Knowledge Graph Embedding with Atrous Convolution and Residual Learning

Proceedings of the 28th International Conference on Computational Linguistics, pages 1532–1543 Barcelona, Spain (Online), December 8-13, 2020 1532 Knowledge Graph Embedding with Atrous Convolution and Residual Learning Feiliang Ren, Juchen Li, Huihui Zhang, Shilei Liu, Bochao Li, Ruicheng Ming, Yujia Bai School of Computer Science and Engineering, Northeastern University Shenyang, 110169, China renfeiliang@cse.neu.edu.cn Abstract Knowledge graph embedding is an important task and it will benefit lots of downstream appli- cations. Currently, deep neural networks based methods achieve state-of-the-art performance. However, most of these existing methods are very complex and need much time for training and inference. To address this issue, we propose a simple but effective atrous convolution based knowledge graph embedding method. Compared with existing state-of-the-art methods, our method has following main characteristics. First, it effectively increases feature interac- tions by using atrous convolutions. Second, to address the original information forgotten issue and vanishing/exploding gradient issue, it uses the residual learning method. Third, it has sim- pler structure but much higher parameter efficiency. We evaluate our method on six benchmark datasets with different evaluation metrics. Extensive experiments show that our model is very effective. On these diverse datasets, it achieves better results than the compared state-of-the- art methods on most of evaluation metrics. The source codes of our model could be found at https://github.com/neukg/AcrE. 1 Introduction Knowledge graph is a kind of valuable knowledge bases and it is important for many AI-related appli- cations. Generally, a KG stores factual knowledge in the form of structural triplets like <h, r, t>, which means there is a kind of r relation from h (head entity) to t (tail entity). Nowadays, great achievements have been made in building large scale KGs. Usually a KG may contain millions of entities and billions of relational facts. However, there are still two major difficulties that prohibit the availability of KGs. First, although most existing KGs contain large amount of triplets, they are far from completeness. Sec- ond, most existing KGs are stored in symbolic and logical formations while applications often involve numerical computing in continuous spaces. To address these two issues, researchers proposed knowledge graph embedding (KGE) methods that aim to learn a kind of embedding representations for a KG’s items (entities and relations) by projecting these items into some continuous low-dimensional spaces. Gener- ally, different kinds of KGE methods mainly differ in how to view the role of relations in the projected spaces. For example, translation based methods (TransE (Bordes et al. , 2013), TransH (Wang et al. , 2014), TransR (Lin et al. , 2015a), TransD (Ji et al. , 2015), et al.) view the relation in a triplet as a translation operation from the head entity to the tail entity. Other KGE methods view relations as some kind of combination operators that link head entities and tail entities. For example, HolE (Nickel et al. , 2016) employs a circular correlation function as the combination operator in the project space. ComplEx (Trouillon et al. , 2016) makes use of complex valued embeddings and …

Content truncated to 500 words