[论文解读] A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodal

Ke Liang, Lingyuan Meng+7 more|arXiv (Cornell University)|Dec 12, 2022

Advanced Graph Neural Networks被引用 46

一句话总结

本论文综述知识图谱推理（KGR）在三类图上——静态、时序和多模态——使用双层分类法，并提供数据集、挑战以及一个开源代码库。

ABSTRACT

Knowledge graph reasoning (KGR), aiming to deduce new facts from existing facts based on mined logic rules underlying knowledge graphs (KGs), has become a fast-growing research direction. It has been proven to significantly benefit the usage of KGs in many AI applications, such as question answering, recommendation systems, and etc. According to the graph types, existing KGR models can be roughly divided into three categories, i.e., static models, temporal models, and multi-modal models. Early works in this domain mainly focus on static KGR, and recent works try to leverage the temporal and multi-modal information, which are more practical and closer to real-world. However, no survey papers and open-source repositories comprehensively summarize and discuss models in this important direction. To fill the gap, we conduct a first survey for knowledge graph reasoning tracing from static to temporal and then to multi-modal KGs. Concretely, the models are reviewed based on bi-level taxonomy, i.e., top-level (graph types) and base-level (techniques and scenarios). Besides, the performances, as well as datasets, are summarized and presented. Moreover, we point out the challenges and potential opportunities to enlighten the readers. The corresponding open-source repository is shared on GitHub https://github.com/LIANGKE23/Awesome-Knowledge-Graph-Reasoning.

研究动机与目标

• 定义并区分静态、时序和多模态知识图谱（KGs）。
• 为 KGR 模型提供一个双层分类法（图类型；技术与场景）。
• 综述最先进的 KGR 模型及其性能、数据集和应用。
• 突出挑战与机会，并在 GitHub 分享一个开源资源。

提出的方法

• 按顶层图类型（静态、时序、多模态）对 KGR 模型进行分类。
• 按底层技术对每种类型进一步分类（嵌入式方法、基于路径的方法、基于规则的方法；对于特定类型，使用 RNN-based 和 Transformer-based）。
• 将推理场景细分为静态的传导式/归纳式（transductive/inductive）和时序的内插/外推（interpolation/extrapolation）。
• 总结所调查模型的数据集、性能和常用评估指标。
• 提供一个包含模型（论文与代码）和数据集的开源仓库。

实验结果

研究问题

• RQ1 静态、时序和多模态 KG 类型在 KGR 建模需求上的主要差异是什么？
• RQ2 哪些技术最能应对每种 KG 类型和推理场景的独特挑战？
• RQ3 数据集和评估设置在静态、时序和多模态 KGR 中有何变化？有哪些开放的研究机会？

主要发现

• 该综述为 KGR 模型提出一个双层分类法：图类型作为顶层，技术/场景作为底层。
• 它汇总了 180 个最先进的 KGR 模型和 67 个数据集，提供跨 KG 类型的结构化概览。
• 它分析现有模型的优缺点并为研究中的基准选择提供指南。
• 它识别了静态、时序和多模态 KGR 的挑战与机会，并在 GitHub 上提供一个开源资源。