# Knowledge Reasoning via Jointly Modeling Knowledge Graphs and Soft Rules

arXiv: https://arxiv.org/abs/2301.02781 · HTML: https://mlsanity.com/paper/2301.02781/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 54 references that are in the map.
- First posted on arXiv 7 Jan 2023.

## Builds on (most cited first, 26 of 26)

- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Embedding Entities and Relations for Learning and Inference in Knowledge Bases](https://mlsanity.com/paper/1412.6575/) (2014)
- [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016)
- [RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space](https://mlsanity.com/paper/1902.10197/) (2019)
- [Convolutional 2D Knowledge Graph Embeddings](https://mlsanity.com/paper/1707.01476/) (2017)
- [A Survey on Knowledge Graphs: Representation, Acquisition and Applications](https://mlsanity.com/paper/2002.00388/) (2020)
- [A Review of Relational Machine Learning for Knowledge Graphs](https://mlsanity.com/paper/1503.00759/) (2015)
- [Holographic Embeddings of Knowledge Graphs](https://mlsanity.com/paper/1510.04935/) (2015)
- [End-to-end Structure-Aware Convolutional Networks for Knowledge Base Completion](https://mlsanity.com/paper/1811.04441/) (2018)
- [Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction](https://mlsanity.com/paper/1911.09419/) (2019)
- [Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences](https://mlsanity.com/paper/1902.06236/) (2019)
- [Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs](https://mlsanity.com/paper/1905.04914/) (2019)
- [Analogical Inference for Multi-Relational Embeddings](https://mlsanity.com/paper/1705.02426/) (2017)
- [Probabilistic Logic Neural Networks for Reasoning](https://mlsanity.com/paper/1906.08495/) (2019)
- [Improving Question Answering by Commonsense-Based Pre-Training](https://mlsanity.com/paper/1809.03568/) (2018)
- [Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoning](https://mlsanity.com/paper/1903.08948/) (2019)
- [Modeling Relation Paths for Representation Learning of Knowledge Bases](https://mlsanity.com/paper/1506.00379/) (2015)
- [Knowledge Graph Embedding with Iterative Guidance from Soft Rules](https://mlsanity.com/paper/1711.11231/) (2017)
- [Universal Representation Learning of Knowledge Bases by Jointly Embedding Instances and Ontological Concepts](https://mlsanity.com/paper/2103.08115/) (2021)
- [Improving Knowledge Graph Embedding Using Simple Constraints](https://mlsanity.com/paper/1805.02408/) (2018)
- [CoKE: Contextualized Knowledge Graph Embedding](https://mlsanity.com/paper/1911.02168/) (2019)
- [ProjE: Embedding Projection for Knowledge Graph Completion](https://mlsanity.com/paper/1611.05425/) (2016)
- [Dynamically Pruned Message Passing Networks for Large-Scale Knowledge Graph Reasoning](https://mlsanity.com/paper/1909.11334/) (2019)
- [CAKE: A Scalable Commonsense-Aware Framework For Multi-View Knowledge Graph Completion](https://mlsanity.com/paper/2202.13785/) (2022)
- [Improved Knowledge Graph Embedding using Background Taxonomic Information](https://mlsanity.com/paper/1812.03235/) (2018)
- [LogicENN: A Neural Based Knowledge Graphs Embedding Model with Logical Rules](https://mlsanity.com/paper/1908.07141/) (2019)

## Built on by (most cited first, 1 of 1)

- [ConstraintChecker: A Plugin for Large Language Models to Reason on Commonsense Knowledge Bases](https://mlsanity.com/paper/2401.14003/) (2024)

## Abstract (arXiv)

Knowledge graphs (KGs) play a crucial role in many applications, such as question answering, but incompleteness is an urgent issue for their broad application. Much research in knowledge graph completion (KGC) has been performed to resolve this issue. The methods of KGC can be classified into two major categories: rule-based reasoning and embedding-based reasoning. The former has high accuracy and good interpretability, but a major challenge is to obtain effective rules on large-scale KGs. The latter has good efficiency and scalability, but it relies heavily on data richness and cannot fully use domain knowledge in the form of logical rules. We propose a novel method that injects rules and learns representations iteratively to take full advantage of rules and embeddings. Specifically, we model the conclusions of rule groundings as 0-1 variables and use a rule confidence regularizer to remove the uncertainty of the conclusions. The proposed approach has the following advantages: 1) It combines the benefits of both rules and knowledge graph embeddings (KGEs) and achieves a good balance between efficiency and scalability. 2) It uses an iterative method to continuously improve KGEs and remove incorrect rule conclusions. Evaluations on two public datasets show that our method outperforms the current state-of-the-art methods, improving performance by 2.7% and 4.3% in mean reciprocal rank (MRR).