A Survey on Knowledge Graphs: Representation, Acquisition and Applications

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 libraries on different tasks. In the end, we have a thorough outlook on several promising research directions.

References in corpus (49)

• KGAT: Knowledge Graph Attention Network for Recommendation
• A Review of Relational Machine Learning for Knowledge Graphs
• Complex Embeddings for Simple Link Prediction
• A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network
• ConceptNet 5.5: An Open Multilingual Graph of General Knowledge
• ERNIE: Enhanced Representation through Knowledge Integration
• RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
• TuckER: Tensor Factorization for Knowledge Graph Completion
• Large-scale Simple Question Answering with Memory Networks
• Reinforcement Knowledge Graph Reasoning for Explainable Recommendation
• Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning
• SimplE Embedding for Link Prediction in Knowledge Graphs
• KG-BERT: BERT for Knowledge Graph Completion
• Quaternion Knowledge Graph Embeddings
• A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs
• Analogical Inference for Multi-Relational Embeddings
• Hypernetwork Knowledge Graph Embeddings
• DKN: Deep Knowledge-Aware Network for News Recommendation
• Reinforcement Learning for Relation Classification from Noisy Data
• Variational Reasoning for Question Answering with Knowledge Graph
• ProjE: Embedding Projection for Knowledge Graph Completion
• Interaction Embeddings for Prediction and Explanation in Knowledge Graphs
• Tensor Decompositions for temporal knowledge base completion
• End-to-End Differentiable Proving
• SSP: Semantic Space Projection for Knowledge Graph Embedding with Text Descriptions
• TransA: An Adaptive Approach for Knowledge Graph Embedding
• A Neural Knowledge Language Model
• Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs
• Multi-Grained Named Entity Recognition
• Probabilistic Logic Neural Networks for Reasoning
• Leveraging Deep Neural Networks and Knowledge Graphs for Entity Disambiguation
• Probabilistic Reasoning via Deep Learning: Neural Association Models
• CoKE: Contextualized Knowledge Graph Embedding
• Relation Embedding with Dihedral Group in Knowledge Graph
• Few-shot Relation Extraction via Bayesian Meta-learning on Relation Graphs
• End-to-end Structure-Aware Convolutional Networks for Knowledge Base Completion
• M-Walk: Learning to Walk over Graphs using Monte Carlo Tree Search
• Knowledge Questions from Knowledge Graphs
• On Multi-Relational Link Prediction with Bilinear Models
• Integrating Graph Contextualized Knowledge into Pre-trained Language Models
• Efficient Probabilistic Logic Reasoning with Graph Neural Networks
• A Frustratingly Easy Approach for Entity and Relation Extraction
• Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction
• Inductive Representation Learning on Temporal Graphs
• Multi-relational Poincaré Graph Embeddings
• Knowledge Representation Learning: A Quantitative Review
• Probability Calibration for Knowledge Graph Embedding Models
• Knowledge-driven Encode, Retrieve, Paraphrase for Medical Image Report Generation
• LowFER: Low-rank Bilinear Pooling for Link Prediction

Cited by in corpus (173)

• Knowledge Graphs
• Unifying Large Language Models and Knowledge Graphs: A Roadmap
• Graph Self-Supervised Learning: A Survey
• A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs
• A Survey of Knowledge-Enhanced Text Generation
• Knowledge Graphs in Manufacturing and Production: A Systematic Literature Review
• Knowledge Graph Contrastive Learning Based on Relation-Symmetrical Structure
• Neural Entity Linking: A Survey of Models Based on Deep Learning
• Knowledge Graph Reasoning with Relational Digraph
• Bringing Light Into the Dark: A Large-scale Evaluation of Knowledge Graph Embedding Models Under a Unified Framework
• Anomaly Detection in Dynamic Graphs via Transformer
• BERT Based Clinical Knowledge Extraction for Biomedical Knowledge Graph Construction and Analysis
• Temporal and Heterogeneous Graph Neural Network for Financial Time Series Prediction
• Graph Convolutional Networks for Graphs Containing Missing Features
• Machine Knowledge: Creation and Curation of Comprehensive Knowledge Bases
• Comprehensive evaluation of deep and graph learning on drug-drug interactions prediction
• Self-Supervised Temporal Graph learning with Temporal and Structural Intensity Alignment
• Applications of knowledge graphs for food science and industry
• EvoKG: Jointly Modeling Event Time and Network Structure for Reasoning over Temporal Knowledge Graphs
• Unlocking the Emotional World of Visual Media: An Overview of the Science, Research, and Impact of Understanding Emotion
• Engineering Semantic Communication: A Survey
• Construction of Knowledge Graphs: State and Challenges
• Representation Learning for Natural Language Processing
• Time-aware Path Reasoning on Knowledge Graph for Recommendation
• Explainability in Music Recommender Systems
• Abstractive Text Summarization: State of the Art, Challenges, and Improvements
• Graph Neural Networks for Natural Language Processing: A Survey
• Understanding the Performance of Knowledge Graph Embeddings in Drug Discovery
• Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metrics
• Trans4E: Link Prediction on Scholarly Knowledge Graphs
• Relphormer: Relational Graph Transformer for Knowledge Graph Representations
• WiserVR: Semantic Communication Enabled Wireless Virtual Reality Delivery
• Neurosymbolic Reinforcement Learning and Planning: A Survey
• Probabilistic Semantic Communication over Wireless Networks with Rate Splitting
• Towards Next-Generation Urban Decision Support Systems through AI-Powered Construction of Scientific Ontology using Large Language Models -- A Case in Optimizing Intermodal Freight Transportation
• Neuromorphic Camera Denoising using Graph Neural Network-driven Transformers
• Neurosymbolic AI for Reasoning over Knowledge Graphs: A Survey
• A new communication paradigm: from bit accuracy to semantic fidelity
• KnowledgeNavigator: Leveraging Large Language Models for Enhanced Reasoning over Knowledge Graph
• Normalizing Flow-based Neural Process for Few-Shot Knowledge Graph Completion
• Modifying Memories in Transformer Models
• A Unified Review of Deep Learning for Automated Medical Coding
• CORE: A Knowledge Graph Entity Type Prediction Method via Complex Space Regression and Embedding
• Superpixel perception graph neural network for intelligent defect detection of aero-engine blade
• Knowledge Graphs in the Digital Twin: A Systematic Literature Review About the Combination of Semantic Technologies and Simulation in Industrial Automation
• Deep learning for dynamic graphs: models and benchmarks
• Heterogeneous Network Representation Learning: A Unified Framework with Survey and Benchmark
• Link Prediction with Attention Applied on Multiple Knowledge Graph Embedding Models
• Semantic Communication with Probability Graph: A Joint Communication and Computation Design
• Knowledge Graphs and Pre-trained Language Models enhanced Representation Learning for Conversational Recommender Systems
• Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learning
• Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks
• A Joint Communication and Computation Design for Semantic Wireless Communication with Probability Graph
• Empathetic Response Generation through Graph-based Multi-hop Reasoning on Emotional Causality
• Large-scale Entity Alignment via Knowledge Graph Merging, Partitioning and Embedding
• Uncovering CWE-CVE-CPE Relations with Threat Knowledge Graphs
• Geometric Algebra based Embeddings for Static and Temporal Knowledge Graph Completion
• A Survey of Knowledge Enhanced Pre-trained Models
• Artificial Intelligence-based algorithms in medical image scan seg-mentation and intelligent visual-content generation -- a concise overview
• VN Network: Embedding Newly Emerging Entities with Virtual Neighbors
• Towards Graph Self-Supervised Learning with Contrastive Adjusted Zooming
• FinDKG: Dynamic Knowledge Graphs with Large Language Models for Detecting Global Trends in Financial Markets
• Schema-aware Reference as Prompt Improves Data-Efficient Knowledge Graph Construction
• Unstructured Text Enhanced Open-domain Dialogue System: A Systematic Survey
• Path-based Explanation for Knowledge Graph Completion
• Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Games
• Inductive Meta-path Learning for Schema-complex Heterogeneous Information Networks
• Improving Hyper-Relational Knowledge Graph Completion
• Multi-source Education Knowledge Graph Construction and Fusion for College Curricula
• nuScenes Knowledge Graph -- A comprehensive semantic representation of traffic scenes for trajectory prediction
• Representation Learning on Hyper-Relational and Numeric Knowledge Graphs with Transformers
• Deep Outdated Fact Detection in Knowledge Graphs
• Counterfactual Learning on Graphs: A Survey
• Logical Reasoning with Relation Network for Inductive Knowledge Graph Completion
• Pre-Training and Prompting for Few-Shot Node Classification on Text-Attributed Graphs
• Knowledge-Enhanced Conversational Recommendation via Transformer-based Sequential Modelling
• Learning Representations of Bi-level Knowledge Graphs for Reasoning beyond Link Prediction
• NodePiece: Compositional and Parameter-Efficient Representations of Large Knowledge Graphs
• Clinical Relation Extraction Using Transformer-based Models
• Towards Complex Dynamic Physics System Simulation with Graph Neural ODEs
• Knowledge-Aware Semantic Communication System Design and Data Allocation
• Advancing Biomedicine with Graph Representation Learning: Recent Progress, Challenges, and Future Directions
• Knowledge-Aware Semantic Communication System Design
• Knowledge-driven Site Selection via Urban Knowledge Graph
• Automatic Expansion of Domain-Specific Affective Models for Web Intelligence Applications
• Label Informed Contrastive Pretraining for Node Importance Estimation on Knowledge Graphs
• From Semantic Communication to Semantic-aware Networking: Model, Architecture, and Open Problems
• High-quality Task Division for Large-scale Entity Alignment
• Acquiring and Modelling Abstract Commonsense Knowledge via Conceptualization
• Logic Augmented Generation
• KGBoost: A Classification-based Knowledge Base Completion Method with Negative Sampling
• An Epidemiological Knowledge Graph extracted from the World Health Organization's Disease Outbreak News
• A Knowledge Graph based Approach for Mobile Application Recommendation
• Role-Aware Modeling for N-ary Relational Knowledge Bases
• PromptORE -- A Novel Approach Towards Fully Unsupervised Relation Extraction
• Adaptive Attentional Network for Few-Shot Knowledge Graph Completion
• On the Impact of Knowledge-based Linguistic Annotations in the Quality of Scientific Embeddings
• Relevant Entity Selection: Knowledge Graph Bootstrapping via Zero-Shot Analogical Pruning
• AutoETER: Automated Entity Type Representation for Knowledge Graph Embedding
• Link Prediction on N-ary Relational Facts: A Graph-based Approach
• LMKG: Learned Models for Cardinality Estimation in Knowledge Graphs
• A Survey of Knowledge Graph Embedding and Their Applications
• BedreFlyt: Improving Patient Flows through Hospital Wards with Digital Twins
• QAEA-DR: A Unified Text Augmentation Framework for Dense Retrieval
• Knowledge-Enhanced Recommendation with User-Centric Subgraph Network
• Term-community-based topic detection with variable resolution
• Improving Federated Relational Data Modeling via Basis Alignment and Weight Penalty
• Abstraction Alignment: Comparing Model-Learned and Human-Encoded Conceptual Relationships
• Automatic Semantic Modeling for Structural Data Source with the Prior Knowledge from Knowledge Base
• Triplètoile: Extraction of Knowledge from Microblogging Text
• Duplication Detection in Knowledge Graphs: Literature and Tools
• Action Class Relation Detection and Classification Across Multiple Video Datasets
• Faithfully Explainable Recommendation via Neural Logic Reasoning
• Knowledge Graph Refinement based on Triplet BERT-Networks
• Temporal Knowledge Graph Reasoning Triggered by Memories
• Query Embedding on Hyper-relational Knowledge Graphs
• Out-of-Vocabulary Entities in Link Prediction
• A Robust and Generalized Framework for Adversarial Graph Embedding
• Dynamic Relation Repairing for Knowledge Enhancement
• Neural, Symbolic and Neural-Symbolic Reasoning on Knowledge Graphs
• Towards Feature Engineering with Human and AI's Knowledge: Understanding Data Science Practitioners' Perceptions in Human&AI-Assisted Feature Engineering Design
• Drug-Drug Interaction Prediction with Wasserstein Adversarial Autoencoder-based Knowledge Graph Embeddings
• Automating IRAC Analysis in Malaysian Contract Law using a Semi-Structured Knowledge Base
• AutoMathKG: The automated mathematical knowledge graph based on LLM and vector database
• Str-GCL: Structural Commonsense Driven Graph Contrastive Learning
• Locality Preserving Dense Graph Convolutional Networks with Graph Context-Aware Node Representations
• Training like Playing: A Reinforcement Learning And Knowledge Graph-based framework for building Automatic Consultation System in Medical Field
• NLP for Climate Policy: Creating a Knowledge Platform for Holistic and Effective Climate Action
• Billion-scale Pre-trained E-commerce Product Knowledge Graph Model
• Semantic data discovery from Social Big Data
• Disentangle-based Continual Graph Representation Learning
• NASE: Learning Knowledge Graph Embedding for Link Prediction via Neural Architecture Search
• Enhancing Cross-Modal Contextual Congruence for Crowdfunding Success using Knowledge-infused Learning
• Few-shot Knowledge Graph-to-Text Generation with Pretrained Language Models
• Recent Advances in Automated Question Answering In Biomedical Domain
• Knowing the No-match: Entity Alignment with Dangling Cases
• Current Challenges and Future Directions in Podcast Information Access
• HopfE: Knowledge Graph Representation Learning using Inverse Hopf Fibrations
• FAIR GraphRAG: A Retrieval-Augmented Generation Approach for Semantic Data Analysis
• Synergizing LLMs and Knowledge Graphs: A Novel Approach to Software Repository-Related Question Answering
• Effective FAQ Retrieval and Question Matching With Unsupervised Knowledge Injection
• A Data-Driven Study of Commonsense Knowledge using the ConceptNet Knowledge Base
• AI Marker-based Large-scale AI Literature Mining
• DisenE: Disentangling Knowledge Graph Embeddings
• The Knowledge Graph for Macroeconomic Analysis with Alternative Big Data
• PPKE: Knowledge Representation Learning by Path-based Pre-training
• Comprehensive Event Representations using Event Knowledge Graphs and Natural Language Processing
• Hyperownership: Beyond the Current State of Interaction with Digital Property
• Textual Entailment for Effective Triple Validation in Object Prediction
• Analyzing the Influence of Knowledge Graph Information on Relation Extraction
• DISCIE -- Discriminative Closed Information Extraction
• Mutual Teaching for Graph Convolutional Networks
• VisualSem: A High-quality Knowledge Graph for Vision and Language
• Improving Continual Learning of Knowledge Graph Embeddings via Informed Initialization
• Link Prediction or Perdition: the Seeds of Instability in Knowledge Graph Embeddings
• Revisit Systematic Generalization via Meaningful Learning
• Narrative Cartography with Knowledge Graphs
• Knowledge graphs for empirical concept retrieval
• Towards Top-Down Automated Development in Limited Scopes: A Neuro-Symbolic Framework from Expressibles to Executables
• Multi-modal Entity Alignment in Hyperbolic Space
• Low-Resource Named Entity Recognition Based on Multi-hop Dependency Trigger
• HYPER^2: Hyperbolic Poincare Embedding for Hyper-Relational Link Prediction
• Multilingual Knowledge Graph Completion via Ensemble Knowledge Transfer
• Learning Syntactic Dense Embedding with Correlation Graph for Automatic Readability Assessment
• Causal Discovery in Knowledge Graphs by Exploiting Asymmetric Properties of Non-Gaussian Distributions
• Scalable Construction of a Lung Cancer Knowledge Base: Profiling Semantic Reasoning in LLMs
• A Fully Automated DM-BIM-BEM Pipeline Enabling Graph-Based Intelligence, Interoperability, and Performance-Driven Early Design
• Using Meta-Knowledge Mined from Identifiers to Improve Intent Recognition in Neuro-Symbolic Algorithms
• R2D2: Relational Text Decoding with Transformers
• Dual Graph Embedding for Object-Tag LinkPrediction on the Knowledge Graph
• Understood in Translation, Transformers for Domain Understanding
• Decoding Virtual Healthcare Success through Knowledge-Aware and Multimodal Predictive Modeling
• Automatic Knowledge Extraction with Human Interface