arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2208.03075cs.LG
收藏

PGX:一个基于分离知识蒸馏过程的多层次GNN解释框架

PGX: A Multi-level GNN Explanation Framework Based on Separate Knowledge Distillation Processes

Seoul National University(首尔国立大学)

Tien-Cuong Bui, Wen-syan Li, Sang-Kyun Cha

摘要:

图神经网络(GNN)由于其对图数据的表示学习能力而被广泛应用于高级AI系统中。尽管GNN解释对于增加用户对系统的信任至关重要,但由于GNN执行的复杂性,它具有挑战性。最近,已经提出了许多工作来解决GNN解释中的一些问题。然而,当图的规模很大时,它们缺乏推广能力或遭受计算负担。为了解决这些挑战,我们提出了一个多层次的GNN解释框架的基础上观察,GNN是一个多模式的学习过程中的多个组件的图形数据。原来的问题的复杂性是放松分解成多个子部分表示为一个层次结构。顶层解释旨在说明每个组件对模型执行和预测的贡献,而细粒度级别则侧重于基于知识蒸馏的特征属性和图结构属性分析。学生模型在独立模式下训练,负责捕捉不同的教师行为,随后用于特定的组件解释。此外,我们还旨在个性化的解释,因为该框架可以根据用户的偏好生成不同的结果。最后,大量的实验证明了我们所提出的方法的有效性和保真度。

英文摘要:

Graph Neural Networks (GNNs) are widely adopted in advanced AI systems due to their capability of representation learning on graph data. Even though GNN explanation is crucial to increase user trust in the systems, it is challenging due to the complexity of GNN execution. Lately, many works have been proposed to address some of the issues in GNN explanation. However, they lack generalization capability or suffer from computational burden when the size of graphs is enormous. To address these challenges, we propose a multi-level GNN explanation framework based on an observation that GNN is a multimodal learning process of multiple components in graph data. The complexity of the original problem is relaxed by breaking into multiple sub-parts represented as a hierarchical structure. The top-level explanation aims at specifying the contribution of each component to the model execution and predictions, while fine-grained levels focus on feature attribution and graph structure attribution analysis based on knowledge distillation. Student models are trained in standalone modes and are responsible for capturing different teacher behaviors, later used for particular component interpretation. Besides, we also aim for personalized explanations as the framework can generate different results based on user preferences. Finally, extensive experiments demonstrate the effectiveness and fidelity of our proposed approach.

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。

↑