论文标题
双重性引起的基于张分解的知识图的正规器
Duality-Induced Regularizer for Tensor Factorization Based Knowledge Graph Completion
论文作者
论文摘要
基于张量分解的模型在知识图完成（KGC）中表现出很大的功能。但是，他们的表现通常会严重遇到过度拟合问题。这激发了各种正规化器（例如平方的Frobenius Norm和Tensor Norm Norm正常机），而有限的适用性则显着限制了其实际使用情况。为了应对这一挑战，我们提出了一个新颖的正规器 - 即双重性引起的正规器（Dura） - 它不仅有效地改善了现有模型的性能，而且可以广泛适用于各种方法。硬脑膜的主要新颖性是基于这样的观察结果，即对于现有的基于张量的KGC模型（原始），通常存在与之紧密相关的另一个基于距离的KGC模型（dual）。实验表明，硬脑膜在基准上产生一致且显着改善。
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.
