# Traversing Knowledge Graphs in Vector Space

arXiv: https://arxiv.org/abs/1506.01094 · HTML: https://mlsanity.com/paper/1506.01094/

## Key facts

- Cited by 51 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jun 2015.

## Built on by (most cited first, 30 of 51)

- [QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering](https://mlsanity.com/paper/2104.06378/) (2021)
- [ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs](https://mlsanity.com/paper/2110.13715/) (2021)
- [Neural-Symbolic Models for Logical Queries on Knowledge Graphs](https://mlsanity.com/paper/2205.10128/) (2022)
- [CiteME: Can Language Models Accurately Cite Scientific Claims?](https://mlsanity.com/paper/2407.12861/) (2024)
- [Neural Graph Reasoning: Complex Logical Query Answering Meets Graph Databases](https://mlsanity.com/paper/2303.14617/) (2023)
- [Answering Complex Logical Queries on Knowledge Graphs via Query Computation Tree Optimization](https://mlsanity.com/paper/2212.09567/) (2022)
- [Neuro-Symbolic Hierarchical Rule Induction](https://mlsanity.com/paper/2112.13418/) (2021)
- [GammaE: Gamma Embeddings for Logical Queries on Knowledge Graphs](https://mlsanity.com/paper/2210.15578/) (2022)
- [Knowledge Graph Reasoning with Logics and Embeddings: Survey and Perspective](https://mlsanity.com/paper/2202.07412/) (2022)
- [Logic Embeddings for Complex Query Answering](https://mlsanity.com/paper/2103.00418/) (2021)
- [SMORE: Knowledge Graph Completion and Multi-hop Reasoning in Massive Knowledge Graphs](https://mlsanity.com/paper/2110.14890/) (2021)
- [Neural Methods for Logical Reasoning Over Knowledge Graphs](https://mlsanity.com/paper/2209.14464/) (2022)
- [Logic Jailbreak: Efficiently Unlocking LLM Safety Restrictions Through Formal Logical Expression](https://mlsanity.com/paper/2505.13527/) (2025)
- [Link Prediction on N-ary Relational Data Based on Relatedness Evaluation](https://mlsanity.com/paper/2104.10424/) (2021)
- [Joint Language Semantic and Structure Embedding for Knowledge Graph Completion](https://mlsanity.com/paper/2209.08721/) (2022)
- [UKnow: A Unified Knowledge Protocol with Multimodal Knowledge Graph Datasets for Reasoning and Vision-Language Pre-Training](https://mlsanity.com/paper/2302.06891/) (2023)
- [Poisoning Knowledge Graph Embeddings via Relation Inference Patterns](https://mlsanity.com/paper/2111.06345/) (2021)
- [Bilinear Scoring Function Search for Knowledge Graph Learning](https://mlsanity.com/paper/2107.00184/) (2021)
- [Fuzzy Logic Based Logical Query Answering on Knowledge Graphs](https://mlsanity.com/paper/2108.02390/) (2021)
- [Knowledge Sheaves: A Sheaf-Theoretic Framework for Knowledge Graph Embedding](https://mlsanity.com/paper/2110.03789/) (2021)
- [SQALER: Scaling Question Answering by Decoupling Multi-Hop and Logical Reasoning](https://mlsanity.com/paper/2110.14266/) (2021)
- [Contextualizing biological perturbation experiments through language](https://mlsanity.com/paper/2502.21290/) (2025)
- [Is Complex Query Answering Really Complex?](https://mlsanity.com/paper/2410.12537/) (2024)
- [On the Security Risks of Knowledge Graph Reasoning](https://mlsanity.com/paper/2305.02383/) (2023)
- [Integrating Approaches to Word Representation](https://mlsanity.com/paper/2109.04876/) (2021)
- [Cross-Domain Aspect Extraction using Transformers Augmented with Knowledge Graphs](https://mlsanity.com/paper/2210.10144/) (2022)
- [Principled and Efficient Motif Finding for Structure Learning of Lifted Graphical Models](https://mlsanity.com/paper/2302.04599/) (2023)
- [DREAM: Adaptive Reinforcement Learning based on Attention Mechanism for Temporal Knowledge Graph Reasoning](https://mlsanity.com/paper/2304.03984/) (2023)
- [Inductive Meta-path Learning for Schema-complex Heterogeneous Information Networks](https://mlsanity.com/paper/2307.03937/) (2023)
- [Query2Triple: Unified Query Encoding for Answering Diverse Complex Queries over Knowledge Graphs](https://mlsanity.com/paper/2310.11246/) (2023)

## 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.