A Survey on Knowledge Graphs: Representation, Acquisition and Applications
Shaoxiong Ji, Shirui Pan, Erik Cambria, Pekka Marttinen, Philip S. Yu Manuscript received August 09, 2020; revised November xx, 2020; accepted March 30, 2021. This work is supported in part by NSF under grants III-1763325, III-1909323, SaTC-1930941, in part by the Agency for Science, Technology and Research (A*STAR) under its AME Programmatic Funding Scheme (Project #A18A2b0046), and in part by the Academy of Finland (grants 336033, 315896), BusinessFinland (grant 884/31/2018), and EU H2020 (grant 101016775). (Corresponding author: Shirui Pan.)S. Ji and P. Marttinen are with Aalto University, Finland. E-mail: {shaoxiong.ji; S. Pan is with the Department of Data Science and AI, Faculty of IT, Monash University, Australia. E-mail: E. Cambria is with Nanyang Technological University, Singapore. E-mail: P.S. Yu is with University of Illinois at Chicago, USA. E-mail:
Abstract
Human knowledge provides a formal understanding of the world. Knowledge graphs that represent structural relations between entities have become an increasingly popular research direction towards cognition and human-level intelligence. In this survey, we provide a comprehensive review of knowledge graph covering overall research topics about 1) knowledge graph representation learning, 2) knowledge acquisition and completion, 3) temporal knowledge graph, and 4) knowledge-aware applications, and summarize recent breakthroughs and perspective directions to facilitate future research. We propose a full-view categorization and new taxonomies on these topics. Knowledge graph embedding is organized from four aspects of representation space, scoring function, encoding models, and auxiliary information. For knowledge acquisition, especially knowledge graph completion, embedding methods, path inference, and logical rule reasoning, are reviewed. We further explore several emerging topics, including meta relational learning, commonsense reasoning, and temporal knowledge graphs. To facilitate future research on knowledge graphs, we also provide a curated collection of datasets and open-source li
中文速览
知识图谱（Knowledge Graph）长期面临如何高效表示实体与关系、自动补全缺失知识、并将其用于实际应用的挑战，而现有综述往往只聚焦某一局部。这篇文章对知识图谱领域的研究做了全面系统的梳理，从知识图谱嵌入（Knowledge Graph Embedding）的表示空间、评分函数、编码模型和辅助信息四个维度出发，深入介绍了知识获取与补全、时序知识图谱以及推荐系统、问答等下游应用。作者还专门整理了各类公开数据集和开源工具库，并对元关系学习、常识推理等新兴方向进行了覆盖。这项工作的价值在于，它为研究者提供了一张清晰的全景地图，既能帮助入门者快速把握领域脉络，也为从业者提供了系统的方法对比与未来研究路线参考。
原文 arXiv:2002.00388;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2002.00388v4