# GMH: A General Multi-hop Reasoning Model for KG Completion

arXiv: https://arxiv.org/abs/2010.07620 · HTML: https://mlsanity.com/paper/2010.07620/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Oct 2020.

## Built on by (most cited first, 6 of 6)

- [Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering](https://mlsanity.com/paper/2105.11776/) (2021)
- [Exploiting Reasoning Chains for Multi-hop Science Question Answering](https://mlsanity.com/paper/2109.02905/) (2021)
- [Dense-ATOMIC: Towards Densely-connected ATOMIC with High Knowledge Coverage and Massive Multi-hop Paths](https://mlsanity.com/paper/2210.07621/) (2022)
- [DREAM: Adaptive Reinforcement Learning based on Attention Mechanism for Temporal Knowledge Graph Reasoning](https://mlsanity.com/paper/2304.03984/) (2023)
- [Uncertainty-Aware Relational Graph Neural Network for Few-Shot Knowledge Graph Completion](https://mlsanity.com/paper/2403.04521/) (2024)
- [Question-Aware Memory Network for Multi-hop Question Answering in Human-Robot Interaction](https://mlsanity.com/paper/2104.13173/) (2021)

## Abstract (arXiv)

Knowledge graphs are essential for numerous downstream natural language processing applications, but are typically incomplete with many facts missing. This results in research efforts on multi-hop reasoning task, which can be formulated as a search process and current models typically perform short distance reasoning. However, the long-distance reasoning is also vital with the ability to connect the superficially unrelated entities. To the best of our knowledge, there lacks a general framework that approaches multi-hop reasoning in mixed long-short distance reasoning scenarios. We argue that there are two key issues for a general multi-hop reasoning model: i) where to go, and ii) when to stop. Therefore, we propose a general model which resolves the issues with three modules: 1) the local-global knowledge module to estimate the possible paths, 2) the differentiated action dropout module to explore a diverse set of paths, and 3) the adaptive stopping search module to avoid over searching. The comprehensive results on three datasets demonstrate the superiority of our model with significant improvements against baselines in both short and long distance reasoning scenarios.