arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.10261cs.LGcs.AIcs.LO
收藏

关系图卷积网络无法学习可靠规则

Relational Graph Convolutional Networks Do Not Learn Sound Rules

University of Oxford(牛津大学);Royal Holloway, University of London(伦敦大学皇家霍洛威学院)

Matthew Morris, David J. Tena Cucala, Bernardo Cuenca Grau, Ian Horrocks

AI总结:

本文研究R-GCN在知识图谱补全中的可解释性,提出提取和验证可靠规则的方法,发现其无法学习可靠规则,并通过训练变体在准确性与规则可靠性间取得平衡。

摘要:

图神经网络(GNNs)经常被用于预测知识图谱(KGs)中缺失的事实。由于这些模型输出缺乏可解释性,近期工作旨在使用Datalog(一种广泛使用的基于逻辑的形式体系)来解释其预测。然而,这些工作仅限于GNN的某些子类。在本文中,我们考虑了最流行的用于知识图谱的GNN架构之一——R-GCN,并提供了两种方法来提取解释其预测的规则,这些规则是可靠的,即对于任何输入数据集,由这些规则推导出的每个事实也由GNN预测。此外,我们提供了一种方法,可以验证某些类别的Datalog规则对于R-GCN并非可靠。在我们的实验中,我们在知识图谱补全基准上训练R-GCN,并能够验证对于这些模型,没有任何Datalog规则是可靠的,尽管这些模型通常获得高至近乎完美的准确率。这引发了对R-GCN模型泛化能力及其预测可解释性的一些担忧。我们进一步提供了R-GCN训练范式的两种变体,鼓励其学习可靠规则,并在模型准确性与所学可靠规则数量之间找到权衡。

英文摘要:

Graph neural networks (GNNs) are frequently used to predict missing facts in knowledge graphs (KGs). Motivated by the lack of explainability for the outputs of these models, recent work has aimed to explain their predictions using Datalog, a widely used logic-based formalism. However, such work has been restricted to certain subclasses of GNNs. In this paper, we consider one of the most popular GNN architectures for KGs, R-GCN, and we provide two methods to extract rules that explain its predictions and are sound, in the sense that each fact derived by the rules is also predicted by the GNN, for any input dataset. Furthermore, we provide a method that can verify that certain classes of Datalog rules are not sound for the R-GCN. In our experiments, we train R-GCNs on KG completion benchmarks, and we are able to verify that no Datalog rule is sound for these models, even though the models often obtain high to near-perfect accuracy. This raises some concerns about the ability of R-GCN models to generalise and about the explainability of their predictions. We further provide two variations to the training paradigm of R-GCN that encourage it to learn sound rules and find a trade-off between model accuracy and the number of learned sound rules.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑