SES：弥合图神经网络可解释性与预测之间的差距
SES: Bridging the Gap Between Explainability and Prediction of Graph Neural Networks
- School of Internet（互联网学院）
- Anhui University（安徽大学）
- Amazon Research（亚马逊研究院）
- University of California Irvine（加州大学欧文分校）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
提出自解释且自监督的图神经网络SES，通过可解释训练和增强预测学习两个过程，利用全局掩码生成器生成结构与特征掩码，并基于掩码构建正负样本对进行对比学习，从而弥合可解释性与预测性能之间的差距。
AI中文摘要：
尽管图神经网络（GNNs）在分析图数据方面表现出色，但实现高精度和可解释的预测仍然具有挑战性。现有的GNN解释器通常提供与GNN预测脱节的事后解释，导致解释失真。自解释GNN在训练过程中提供内置解释。然而，它们无法利用解释结果来增强预测性能，且无法对节点特征提供高质量解释，并需要额外流程来生成可解释子图，成本高昂。为解决上述局限，我们提出了一种自解释且自监督的图神经网络（SES），以弥合可解释性与预测之间的差距。SES包含两个过程：可解释训练和增强预测学习。在可解释训练中，SES采用与图编码器协同训练的全局掩码生成器，直接生成关键结构和特征掩码，降低时间消耗并提供节点特征和子图解释。在增强预测学习阶段，利用解释构建基于掩码的正负样本对，以计算三元组损失，并通过对比学习增强节点表示。
英文摘要：
Despite the Graph Neural Networks' (GNNs) proficiency in analyzing graph data, achieving high-accuracy and interpretable predictions remains challenging. Existing GNN interpreters typically provide post-hoc explanations disjointed from GNNs' predictions, resulting in misrepresentations. Self-explainable GNNs offer built-in explanations during the training process. However, they cannot exploit the explanatory outcomes to augment prediction performance, and they fail to provide high-quality explanations of node features and require additional processes to generate explainable subgraphs, which is costly. To address the aforementioned limitations, we propose a self-explained and self-supervised graph neural network (SES) to bridge the gap between explainability and prediction. SES comprises two processes: explainable training and enhanced predictive learning. During explainable training, SES employs a global mask generator co-trained with a graph encoder and directly produces crucial structure and feature masks, reducing time consumption and providing node feature and subgraph explanations. In the enhanced predictive learning phase, mask-based positive-negative pairs are constructed utilizing the explanations to compute a triplet loss and enhance the node representations by contrastive learning.
