A review: Knowledge reasoning over knowledge graph

By Xiaojun Chen, Shengbin Jia, Yang Xiang. Expert systems with applications, 2020

956 citations recorded by the source corpus.

Abstract Mining valuable hidden knowledge from large-scale data relies on the support of reasoning technology. Knowledge graphs, as a new type of knowledge representation, have gained much attention in natural language processing. Knowledge graphs can effectively organize and represent knowledge so that it can be efficiently utilized in advanced applications. Recently, reasoning over knowledge graphs has become a hot research topic, since it can obtain new knowledge and conclusions from existing data. Herein we review the basic concept and definitions of knowledge reasoning and the methods for reasoning over knowledge graphs. Specifically, we dissect the reasoning methods into three categories: rule-based reasoning, distributed representation-based reasoning and neural network-based reasoning. We also review the related applications of knowledge graph reasoning, such as knowledge graph completion, question answering, and recommender systems. Finally, we discuss the remaining challenges and research opportunities for knowledge graph reasoning.

Subfields: Artificial Intelligence, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/cd343276aec1b22e0c273b1cf5986bb826d3e5a4

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Philip S. Yu
2. Meng Jiang
3. Chenguang Zhu
4. Shirui Pan
5. Erik Cambria
6. Feng Xia
7. Heng Ji
8. W. Yu

In Management Science and Operations Research

1. Heng Ji
2. Philip S. Yu
3. Meng Jiang
4. Pekka Marttinen
5. Shirui Pan
6. Zhiting Hu
7. Erik Cambria
8. Shaoxiong Ji

Citations in the corpus

• Knowledge Graphs: Opportunities and Challenges (2023, methodology): “to the users based on the information of user-item interaction (Chen et al. 2020c).”
• A Survey on Knowledge Graphs: Representation, Acquisition, and Applications (2020, background): “refinement [11], Chinese knowledge graph construction [13], knowledge reasoning [14], KGE [5] or KRL [9].”
• A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly (2023, background): “Beyond the architecture of LLMs themselves, studies have focused on improving LLM safety by combining them with external modules including knowledge graphs [39] and cognitive architectures (CAs) [143, 11].”
• A Survey of Knowledge-enhanced Text Generation (2020, positive): “The corresponding techniques are knowledge graph embedding (KGE) [126] and path-based knowledge graph reasoning [15].”
• Neural, symbolic and neural-symbolic reasoning on knowledge graphs (2021, background): “…across research communities as it achieved superior performances on many tasks in different fi elds such as image classi fi cation in computer vision (Chen et al., 2020a; He et al., 2016, 2020), language modeling in natural language processing (Brown et al., 2020; Devlin et al., 2018), and link…”
• Comparing RAG and GraphRAG for Page-Level Retrieval Question Answering on Math Textbook (2025, unknown): “GraphRAG [6] is a framework introduced by Microsoft Research, which extends the standard Retrieval-Augmented Generation (RAG) paradigm by leveraging structured knowledge graphs to improve document retrieval and response generation [3].”
• STMA: A Spatio-Temporal Memory Agent for Long-Horizon Embodied Task Planning (2025, unknown): “Hippo RAG [44] mimics the human hippocampus [45] and introduces KGs as long-term memory indices [46], significantly enhancing knowledge retrieval.”