Summary of Kgexplainer: Towards Exploring Connected Subgraph Explanations For Knowledge Graph Completion, by Tengfei Ma et al.
KGExplainer: Towards Exploring Connected Subgraph Explanations for Knowledge Graph Completion
by Tengfei Ma, Xiang song, Wen Tao, Mufei Li, Jiani Zhang, Xiaoqin Pan, Jianxin Lin, Bosheng Song, xiangxiang Zeng
First submitted to arxiv on: 5 Apr 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper tackles knowledge graph completion (KGC), a crucial task for web-based recommendations. Current KGE models excel at predicting missing links but lack transparency and accountability, hindering the development of accountable models. Existing explanation methods focus on isolated edges or key paths, which is insufficient for understanding target predictions. To overcome these limitations, the authors propose KGExplainer, a model-agnostic method that identifies connected subgraph explanations and distills an evaluator to assess their quality quantitatively. The approach employs a perturbation-based greedy search algorithm to find key connected subgraphs and evaluates them using a distilled evaluator from the target KGE model. Extensive experiments on benchmark datasets demonstrate the efficacy of KGExplainer, achieving an optimal ratio of 83.3% in human evaluation. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about making sense of incomplete information online. Right now, computers are great at predicting what’s missing, but they don’t explain why they think that way. The authors want to change this by creating a new method called KGExplainer that finds connected groups of information that help us understand the predictions. They test their method on different datasets and show it works well. |
Keywords
» Artificial intelligence » Knowledge graph
