Knowledge graph embedding has been an active research topic for knowledge base completion, with progressive improvement from the initial TransE, TransH, DistMult et al to the current state-of-the-art ConvE. ConvE uses 2D convolution over embeddings and multiple layers of nonlinear features to model knowledge graphs. The model can be efficiently trained and scalable to large knowledge graphs. However, there is no structure enforcement in the embedding space of ConvE. The recent graph convolutional network (GCN) provides another way of learning graph node embedding by successfully utilizing graph connectivity structure. In this work, we propose a novel end-to-end Structure-Aware Convolutional Network (SACN) that takes the benefit of GCN and ConvE together. SACN consists of an encoder of a weighted graph convolutional network (WGCN), and a decoder of a convolutional network called Conv-TransE. WGCN utilizes knowledge graph node structure, node attributes and edge relation types. It has learnable weights that adapt the amount of information from neighbors used in local aggregation, leading to more accurate embeddings of graph nodes. Node attributes in the graph are represented as additional nodes in the WGCN. The decoder Conv-TransE enables the state-of-the-art ConvE to be translational between entities and relations while keeps the same link prediction performance as ConvE. We demonstrate the effectiveness of the proposed SACN on standard FB15k-237 and WN18RR datasets, and it gives about 10% relative improvement over the state-of-the-art ConvE in terms of HITS@1, HITS@3 and HITS@10.
ConvD: Attention Enhanced Dynamic Convolutional Embeddings for Knowledge Graph Completion
College of Intelligence and Computing, Tianjin University（天津大学智能与计算学院）；Tianjin Key Laboratory of Cognitive Computing and Application（认知计算与应用重点实验室）；School of Economics and Management, Ningxia University（宁夏大学经济管理学院）；School of Computer Science and Technology, Beijing Institute of Technology（北京理工大学计算机科学与技术学院）
Rethinking Graph Convolutional Networks in Knowledge Graph Completion
University of Science and Technology of China（中国科学技术大学）；Hefei Comprehensive National Science Center（合肥综合性国家科学中心）；University of Michigan（密歇根大学）；KE Holdings Inc.（贝壳控股有限公司）
Learning Granularity Representation for Temporal Knowledge Graph Completion
School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院）；Beijing Institute of Aerospace Measurement and Testing Technology（北京航天计量测试技术研究所）；School of Information and Software Engineering, University of Electronic Science and Technology of China（电子科技大学信息与软件工程学院）；KASH Institute of Electronics and Information Industry（喀什电子信息产业研究院）
Completion of partial structures using Patterson maps with the CrysFormer machine learning model
Department of Computer Science, Rice University（计算机科学系， Rice大学）；Rice University（Rice大学）；Computer Science Dept., Rice University（计算机科学系， Rice大学）；Ken Kennedy Institute, Rice University（Ken Kennedy研究所， Rice大学）；Department of BioSciences and Department of Chemistry, Rice University（生物科学系和化学系， Rice大学）
