# Variational Knowledge Graph Reasoning

arXiv: https://arxiv.org/abs/1803.06581 · HTML: https://mlsanity.com/paper/1803.06581/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Mar 2018.

## Built on by (most cited first, 27 of 27)

- [Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction](https://mlsanity.com/paper/2106.06935/) (2021)
- [A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodal](https://mlsanity.com/paper/2212.05767/) (2022)
- [A*Net: A Scalable Path-based Reasoning Approach for Knowledge Graphs](https://mlsanity.com/paper/2206.04798/) (2022)
- [Search from History and Reason for Future: Two-stage Reasoning on Temporal Knowledge Graphs](https://mlsanity.com/paper/2106.00327/) (2021)
- [On the Explainability of Natural Language Processing Deep Models](https://mlsanity.com/paper/2210.06929/) (2022)
- [Contrastive Language-Image Pre-Training with Knowledge Graphs](https://mlsanity.com/paper/2210.08901/) (2022)
- [Prototypical Representation Learning for Relation Extraction](https://mlsanity.com/paper/2103.11647/) (2021)
- [Inductive Relation Prediction by BERT](https://mlsanity.com/paper/2103.07102/) (2021)
- [An Open Challenge for Inductive Link Prediction on Knowledge Graphs](https://mlsanity.com/paper/2203.01520/) (2022)
- [Variational Reasoning over Incomplete Knowledge Graphs for Conversational Recommendation](https://mlsanity.com/paper/2212.11868/) (2022)
- [Neural Methods for Logical Reasoning Over Knowledge Graphs](https://mlsanity.com/paper/2209.14464/) (2022)
- [Enhancing Complex Question Answering over Knowledge Graphs through Evidence Pattern Retrieval](https://mlsanity.com/paper/2402.02175/) (2024)
- [Explicit Planning Helps Language Models in Logical Reasoning](https://mlsanity.com/paper/2303.15714/) (2023)
- [Is Multi-Hop Reasoning Really Explainable? Towards Benchmarking Reasoning Interpretability](https://mlsanity.com/paper/2104.06751/) (2021)
- [Weakly Supervised Text Classification using Supervision Signals from a Language Model](https://mlsanity.com/paper/2205.06604/) (2022)
- [Logical Entity Representation in Knowledge-Graphs for Differentiable Rule Learning](https://mlsanity.com/paper/2305.12738/) (2023)
- [Open Relation Modeling: Learning to Define Relations between Entities](https://mlsanity.com/paper/2108.09241/) (2021)
- [R5: Rule Discovery with Reinforced and Recurrent Relational Reasoning](https://mlsanity.com/paper/2205.06454/) (2022)
- [DEER: Descriptive Knowledge Graph for Explaining Entity Relationships](https://mlsanity.com/paper/2205.10479/) (2022)
- [Knowledge Graph Anchored Information-Extraction for Domain-Specific Insights](https://mlsanity.com/paper/2104.08936/) (2021)
- [VEM2L: A Plug-and-play Framework for Fusing Text and Structure Knowledge on Sparse Knowledge Graph Completion](https://mlsanity.com/paper/2207.01528/) (2022)
- [Wikidata as a seed for Web Extraction](https://mlsanity.com/paper/2401.07812/) (2024)
- [Harnessing the Power of Large Language Model for Uncertainty Aware Graph Processing](https://mlsanity.com/paper/2404.00589/) (2024)
- [APPTeK: Agent-Based Predicate Prediction in Temporal Knowledge Graphs](https://mlsanity.com/paper/2110.14284/) (2021)
- [An Inference Approach To Question Answering Over Knowledge Graphs](https://mlsanity.com/paper/2112.11070/) (2021)
- [Logic Diffusion for Knowledge Graph Reasoning](https://mlsanity.com/paper/2306.03515/) (2023)
- [MPRM: A Markov Path-based Rule Miner for Efficient and Interpretable Knowledge Graph Reasoning](https://mlsanity.com/paper/2505.12329/) (2025)

## Abstract (arXiv)

Inferring missing links in knowledge graphs (KG) has attracted a lot of attention from the research community. In this paper, we tackle a practical query answering task involving predicting the relation of a given entity pair. We frame this prediction problem as an inference problem in a probabilistic graphical model and aim at resolving it from a variational inference perspective. In order to model the relation between the query entity pair, we assume that there exists an underlying latent variable (paths connecting two nodes) in the KG, which carries the equivalent semantics of their relations. However, due to the intractability of connections in large KGs, we propose to use variation inference to maximize the evidence lower bound. More specifically, our framework (textscDiva) is composed of three modules, i.e. a posterior approximator, a prior (path finder), and a likelihood (path reasoner). By using variational inference, we are able to incorporate them closely into a unified architecture and jointly optimize them to perform KG reasoning. With active interactions among these sub-modules, textscDiva is better at handling noise and coping with more complex reasoning scenarios. In order to evaluate our method, we conduct the experiment of the link prediction task on multiple datasets and achieve state-of-the-art performances on both datasets.