# LinkLogic: A New Method and Benchmark for Explainable Knowledge Graph Predictions

arXiv: https://arxiv.org/abs/2406.00855 · HTML: https://mlsanity.com/paper/2406.00855/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 21 references that are in the map.
- First posted on arXiv 2 Jun 2024.

## Builds on (most cited first, 15 of 15)

- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016)
- [DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning](https://mlsanity.com/paper/1707.06690/) (2017)
- [A Review of Relational Machine Learning for Knowledge Graphs](https://mlsanity.com/paper/1503.00759/) (2015)
- [DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphs](https://mlsanity.com/paper/1911.00055/) (2019)
- [RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs](https://mlsanity.com/paper/2010.04029/) (2020)
- [Multi-Hop Knowledge Graph Reasoning with Reward Shaping](https://mlsanity.com/paper/1808.10568/) (2018)
- [Translation-based Recommendation](https://mlsanity.com/paper/1707.02410/) (2017)
- [Probabilistic Logic Neural Networks for Reasoning](https://mlsanity.com/paper/1906.08495/) (2019)
- [DGL-KE: Training Knowledge Graph Embeddings at Scale](https://mlsanity.com/paper/2004.08532/) (2020)
- [GraphSVX: Shapley Value Explanations for Graph Neural Networks](https://mlsanity.com/paper/2104.10482/) (2021)
- [Interaction Embeddings for Prediction and Explanation in Knowledge Graphs](https://mlsanity.com/paper/1903.04750/) (2019)
- [A Review of Biomedical Datasets Relating to Drug Discovery: A Knowledge Graph Perspective](https://mlsanity.com/paper/2102.10062/) (2021)
- [Knowledge Graph Embeddings and Explainable AI](https://mlsanity.com/paper/2004.14843/) (2020)
- [Interpreting Embedding Models of Knowledge Bases: A Pedagogical Approach](https://mlsanity.com/paper/1806.09504/) (2018)

## Abstract (arXiv)

While there are a plethora of methods for link prediction in knowledge graphs, state-of-the-art approaches are often black box, obfuscating model reasoning and thereby limiting the ability of users to make informed decisions about model predictions. Recently, methods have emerged to generate prediction explanations for Knowledge Graph Embedding models, a widely-used class of methods for link prediction. The question then becomes, how well do these explanation systems work? To date this has generally been addressed anecdotally, or through time-consuming user research. In this work, we present an in-depth exploration of a simple link prediction explanation method we call LinkLogic, that surfaces and ranks explanatory information used for the prediction. Importantly, we construct the first-ever link prediction explanation benchmark, based on family structures present in the FB13 dataset. We demonstrate the use of this benchmark as a rich evaluation sandbox, probing LinkLogic quantitatively and qualitatively to assess the fidelity, selectivity and relevance of the generated explanations. We hope our work paves the way for more holistic and empirical assessment of knowledge graph prediction explanation methods in the future.