Knowledge Graphs
2020/03/04 by Aidan Hogan, Eva Blomqvist, Michael Cochez +17 · 3 voices · 1,657 citations
Computer Science · Decision Sciences · #Advanced Graph Neural Networks #Artificial intelligence #Computer science #Data Quality and Management #Knowledge graph #Machine Learning and Algorithms #cs.AI #cs.DB #cs.LG
paper · pdf · open access · doi:10.1145/3447772
published in ACM Computing Surveys 54(4), 1-37 (Association for Computing Machinery) · Revision from v5: Correcting errata from previous version for entailment/models, and some other minor typos
openalex created_date 2020/03/13 · openalex publication_date 2021/07/02 · arxiv created 2021/09/11 · arxiv updated 2021/09/14 · openalex updated_date 2026/08/05
Abstract
In this paper we provide a comprehensive introduction to knowledge graphs, which have recently garnered significant attention from both industry and academia in scenarios that require exploiting diverse, dynamic, large-scale collections of data. After some opening remarks, we motivate and contrast various graph-based data models and query languages that are used for knowledge graphs. We discuss the roles of schema, identity, and context in knowledge graphs. We explain how knowledge can be represented and extracted using a combination of deductive and inductive techniques. We summarise methods for the creation, enrichment, quality assessment, refinement, and publication of knowledge graphs. We provide an overview of prominent open knowledge graphs and enterprise knowledge graphs, their applications, and how they use the aforementioned techniques. We conclude with high-level future research directions for knowledge graphs.
Citations
Cited by
- Artificial Intelligence in manufacturing: State of the art, perspectives, and future directions
- MedKGent: A Large Language Model Agent Framework for Constructing Temporally Evolving Medical Knowledge Graph
- Short-Term-to-Long-Term Memory Transfer for Knowledge Graphs under Partial Observability
- From Static Bibliometrics to Dynamic Knowledge Graphs: An LLM-Powered Framework for Modernizing Science, Technology, and Innovation (STI) Analytics
- CLARK: Closed-loop Learning for Adaptive Reasoning over Knowledge Graphs
- Neuro-Symbolic Meta-Policies for Temporal Knowledge-Graph Memory under Partial Observability
- DeLIVeR: Decomposed Learning for Information-grounded Veracity Recognition via Reinforced Knowledge Graph Exploration
- Debate-on-Graph: Reliable and Adaptive Reasoning of Large Language Model on Uncertain Knowledge Graph
- ProbSPARQL: Querying Knowledge Graphs with Multi-dimensional, Uncertain Numeric Data
- MR2-KG: A Multi-Relation Multi-Rationale Knowledge Graph for Modeling Software Engineering Knowledge on Stack Overflow
- Geometric Structural Knowledge Graph Foundation Model
- Debugging Tabular Log as Dynamic Graphs
- SoDA: An Efficient Interaction Paradigm for the Agentic Web
- TRACE-CTI: Auditable Post-Extraction Governance of TTP Claims with Knowledge Graphs
- Automatic Knowledge Graph Construction and Query for Earthquake Catalogs
- SCAIR: Schema-Conditioned Agentic Iterative Reasoning for Enterprise Knowledge Graphs
- Intelligent Human-Machine Partnership for Manufacturing: Enhancing Warehouse Planning through Simulation-Driven Knowledge Graphs and LLM Collaboration
- Intelligent Knowledge Mining Framework: Bridging AI Analysis and Trustworthy Preservation
- A Survey on Spatio-Temporal Knowledge Graph Models
- IaC Generation with LLMs: An Error Taxonomy and A Study on Configuration Knowledge Injection
- BRIDG-ICS: AI-Grounded Knowledge Graphs for Intelligent Threat Analytics in Industry~5.0 Cyber-Physical Systems
- CKG-LLM: LLM-Assisted Detection of Smart Contract Access Control Vulnerabilities Based on Knowledge Graphs
- Knowledge-driven Site Selection via Urban Knowledge Graph
- Lumos: Let there be Language Model System Certification
- Counting Still Counts: Understanding Neural Complex Query Answering Through Query Relaxation
- OntoMetric: An Ontology-Guided Framework for Automated ESG Knowledge Graph Construction
- Fostering Innovation: Streamlining Magnetocaloric Materials Research by Digitalization
- Efficient Multi-Hop Question Answering over Knowledge Graphs via LLM Planning and Embedding-Guided Search
- AI- and Ontology-Based Enhancements to FMEA for Advanced Systems Engineering: Current Developments and Future Directions
- Learning to Debug: LLM-Organized Knowledge Trees for Solving RTL Assertion Failures
- Systematic Reconstruction of Disease Networks from Longitudinal Blood Data for Causal Discovery and Intervention Analysis
- FuseSampleAgg: Fused Neighbor Sampling and Aggregation for Mini-batch GNNs
- Learning to Refine: An Agentic RL Approach for Iterative SPARQL Query Construction
- Improving Graph Embeddings in Machine Learning Using Knowledge Completion with Validation in a Case Study on COVID-19 Spread
- Unlocking Advanced Graph Machine Learning Insights through Knowledge Completion on Neo4j Graph Database
- AI Agent-Driven Framework for Automated Product Knowledge Graph Construction in E-Commerce
- Graph-Memoized Reasoning: Foundations Structured Workflow Reuse in Intelligent Systems
- MetaConfigurator: AI-Assisted RDF Authoring from JSON Data
- A Multi-Agent System for Semantic Mapping of Relational Data to Knowledge Graphs
- LGM: Enhancing Large Language Models with Conceptual Meta-Relations and Iterative Retrieval
- GraphCompliance: Aligning Policy and Context Graphs for LLM-Based Regulatory Compliance
- Monitoring Transformative Technological Convergence Through LLM-Extracted Semantic Entity Triple Graphs
- Parameter Averaging in Link Prediction
- GuidedRAG: Semantic Steering of Retrieval-Augmented Generation
- Large language models for knowledge graph extraction from tables in materials science
- Knowledge graphs for seismic data and metadata
- Improving Human-Robot Teamwork in Urban Search and Rescue Through Episodic Memory of Prior Collaboration
- Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic Cones
- Certainty in Uncertainty: Reasoning over Uncertain Knowledge Graphs with Statistical Guarantees
- Sound Logical Explanations for Mean Aggregation Graph Neural Networks
- Explainable Benchmarking through the Lense of Concept Learning
- Learning Efficient and Generalizable Graph Retriever for Knowledge-Graph Question Answering
- Applicability Assessment of Technologies for Predictive and Prescriptive Analytics of Nephrology Big Data
- Domain-Contextualized Concept Graphs: A Computable Framework for Knowledge Representation
- Multi-dimensional Data Analysis and Applications Basing on LLM Agents and Knowledge Graph Interactions
- Knowledge-Graph Based RAG System Evaluation Framework
- Smart UX-design for Rescue Operations Wearable - A Knowledge Graph Informed Visualization Approach for Information Retrieval in Emergency Situations
- PromoGuardian: Detecting Promotion Abuse Fraud with Multi-Relation Fused Graph Neural Networks
- Aligning Language Models with Investor and Market Behavior for Financial Recommendations
- Improving Knowledge Graph Embeddings through Contrastive Learning with Negative Statements
- Ontolearn-A Framework for Large-scale OWL Class Expression Learning in Python
- KG-MAS: Knowledge Graph-Enhanced Multi-Agent Infrastructure for coupling physical and digital robotic environments
- Unveiling Gamer Archetypes through Multi modal feature Correlations and Unsupervised Learning
- What Do We Mean When We Say “Insight”? A Formal Synthesis of Existing Theory
- REBot: From RAG to CatRAG with Semantic Enrichment and Graph Routing
- MetaboT: An LLM-based Multi-Agent Frameworkfor Interactive Analysis of Mass SpectrometryMetabolomics Knowledge Graphs
- VisPile: A Visual Analytics System for Analyzing Multiple Text Documents With Large Language Models and Knowledge Graphs
- Comparing Knowledge Source Integration Methods for Optimizing Healthcare Knowledge Fusion in Rescue Operation
- KEO: Knowledge Extraction on OMIn via Knowledge Graphs and RAG for Safety-Critical Aviation Maintenance
- Duplication Detection in Knowledge Graphs: Literature and Tools
- Large Language Models Hallucination: A Comprehensive Survey
- Graph-S3: Enhancing Agentic textual Graph Retrieval with Synthetic Stepwise Supervision
- FusionAdapter for Few-Shot Relation Learning in Multimodal Knowledge Graphs
- Type-Less yet Type-Aware Inductive Link Prediction with Pretrained Language Models
- Rescue Operators' Perspectives on KIRETT Wearable Technology: A Qualitative Study
- Agentic Services Computing
- G-reasoner: Foundation Models for Unified Reasoning over Graph-structured Knowledge
- A Computational Perspective on NeuroAI and Synthetic Biological Intelligence
- Knowledge graph validation by integrating LLMs and human-in-the-loop
- Discovering Association Rules in High-Dimensional Small Tabular Data
- Publishing FAIR and machine-actionable reviews in materials science: The case for symbolic knowledge in neuro-symbolic artificial intelligence
- CS-KG 2.0: A Large-scale Knowledge Graph of Computer Science
- Declarative Lifecycle Management for Self-Adaptive Systems
- THGFM: Dual-Branch Temporal Heterogeneous Graph Fusion Model
- Annotation of biological samples data to standard ontologies with support from large language models
- Ontology-Based Knowledge Graph Approach for Legal Queries
- Research hypothesis generation over scientific knowledge graphs
- ARK-V1: An LLM-Agent for Knowledge Graph Question Answering Requiring Commonsense Reasoning
- Automated Knowledge Graph Construction using Large Language Models and Sentence Complexity Modelling
- Causal-Counterfactual RAG: The Integration of Causal-Counterfactual Reasoning into RAG
- A Scenario-Driven Cognitive Approach to Next-Generation AI Memory
- SPARK: Adaptive Low-Rank Knowledge Graph Modeling in Hybrid Geometric Spaces for Recommendation
- Bio-KGvec2go: Serving up-to-date Dynamic Biomedical Knowledge Graph Embeddings
- An Optimized Pipeline for Automatic Educational Knowledge Graph Construction
- An Epidemiological Knowledge Graph extracted from the World Health Organization's Disease Outbreak News
- UrbanInsight: A Distributed Edge Computing Framework with LLM-Powered Data Filtering for Smart City Digital Twins
- Enabling Transparent Cyber Threat Intelligence Combining Large Language Models and Domain Ontologies
- Views: a hardware-friendly graph database model for storing semantic information
- NoteIt: A System Converting Instructional Videos to Interactable Notes Through Multimodal Video Understanding
- ReviewGraph: A Knowledge Graph Embedding Based Framework for Review Rating Prediction with Sentiment Features
- Knowledge Graph Completion for Action Prediction on Situational Graphs -- A Case Study on Household Tasks
- Interactive Query Answering on Knowledge Graphs with Soft Entity Constraints
- Why Settle for Just One? Extending EL++ Ontology Embeddings with Many-to-Many Relationships
- RAGulating Compliance: A Multi-Agent Knowledge Graph for Regulatory QA
- GRainsaCK: a Comprehensive Software Library for Benchmarking Explanations of Link Prediction Tasks on Knowledge Graphs
- KIRETT: Knowledge-Graph-Based Smart Treatment Assistant for Intelligent Rescue Operations
- Large Language Models as Oracles for Ontology Alignment
- Automated Creation of the Legal Knowledge Graph Addressing Legislation on Violence Against Women: Resource, Methodology and Lessons Learned
- A Neurosymbolic Framework for Interpretable Cognitive Attack Detection in Augmented Reality
- mKG-RAG: Multimodal Knowledge Graph-Enhanced RAG for Visual Question Answering
- Difference Views for Visual Graph Query Building
- AgREE: Agentic Reasoning for Knowledge Graph Completion on Emerging Entities
- An Entity Linking Agent for Question Answering
- Data Overdose? Time for a Quadruple Shot: Knowledge Graph Construction using Enhanced Triple Extraction
- The KG-ER Conceptual Schema Language
- Improving Knowledge Graph Understanding with Contextual Views -- Extended
- 5G Core Fault Detection and Root Cause Analysis using Machine Learning and Generative AI
- Ontology-Enhanced Knowledge Graph Completion using Large Language Models
- Query Embedding on Hyper-relational Knowledge Graphs
- The Semantic Units Framework, a technology-agnostic representational approach to FAIR and CLEAR knowledge infrastructures
- Rosetta Statements: simplifying FAIR knowledge graph construction with a user-centred approach
- Full Triple Matcher: Integrating all triple elements between heterogeneous Knowledge Graphs
- PARK: Personalized academic retrieval with knowledge-graphs
- BifrostRAG: Bridging Dual Knowledge Graphs for Multi-Hop Question Answering in Construction Safety
- Creating Knowledge Graphs Subsets using Shape Expressions
- Argumentation meets matrix factorization: A dual perspective for explainable recommendations
- XAI4Wind: A Multimodal Knowledge Graph Database for Explainable Decision Support in Operations & Maintenance of Wind Turbines
- Introducing the Swiss Food Knowledge Graph: AI for Context-Aware Nutrition Recommendation
- Automating SPARQL Query Translations between DBpedia and Wikidata
- CAVA: A Visual Analytics System for Exploratory Columnar Data Augmentation Using Knowledge Graphs
- MountainLion: A Multi-Modal LLM-Based Agent System for Interpretable and Adaptive Financial Trading
- Knowledge Conceptualization Impacts RAG Efficacy
- An Integrated Framework of Prompt Engineering and Multidimensional Knowledge Graphs for Legal Dispute Analysis
- KeyKnowledgeRAG (K2RAG): An Enhanced RAG method for improved LLM question-answering capabilities
- SemRAG: Semantic Knowledge-Augmented RAG for Improved Question-Answering
- HGMP:Heterogeneous Graph Multi-Task Prompt Learning
- SCoRE: Streamlined Corpus-based Relation Extraction using Multi-Label Contrastive Learning and Bayesian kNN
- Concept-Based Mechanistic Interpretability Using Structured Knowledge Graphs
- Constraint Hypergraphs as a Unifying Framework for Digital Twins
- Knowledge Restoration-driven Prompt Optimization: Unlocking LLM Potential for Open-Domain Relational Triplet Extraction
- Physics-Informed Graph Neural Networks for Attack Path Prediction
- Concepts for a Semantically Accessible Materials Data Space: Overview over Specific Implementations in Materials Science
- GRAPHxx: DSML engineering for knowledge graph building and streamlining with GraphRAG
- Flow-Modulated Scoring for Semantic-Aware Knowledge Graph Completion
- Text2Cypher Across Languages: Evaluating and Finetuning LLMs
- Automatic Prompt Optimization for Knowledge Graph Construction: Insights from an Empirical Study
- PyTorch-based Geometric Learning with Non-CUDA Processing Units: Experiences from Intel Gaudi-v2 HPUs
- Integrating Knowledge Graphs and Bayesian Networks: A Hybrid Approach for Explainable Disease Risk Prediction
- Reasoning with RAGged events: RAG-Enhanced Event Knowledge Base Construction and reasoning with proof-assistants
- (De)composing Craft: An Elementary Grammar for Sharing Expertise in Craft Workflows
- From Symbolic to Neural and Back: Exploring Knowledge Graph-Large Language Model Synergies
- T-TExTS (Teaching Text Expansion for Teacher Scaffolding): Enhancing Text Selection in High School Literature through Knowledge Graph-Based Recommendation
- Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models
- An Ontology for Representing Curriculum and Learning Material
- KERAIA: An Adaptive and Explainable Framework for Dynamic Knowledge Representation and Reasoning
- Schema Generation for Large Knowledge Graphs Using Large Language Models
- KARE-RAG: Knowledge-Aware Refinement and Enhancement for RAG
- A Graph-Retrieval-Augmented Generation Framework Enhances Decision-Making in the Circular Economy
- Enhancing Clinical Multiple-Choice Questions Benchmarks with Knowledge Graph Guided Distractor Generation
- DrKGC: Dynamic Subgraph Retrieval-Augmented LLMs for Knowledge Graph Completion across General and Biomedical Domains
- Guiding Generative Storytelling with Knowledge Graphs
- LLM Inference Enhanced by External Knowledge: A Survey
- KGMark: A Diffusion Watermark for Knowledge Graphs
- Complex System Diagnostics Using a Knowledge Graph-Informed and Large Language Model-Enhanced Framework
- Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA
- Streamlining Knowledge Graph Creation with PyRML
- Position: Foundation Models for Tabular Data within Systemic Contexts Need Grounding
- Towards Knowledge Organization Ecosystems
- Self-Reflective Planning with Knowledge Graphs: Enhancing LLM Reasoning Reliability for Question Answering
- SEMMA: A Semantic Aware Knowledge Graph Foundation Model
- Semantic Networks as Clues: A Theoretical Foundation and Process Optimization for Semantic Network Construction
- How do Scaling Laws Apply to Knowledge Graph Engineering Tasks? The Impact of Model Size on Large Language Model Performance
- The Role of Visualization in LLM-Assisted Knowledge Graph Systems: Effects on User Trust, Exploration, and Workflows
- Self-Reinforced Graph Contrastive Learning
- MRM3: Machine Readable ML Model Metadata
- Q2Forge: Minting Competency Questions and SPARQL Queries for Question-Answering Over Knowledge Graphs
- GDPRShield: AI-Powered GDPR Support for Software Developers in Small and Medium-Sized Enterprises
- Fully Geometric Multi-Hop Reasoning on Knowledge Graphs with Transitive Relations
- HYPERMATRIX ALGEBRA AND IRREDUCIBLE ARITY IN HIGHER-ORDER SYSTEMS: CONCEPTS AND PERSPECTIVES
- MPRM: A Markov Path-based Rule Miner for Efficient and Interpretable Knowledge Graph Reasoning
- The Violation Situation Pattern: Persistent Representation of Compliance Violations in Knowledge Graphs
- SparseMeXT Unlocking the Potential of Sparse Representations for HD Map Construction
- Causal knowledge graph analysis identifies adverse drug effects
- A Grounded Memory System For Smart Personal Assistants
- Enhancing Text2Cypher with Schema Filtering
- Co-Designing a Knowledge Graph Navigation Interface: A Participatory Approach
- IdeaForge: A Knowledge Graph-Grounded Multi-Agent Framework for Cross-Methodology Innovation Analysis and Patent Claim Generation
- Structured Linked Data as a Memory Layer for Agent-Orchestrated Retrieval
- Graph-based Agent Memory: Taxonomy, Techniques, and Applications
- LLM Agents in Law: Taxonomy, Applications, and Challenges
- tmQM-RDF Data Set: A Knowledge Graph Representing Transition Metal Complexes
- An Interaction Language Model: Mechanism Discovery from Statistical Patterns of Physical Interactions
- From Line Knowledge Digraphs to Sheaf Semantics: A Categorical Framework for Knowledge Graphs
- Structural Hallucination in Large Language Models: A Network-Based Evaluation of Knowledge Organization and Citation Integrity
- Towards a format for describing networks / 1. Networks and knowledge graphs
- Towards a format for describing networks / 2. Format elements
- They Think AI Can Do More Than It Actually Can: Practices, Challenges, & Opportunities of AI-Supported Reporting In Local Journalism
- SkillNet: Create, Evaluate, and Connect AI Skills
- Efficiency of Analysis of Transitive Relations using Query-Driven, Ground-and-Solve, and Fact-Driven Inference
- Rethinking the production and publication of machine-reusable expressions of research findings
- MRMS: A Multi-Resolution Memory Substrate for Long-Lived AI Agents
- Context Graphs for Proactive Enterprise Agents
- A Survey of Task-Oriented Knowledge Graph Reasoning: Status, Applications, and Prospects
- Exploring a Large Language Model for Transforming Taxonomic Data into OWL: Lessons Learned and Implications for Ontology Development
- Evaluating Evaluation Metrics -- The Mirage of Hallucination Detection
- Enactive Artificial Intelligence: A Decision-Centric Architecture for Complex Systems
- The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and Learning
- Ontologies in digital twins: A systematic literature review
- Emergence and maintenance of modularity in neural networks with Hebbian and anti-Hebbian inhibitory STDP
- Mitigating LLM Hallucinations with Knowledge Graphs: A Case Study
- Improving Interoperability among Defence and National Security Ontologies: Analysis and Evaluation Tasks
- Siren Federate: Bridging document, relational, and graph models for exploratory graph analysis
- LExT: Towards Evaluating Trustworthiness of Natural Language Explanations
- Decentralizing AI Memory: SHIMI, a Semantic Hierarchical Memory Index for Scalable Agent Reasoning
- Neo4j [wikipedia]
Discussions
Related