mlsanityData to 7 Oct 2026

Traversing Knowledge Graphs in Vector Space

arXiv 1506.01094 ↗First posted 3 Jun 2015cs.CL cs.AI cs.DBcited by 51

Not on the map. Why?

Abstract (arXiv)

Path queries on a knowledge graph can be used to answer compositional questions such as "What languages are spoken by people living in Lisbon?". However, knowledge graphs often have missing facts (edges) which disrupts path queries. Recent models for knowledge base completion impute missing facts by embedding knowledge graphs in vector spaces. We show that these models can be recursively applied to answer path queries, but that they suffer from cascading errors. This motivates a new "compositional" training objective, which dramatically improves all models' ability to answer path queries, in some cases more than doubling accuracy. On a standard knowledge base completion task, we also demonstrate that compositional training acts as a novel form of structural regularization, reliably improving performance across all base models (reducing errors by up to 43%) and achieving new state-of-the-art results.

Key facts. Cited by 51 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Jun 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 20; 2022: 10; 2023: 10; 2024: 7; 2025: 2; 2026: 2.

51 papers.

Sort:

By area:

  1. 2021QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answeringcited by 386
  2. 2021ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphscited by 78
  3. 2022Neural-Symbolic Models for Logical Queries on Knowledge Graphscited by 60
  4. 2024CiteME: Can Language Models Accurately Cite Scientific Claims?cited by 45
  5. 2023Neural Graph Reasoning: Complex Logical Query Answering Meets Graph Databasescited by 35
  6. 2022Answering Complex Logical Queries on Knowledge Graphs via Query Computation Tree Optimizationcited by 28
  7. 2021Neuro-Symbolic Hierarchical Rule Inductioncited by 23
  8. 2022GammaE: Gamma Embeddings for Logical Queries on Knowledge Graphscited by 21
  9. 2022Knowledge Graph Reasoning with Logics and Embeddings: Survey and Perspectivecited by 18
  10. 2021Logic Embeddings for Complex Query Answeringcited by 17
  11. 2021SMORE: Knowledge Graph Completion and Multi-hop Reasoning in Massive Knowledge Graphscited by 17
  12. 2022Neural Methods for Logical Reasoning Over Knowledge Graphscited by 17
38 more
  1. 2025Logic Jailbreak: Efficiently Unlocking LLM Safety Restrictions Through Formal Logical Expressioncited by 16
  2. 2021Link Prediction on N-ary Relational Data Based on Relatedness Evaluationcited by 15
  3. 2022Joint Language Semantic and Structure Embedding for Knowledge Graph Completioncited by 15
  4. 2023UKnow: A Unified Knowledge Protocol with Multimodal Knowledge Graph Datasets for Reasoning and Vision-Language Pre-Trainingcited by 14
  5. 2021Poisoning Knowledge Graph Embeddings via Relation Inference Patternscited by 12
  6. 2021Bilinear Scoring Function Search for Knowledge Graph Learningcited by 11
  7. 2021Fuzzy Logic Based Logical Query Answering on Knowledge Graphscited by 11
  8. 2021SQALER: Scaling Question Answering by Decoupling Multi-Hop and Logical Reasoningcited by 10
  9. 2025Contextualizing biological perturbation experiments through languagecited by 10
  10. 2021Knowledge Sheaves: A Sheaf-Theoretic Framework for Knowledge Graph Embeddingcited by 9
  11. 2024Is Complex Query Answering Really Complex?cited by 7
  12. 2023On the Security Risks of Knowledge Graph Reasoningcited by 5
  13. 2021Integrating Approaches to Word Representationcited by 4
  14. 2022Cross-Domain Aspect Extraction using Transformers Augmented with Knowledge Graphscited by 4
  15. 2023Principled and Efficient Motif Finding for Structure Learning of Lifted Graphical Modelscited by 4
  16. 2023DREAM: Adaptive Reinforcement Learning based on Attention Mechanism for Temporal Knowledge Graph Reasoningcited by 4
  17. 2023Inductive Meta-path Learning for Schema-complex Heterogeneous Information Networkscited by 4
  18. 2023Query2Triple: Unified Query Encoding for Answering Diverse Complex Queries over Knowledge Graphscited by 4
  19. 2021Knowledge Graph Embedding in E-commerce Applications: Attentive Reasoning, Explanations, and Transferable Rulescited by 3
  20. 2022CoSe-Co: Text Conditioned Generative CommonSense Contextualizercited by 3
  21. 2023Query Structure Modeling for Inductive Logical Reasoning Over Knowledge Graphscited by 3
  22. 2024Knowledge Graph Reasoning with Self-supervised Reinforcement Learningcited by 3
  23. 2023Efficient Learning of Discrete-Continuous Computation Graphscited by 2
  24. 2024Walk Wisely on Graph: Knowledge Graph Reasoning with Dual Agents via Efficient Guidance-Explorationcited by 2
  25. 2021An Adversarial Transfer Network for Knowledge Representation Learningcited by 1
  26. 2021Transductive Data Augmentation with Relational Path Rule Mining for Knowledge Graph Embeddingcited by 1
  27. 2021Discovering Supply Chain Links with Augmented Intelligencecited by 1
  28. 2024Pathformer: Recursive Path Query Encoding for Complex Logical Query Answeringcited by 1
  29. 2021Swarm Differential Privacy for Purpose Driven Data-Information-Knowledge-Wisdom Architecturecited by 0
  30. 2021Recent Advances in Automated Question Answering In Biomedical Domaincited by 0
  31. 2021An original model for multi-target learning of logical rules for knowledge graph reasoningcited by 0
  32. 2021DegreEmbed: incorporating entity embedding into logic rule learning for knowledge graph reasoningcited by 0
  33. 2022Learning Attention-based Representations from Multiple Patterns for Relation Prediction in Knowledge Graphscited by 0
  34. 2022Adversarial Robustness of Representation Learning for Knowledge Graphscited by 0
  35. 2023Logic Diffusion for Knowledge Graph Reasoningcited by 0
  36. 2024Efficient Parallel Multi-Hop Reasoning: A Scalable Approach for Knowledge Graph Analysiscited by 0
  37. 2024Reinforcement Learning Discovers Efficient Decentralized Graph Path Search Strategiescited by 0
  38. 2026Holographic Memory for Zero-Shot Compositional Reasoning in Knowledge Graphs: A Mechanistic Study of Where and Why It Failscited by 0

50 most cited of 51 All 51 (JSON)