Duality-Induced Regularizer for Tensor Factorization Based Knowledge Graph Completion
Tensor factorization based models have shown great power in knowledge graph completion (KGC). However, their performance usually suffers from the overfitting problem seriously. This motivates various regularizers -- such as the squared Frobenius norm and tensor nuclear norm regularizers -- while the limited applicability significantly limits their practical usage. To address this challenge, we propose a novel regularizer -- namely, DUality-induced RegulArizer (DURA) -- which is not only effective in improving the performance of existing models but widely applicable to various methods. The major novelty of DURA is based on the observation that, for an existing tensor factorization based KGC model (primal), there is often another distance based KGC model (dual) closely associated with it. Experiments show that DURA yields consistent and significant improvements on benchmarks.
Code (3)
Tasks
Knowledge Graph CompletionLink PredictionSimilar Papers 제목 키워드 기반
ER: Equivariance Regularizer for Knowledge Graph Completion
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 overf…
Knowledge Graph CompletionRelation PredictionDuality-Induced Regularizer for Semantic Matching Knowledge Graph Embeddings
Semantic matching models -- which assume that entities with similar semantics have similar embeddings -- have shown great power in knowledge graph embeddings (KGE). Many existing semantic matching models use inner produc…
Entity EmbeddingsKnowledge Graph EmbeddingsKnowledge GraphsNonnegative Low-Rank Tensor Completion via Dual Formulation with Applications to Image and Video Completion
Recent approaches to the tensor completion problem have often overlooked the nonnegative structure of the data. We consider the problem of learning a nonnegative low-rank tensor, and using duality theory, we propose a no…
Image InpaintingConvex Factorization Machine for Regression
We propose the convex factorization machine (CFM), which is a convex variant of the widely used Factorization Machines (FMs). Specifically, we employ a linear+quadratic model and regularize the linear term with the $\ell…
regressionTemporal Knowledge Graph Completion using a Linear Temporal Regularizer and Multivector Embeddings
Representation learning approaches for knowledge graphs have been mostly designed for static data. However, many knowledge graphs involve evolving data, e.g., the fact (The President of the United States is Barack Obama)…
Knowledge Graph CompletionKnowledge GraphsLink PredictionRepresentation Learning+2