Graph Rationalization with Environment-based Augmentations
Graph Rationalization with Environment-based Augmentations
复制标题
DOI：
10.1145/3534678.3539347
复制
发表时间：
2022-06
期刊：
影响因子：
--
通讯作者：
Gang Liu;Tong Zhao;Jiaxi Xu;Te Luo;Meng Jiang
中科院分区：
文献类型：
--
作者：
Gang Liu;Tong Zhao;Jiaxi Xu;Te Luo;Meng Jiang
基本原理被定义为最能解释或支持机器学习模型预测的输入特征的子集。基本原理识别提高了神经网络在视觉和语言数据上的通用性和可解释性。在分子和聚合物属性预测等图应用中，识别称为图基本原理的代表性子图结构在图神经网络的性能中起着至关重要的作用。现有的图池和/或分布干预方法缺乏学习识别最佳图原理的示例。在这项工作中，我们引入了一种称为环境替换的新增强操作，它会自动创建虚拟数据示例以改进基本原理识别。我们提出了一种有效的框架，可以对潜在空间中的真实示例和增强示例执行基本原理-环境分离和表示学习，以避免显式图解码和编码的高复杂性。与最新技术相比，七个分子和四个聚合物数据集的实验证明了所提出的基于增强的图合理化框架的有效性和效率。拟议框架的数据和实施可公开获取 https://github.com/liugangcode/GREA。
Rationale is defined as a subset of input features that best explains or supports the prediction by machine learning models. Rationale identification has improved the generalizability and interpretability of neural networks on vision and language data. In graph applications such as molecule and polymer property prediction, identifying representative subgraph structures named as graph rationales plays an essential role in the performance of graph neural networks. Existing graph pooling and/or distribution intervention methods suffer from the lack of examples to learn to identify optimal graph rationales. In this work, we introduce a new augmentation operation called environment replacement that automatically creates virtual data examples to improve rationale identification. We propose an efficient framework that performs rationale-environment separation and representation learning on the real and augmented examples in latent spaces to avoid the high complexity of explicit graph decoding and encoding. Comparing against recent techniques, experiments on seven molecular and four polymer datasets demonstrate the effectiveness and efficiency of the proposed augmentation-based graph rationalization framework. Data and the implementation of the proposed framework are publicly available https://github.com/liugangcode/GREA.