A Survey of Task-Oriented Knowledge Graph Reasoning: Status, Applications, and Prospects
2025/04/27 by Guanglin Niu, Bo Li, Niu, Guanglin +3
Computer Science · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #Cognitive Computing and Networks #Computation and Language (cs.CL) #FOS: Computer and information sciences #I.2.7 #Semantic Web and Ontologies
paper · pdf · doi:10.48550/arxiv.2506.11012
openalex publication_date 2025/04/27 · openalex created_date 2025/10/11 · openalex updated_date 2026/07/28
Abstract
Knowledge graphs (KGs) have emerged as a powerful paradigm for structuring and leveraging diverse real-world knowledge, which serve as a fundamental technology for enabling cognitive intelligence systems with advanced understanding and reasoning capabilities. Knowledge graph reasoning (KGR) aims to infer new knowledge based on existing facts in KGs, playing a crucial role in applications such as public security intelligence, intelligent healthcare, and financial risk assessment. From a task-centric perspective, existing KGR approaches can be broadly classified into static single-step KGR, static multi-step KGR, dynamic KGR, multi-modal KGR, few-shot KGR, and inductive KGR. While existing surveys have covered these six types of KGR tasks, a comprehensive review that systematically summarizes all KGR tasks particularly including downstream applications and more challenging reasoning paradigms remains lacking. In contrast to previous works, this survey provides a more comprehensive perspective on the research of KGR by categorizing approaches based on primary reasoning tasks, downstream application tasks, and potential challenging reasoning tasks. Besides, we explore advanced techniques, such as large language models (LLMs), and their impact on KGR. This work aims to highlight key research trends and outline promising future directions in the field of KGR.
Citations
- Diffusion-based Hierarchical Negative Sampling for Multimodal Knowledge Graph Completion
- Large Language Models-guided Dynamic Adaptation for Temporal Knowledge Graph Reasoning
- From Local to Global: A Graph RAG Approach to Query-Focused Summarization
- Find The Gap: Knowledge Base Reasoning For Visual Question Answering
- Self-Improvement Programming for Temporal Knowledge Graph Question Answering
- NativE: Multi-modal Knowledge Graph Completion in the Wild
- Towards Continual Knowledge Graph Embedding via Incremental Distillation
- HiKER-SGG: Hierarchical Knowledge Enhanced Robust Scene Graph Generation
- Multi-perspective Improvement of Knowledge Graph Completion with Large Language Models
- A Survey on Temporal Knowledge Graph: Representation Learning and Applications
- Negative Sampling in Knowledge Graph Representation Learning: A Review
- Two-stage Generative Question Answering on Temporal Knowledge Graph Using Large Language Models
- Chain-of-History Reasoning for Temporal Knowledge Graph Forecasting
- TILP: Differentiable Learning of Temporal Logical Rules on Knowledge Graphs
- KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph
- Direct Evaluation of Chain-of-Thought in Multi-hop Reasoning with Knowledge Graphs
- GLaM: Fine-Tuning Large Language Models for Domain Knowledge Graph Alignment via Neighborhood Partitioning and Generative Subgraph Encoding
- Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey
- Chain of History: Learning and Forecasting with LLMs for Temporal Knowledge Graph Completion
- Advancing Abductive Reasoning in Knowledge Graphs through Complex Logical Hypothesis Generation
- TEILP: Time Prediction over Knowledge Graphs via Logical Reasoning
- Beyond Transduction: A Survey on Inductive, Few Shot, and Zero Shot Link Prediction in Knowledge Graphs
- zrLLM: Zero-Shot Relational Learning on Temporal Knowledge Graphs with Large Language Models
- AgentTuning: Enabling Generalized Agent Abilities for LLMs
- KG-GPT: A General Framework for Reasoning on Knowledge Graphs Using Large Language Models
- GenTKG: Generative Forecasting on Temporal Knowledge Graph with Large Language Models
- Making Large Language Models Perform Better in Knowledge Graph Completion
- Knowledge Solver: Teaching LLMs to Search for Domain Knowledge from Knowledge Graphs
- ChatRule: Mining Logical Rules with Large Language Models for Knowledge Graph Reasoning
- Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answering
- A Survey on Temporal Knowledge Graph Completion: Taxonomy, Progress, and Prospects
- Structure Guided Multi-modal Pre-trained Transformer for Knowledge Graph Reasoning
- Dipping PLMs Sauce: Bridging Structure and Text for Effective Knowledge Graph Completion via Conditional Soft Prompting
- Unifying Large Language Models and Knowledge Graphs: A Roadmap
- Temporal Knowledge Graph Forecasting Without Knowledge Using In-Context Learning
- StructGPT: A General Framework for Large Language Model to Reason over Structured Data
- Pre-trained Language Model with Prompts for Temporal Knowledge Graph Completion
- Complex Logical Reasoning over Knowledge Graphs using Large Language Models
- Improving Few-Shot Inductive Learning on Temporal Knowledge Graphs using Confidence-Augmented Reinforcement Learning
- Inductive Relation Prediction from Relational Paths and Context with Hierarchical Transformers
- Pre-training Transformers for Knowledge Graph Completion
- Generalizing to Unseen Elements: A Survey on Knowledge Extrapolation for Knowledge Graphs
- A Survey On Few-shot Knowledge Graph Completion with Structural and Commonsense Knowledge
- A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodal
- Logic and Commonsense-Guided Temporal Knowledge Graph Completion
- Lifelong Embedding Learning and Transfer for Growing Knowledge Graphs
- Relation-dependent Contrastive Learning with Cluster Sampling for Inductive Relation Prediction
- Few-Shot Inductive Learning on Temporal Knowledge Graphs using Concept-Aware Information
- Knowledge Graph Embedding: A Survey from the Perspective of Representation Spaces
- RAILD: Towards Leveraging Relation Features for Inductive Link Prediction In Knowledge Graphs
- Bi-Link: Bridging Inductive Link Predictions from Text via Contrastive Learning of Transformers and Prompts
- RulE: Knowledge Graph Reasoning with Rule Embedding
- MoSE: Modality Split and Ensemble for Multimodal Knowledge Graph Completion
- Learning to Sample and Aggregate: Few-shot Reasoning over Temporal Knowledge Graphs
- Entity Aware Negative Sampling with Auxiliary Loss of False Negative Prediction for Knowledge Graph Embedding
- Construction and Applications of Billion-Scale Pre-Trained Multimodal Business Knowledge Graph
- Walk-and-Relate: A Random-Walk-based Algorithm for Representation Learning on Sparse Knowledge Graphs
- Ruleformer: Context-aware Differentiable Rule Mining over Knowledge Graph
- Disconnected Emerging Knowledge Graph Oriented Inductive Link Prediction
- MMKGR: Multi-hop Multi-modal Knowledge Graph Reasoning
- Hierarchical Relational Learning for Few-Shot Knowledge Graph Completion
- Inductive Knowledge Graph Reasoning for Multi-batch Emerging Entities
- KRACL: Contrastive Learning with Graph Context Modeling for Sparse Knowledge Graph Completion
- μKG: A Library for Multi-source Knowledge Graph Embeddings and Applications
- Subgraph Neighboring Relations Infomax for Inductive Link Prediction on Knowledge Graphs
- Disentangled Ontology Embedding for Zero-shot Learning
- A*Net: A Scalable Path-based Reasoning Approach for Knowledge Graphs
- A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities
- Exploring Entity Interactions for Few-Shot Relation Learning (Student Abstract)
- Hypergraph Transformer: Weakly-supervised Multi-hop Reasoning for Knowledge-based Visual Question Answering
- ECOLA: Enhanced Temporal Knowledge Embeddings with Contextualized Language Representations
- LEMON: LanguagE ModeL for Negative Sampling of Knowledge Graph Embeddings
- SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Models
- NeuralKG: An Open Source Library for Diverse Representation Learning of Knowledge Graphs
- CAKE: A Scalable Commonsense-Aware Framework For Multi-View Knowledge Graph Completion
- Knowledge Graph Reasoning with Logics and Embeddings: Survey and Perspective
- A Critical Review of Inductive Logic Programming Techniques for Explainable AI
- Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Survey
- TLogic: Temporal Logical Rules for Explainable Link Forecasting on Temporal Knowledge Graphs
- TempoQR: Temporal Question Reasoning over Knowledge Graphs
- Knowledge Graph Embedding in E-commerce Applications: Attentive Reasoning, Explanations, and Transferable Rules
- Perform Like an Engine: A Closed-Loop Neural-Symbolic Learning Framework for Knowledge Graph Inference
- Path-Enhanced Multi-Relational Question Answering with Knowledge Graph Embeddings
- Learning First-Order Rules with Relational Path Contrast for Inductive Relation Reasoning
- Cycle Representation Learning for Inductive Relation Prediction
- Inferring Substitutable and Complementary Products with Knowledge-Aware Path Reasoning based on Dynamic Policy Network
- TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecasting
- Generative Adversarial Networks
- Subgraph-aware Few-Shot Inductive Link Prediction via Meta-Learning
- Graphhopper: Multi-Hop Scene Graph Reasoning for Visual Question\n Answering
- Zero-Shot Scene Graph Relation Prediction through Commonsense Knowledge Integration
- Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction
- Question Answering Over Temporal Knowledge Graphs
- Search from History and Reason for Future: Two-stage Reasoning on Temporal Knowledge Graphs
- Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completion
- TIE: A Framework for Embedding-based Incremental Temporal Knowledge Graph Completion
- Probabilistic Box Embeddings for Uncertain Knowledge Graph Reasoning
- Billion-scale Pre-trained E-commerce Product Knowledge Graph Model
- Inductive Relation Prediction by BERT
- Topology-Aware Correlations Between Relations for Inductive Link Prediction in Knowledge Graphs
- OntoZSL: Ontology-enhanced Zero-shot Learning
- Relation-aware Graph Attention Model With Adaptive Self-adversarial Training
- KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain\n Knowledge-Based VQA
- Communicative Message Passing for Inductive Relation Reasoning
- Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks
- PairRE: Knowledge Graph Embeddings via Paired Relation Vectors
- RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs
- Dynamic Anticipation and Completion for Multi-Hop Reasoning over Sparse Knowledge Graph
- TeRo: A Time-aware Knowledge Graph Embedding via Temporal Rotation
- Inductive Learning on Commonsense Knowledge Graph Completion
- TorchKGE: Knowledge Graph Embedding in Python and PyTorch
- HittER: Hierarchical Transformers for Knowledge Graph Embeddings
- PyKEEN 1.0: A Python Library for Training and Evaluating Knowledge Graph Embeddings
- Fairness-Aware Explainable Recommendation over Knowledge Graphs
- Repurpose Open Data to Discover Therapeutics for COVID-19 using Deep Learning
- DGL-KE: Training Knowledge Graph Embeddings at Scale
- Tensor Decompositions for temporal knowledge base completion
- Realistic Re-evaluation of Knowledge Graph Completion Methods: An Experimental Study
- Knowledge Graphs
- Relational Message Passing for Knowledge Graph Completion
- A Survey on Knowledge Graphs: Representation, Acquisition, and Applications
- Generative Adversarial Zero-Shot Relational Learning for Knowledge Graphs
- Bridging Knowledge Graphs to Generate Scene Graphs
- Few-Shot Knowledge Graph Completion
- Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction
- Rule-Guided Compositional Representation Learning on Knowledge Graphs
- Inductive Relation Prediction by Subgraph Reasoning
- KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation
- A Re-evaluation of Knowledge Graph Completion Methods
- CoKE: Contextualized Knowledge Graph Embedding
- DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphs
- Representation Learning with Ordered Relation Paths for Knowledge Graph\n Completion
- UNITER: UNiversal Image-TExt Representation Learning
- Tackling Long-Tailed Relations and Uncommon Entities in Knowledge Graph Completion
- K-BERT: Enabling Language Representation with Knowledge Graph
- KG-BERT: BERT for Knowledge Graph Completion
- KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning
- VL-BERT: Pre-training of Generic Visual-Linguistic Representations
- LXMERT: Learning Cross-Modality Encoder Representations from Transformers
- Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training
- Distributional Negative Sampling for Knowledge Base Completion
- VisualBERT: A Simple and Performant Baseline for Vision and Language
- ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
- Adapting Meta Knowledge Graph Information for Multi-Hop Reasoning over Few-Shot Relations
- Universal Representation Learning of Knowledge Bases by Jointly Embedding Instances and Ontological Concepts
- A Relational Memory-based Embedding Model for Triple Classification and\n Search Personalization
- Diachronic Embedding for Temporal Knowledge Graph Completion
- Pykg2vec: A Python Library for Knowledge Graph Embedding
- Learning Attention-based Embeddings for Relation Prediction in Knowledge\n Graphs
- Multi-relational Poincaré Graph Embeddings
- Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoning
- Jointly Learning Explainable Rules for Recommendation with Knowledge Graph
- Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks
- EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs
- NSCaching: Simple and Efficient Negative Sampling for Knowledge Graph Embedding
- Logic Attention Based Neighborhood Aggregation for Inductive Knowledge Graph Embedding
- RotatE: Knowledge Graph Embedding by Relational Rotation in Complex\n Space
- Learning Sequence Encoders for Temporal Knowledge Graph Completion
- Embedding Multimodal Relational Data for Knowledge Base Completion
- Multi-Hop Knowledge Graph Reasoning with Reward Shaping
- One-Shot Relational Learning for Knowledge Graphs
- Embedding Models for Episodic Knowledge Graphs
- Incorporating GAN for Negative Sampling in Knowledge Representation Learning
- Variational Knowledge Graph Reasoning
- M-Walk: Learning to Walk over Graphs using Monte Carlo Tree Search
- An Interpretable Reasoning Network for Multi-Relation Question Answering
- Knowledge Graph Embedding with Iterative Guidance from Soft Rules
- GraphGAN: Graph Representation Learning with Generative Adversarial Nets
- Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning
- TorusE: Knowledge Graph Embedding on a Lie Group
- KBGAN: Adversarial Learning for Knowledge Graph Embeddings
- Open-World Knowledge Graph Completion
- DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning
- Best-Effort Inductive Logic Programming via Fine-grained Cost-based Hypothesis Generation
- Convolutional 2D Knowledge Graph Embeddings
- Inductive Representation Learning on Large Graphs
- Poincaré Embeddings for Learning Hierarchical Representations
- Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs
- An Interpretable Knowledge Transfer Model for Knowledge Base Completion
- Modeling Relational Data with Graph Convolutional Networks
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Chains of Reasoning over Entities, Relations, and Text using Recurrent Neural Networks
- Complex Embeddings for Simple Link Prediction
- FVQA: Fact-based Visual Question Answering
- FVQA: Fact-Based Visual Question Answering
- TensorLog: A Differentiable Deductive Database
- Probabilistic Reasoning via Deep Learning: Neural Association Models
- RDF2Rules: Learning Rules from RDF Knowledge Bases by Mining Frequent Predicate Cycles
- From One Point to A Manifold: Knowledge Graph Embedding For Precise Link Prediction
- Explicit Knowledge-based Reasoning for Visual Question Answering
- Holographic Embeddings of Knowledge Graphs
- TransA: An Adaptive Approach for Knowledge Graph Embedding
- Type-Constrained Representation Learning in Knowledge Graphs
- Modeling Relation Paths for Representation Learning of Knowledge Bases
- Compositional Vector Space Models for Knowledge Base Completion
- Embedding Entities and Relations for Learning and Inference in Knowledge Bases
- YAGO2: A spatially and temporally enhanced knowledge base from Wikipedia
- Efficient Estimation of Word Representations in Vector Space
- A Semantic Matching Energy Function for Learning with Multi-relational Data
- Factorizing YAGO
- Learning logical definitions from relations
- What you always wanted to know about Datalog (and never dared to ask)
- Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph
- Meta Relational Learning for Few-Shot Link Prediction in Knowledge Graphs
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Related