ER: Equivariance Regularizer for Knowledge Graph Completion

  title={ER: Equivariance Regularizer for Knowledge Graph Completion},
  author={Zongsheng Cao and Qianqian Xu and Zhiyong Yang and Qingming Huang},
  booktitle={AAAI Conference on Artificial Intelligence},
Tensor factorization and distanced based models play important roles in knowledge graph completion (KGC). However, the relational matrices in KGC methods often induce a high model complexity, bearing a high risk of overfitting. As a remedy, researchers propose a variety of different regularizers such as the tensor nuclear norm regularizer. Our motivation is based on the observation that the previous work only focuses on the “size” of the parametric space, while leaving the implicit semantic… 
1 Citations



Duality-Induced Regularizer for Tensor Factorization Based Knowledge Graph Completion

A novel regularizer, DUality-induced RegulArizer (DURA) is proposed, which is not only effective in improving the performance of existing models but widely applicable to various methods.

Canonical Tensor Decomposition for Knowledge Base Completion

This work motivates and test a novel regularizer, based on tensor nuclear $p$-norms, and presents a reformulation of the problem that makes it invariant to arbitrary choices in the inclusion of predicates or their reciprocals in the dataset.

Regularizing Knowledge Graph Embeddings via Equivalence and Inversion Axioms

A principled and scalable method for leveraging equivalence and inversion axioms during the learning process, by imposing a set of model-dependent soft constraints on the predicate embeddings, which consistently improves the predictive accuracy of several neural knowledge graph embedding models without compromising their scalability properties.

TuckER: Tensor Factorization for Knowledge Graph Completion

This work proposes TuckER, a relatively straightforward but powerful linear model based on Tucker decomposition of the binary tensor representation of knowledge graph triples that outperforms previous state-of-the-art models across standard link prediction datasets, acting as a strong baseline for more elaborate models.

You CAN Teach an Old Dog New Tricks! On Training Knowledge Graph Embeddings

It is found that when trained appropriately, the relative performance differences between various model architectures often shrinks and sometimes even reverses when compared to prior results, and many of the more advanced architectures and techniques proposed in the literature should be revisited to reassess their individual benefits.

Dual Quaternion Knowledge Graph Embeddings

The core of DualE lies a specific design of dual-quaternion-based multiplication, which universally models relations as the compositions of a series of translation and rotation operations.

Semantically Smooth Knowledge Graph Embedding

The key idea of SSE is to take full advantage of additional semantic information and enforce theembedding space to be semantically smooth, i.e., entities belonging to the same semantic category will lie close to each other in the embedding space.

Convolutional 2D Knowledge Graph Embeddings

ConvE, a multi-layer convolutional network model for link prediction, is introduced, and it is found that ConvE achieves state-of-the-art Mean Reciprocal Rank across all datasets.

Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphs

This paper proposes a novel attention-based feature embedding that captures both entity and relation features in any given entity’s neighborhood and encapsulate relation clusters and multi-hop relations in the model.