In graph classification, attention and pooling-based graph neural networks (GNNs) prevail to extract the critical features from the input graph and support the prediction. They mostly follow the paradigm of learning to attend, which maximizes the mutual information between the attended graph and the ground-truth label. However, this paradigm makes GNN classifiers recklessly absorb all the statistical correlations between input features and labels in the training data, without distinguishing the causal and noncausal effects of features. Instead of underscoring the causal features, the attended graphs are prone to visit the noncausal features as the shortcut to predictions. Such shortcut features might easily change outside the training distribution, thereby making the GNN classifiers suffer from poor generalization. In this work, we take a causal look at the GNN modeling for graph classification. With our causal assumption, the shortcut feature serves as a confounder between the causal feature and prediction. It tricks the classifier to learn spurious correlations that facilitate the prediction in in-distribution (ID) test evaluation, while causing the performance drop in out-of-distribution (OOD) test data. To endow the classifier with better interpretation and generalization, we propose the Causal Attention Learning (CAL) strategy, which discovers the causal patterns and mitigates the confounding effect of shortcuts. Specifically, we employ attention modules to estimate the causal and shortcut features of the input graph. We then parameterize the backdoor adjustment of causal theory -- combine each causal feature with various shortcut features. It encourages the stable relationships between the causal estimation and prediction, regardless of the changes in shortcut parts and distributions. Extensive experiments on synthetic and real-world datasets demonstrate the effectiveness of CAL.
翻译:在图表分类中,关注和基于集合的图形神经网络(GNNs)占上风,以从输入图表中提取关键特征,支持预测。它们大多遵循学习参与模式,让参加图表和地面真相标签之间的相互信息最大化。然而,这一模式使GNN分类者鲁莽地吸收了培训数据中输入特征和标签之间的统计相关性,而没有区分各种特征的因果关系和非因果关系。所选图表不是强调因果关系特征,而是容易访问非因果特性,作为预测的捷径。这些直径特性可能很容易在培训分布之外改变,从而使GNN分类的特性因果特征受到不甚一般化的影响。在这项工作中,我们对GNNNG的分类模型进行因果分类,从而鼓励图形分类。根据我们的因果假设,捷径特征成为了因果特征和预测之间的混结点。它让分类者学到了有助于在分配(ID)测试评估中预测的因果特性,同时导致我们交付(OD)测试数据外的性下降,从而让GNNNE分类特性特性特性特性特性特性特性特性特性特性特性特性特征受到不那么的概括化。让我们在解释和直判变变变的内,然后用直判的理论的理论的理论分析和直判法分析中,然后在解释和直判变变变变变。