity alignment.”
Structure-Augmented Text Representation Learning for Efficient Knowledge Graph Completion (2020, methodology): “311 - RotatE [31] .”
Neural, symbolic and neural-symbolic reasoning on knowledge graphs (2021, methodology): “Although some models such as Graft-Net (Sun et al., 2018) and PullNet (Sun et al., 2019a) are the state-of-the-art reasoning models on both the structural and the textual information, it is still challenging to determine the correct evidence to be linked to the incomplete graph structure from the la”