PaGE-Link: Path-based Graph Neural Network Explanation for Heterogeneous Link Prediction
PaGE-Link: Path-based Graph Neural Network Explanation for Heterogeneous Link Prediction
复制标题
DOI：
10.1145/3543507.3583511
复制
发表时间：
2023-02
期刊：
影响因子：
--
通讯作者：
Shichang Zhang;Jiani Zhang;Xiang Song;Soji Adeshina;Da Zheng;C. Faloutsos;Yizhou Sun
中科院分区：
文献类型：
--
作者：
Shichang Zhang;Jiani Zhang;Xiang Song;Soji Adeshina;Da Zheng;C. Faloutsos;Yizhou Sun
透明度和问责制已成为黑盒机器学习（ML）模型的主要问题。对模型行为的适当解释增加了模型的透明度，并帮助研究人员开发出更可靠的模型。图神经网络（GNN）最近在许多图ML问题中表现出比传统方法更上级的性能，并且解释它们引起了越来越多的兴趣。然而，GNN解释链接预测（LP）是缺乏在文献中。LP是一个基本的GNN任务，对应于Web上的推荐和赞助搜索等Web应用程序。鉴于现有的GNN解释方法只解决节点/图级任务，我们提出了基于路径的GNN解释异构链接预测（PaGE-Link），生成具有连接可解释性的解释，享有模型可扩展性，并处理图形异构性。在质量上，PaGE-Link可以生成解释作为连接节点对的路径，它自然地捕获两个节点之间的连接，并轻松地转换为人类可解释的解释。量化，PaGE-Link生成的解释将引用和用户项图的推荐AUC提高了9 - 35%，并在人类评估中被78.79%的回答选择为更好。
Transparency and accountability have become major concerns for black-box machine learning (ML) models. Proper explanations for the model behavior increase model transparency and help researchers develop more accountable models. Graph neural networks (GNN) have recently shown superior performance in many graph ML problems than traditional methods, and explaining them has attracted increased interest. However, GNN explanation for link prediction (LP) is lacking in the literature. LP is an essential GNN task and corresponds to web applications like recommendation and sponsored search on web. Given existing GNN explanation methods only address node/graph-level tasks, we propose Path-based GNN Explanation for heterogeneous Link prediction (PaGE-Link) that generates explanations with connection interpretability, enjoys model scalability, and handles graph heterogeneity. Qualitatively, PaGE-Link can generate explanations as paths connecting a node pair, which naturally captures connections between the two nodes and easily transfer to human-interpretable explanations. Quantitatively, explanations generated by PaGE-Link improve AUC for recommendation on citation and user-item graphs by 9 - 35% and are chosen as better by 78.79% of responses in human evaluation.