Graph Neural Networks (GNNs) have achieved tremendous success in a variety of real-world applications by relying on the fixed graph data as input. However, the initial input graph might not be optimal in terms of specific downstream tasks, because of information scarcity, noise, adversarial attacks, or discrepancies between the distribution in graph topology, features, and groundtruth labels. In this paper, we propose a bi-level optimization approach for learning the optimal graph structure via directly learning the Personalized PageRank propagation matrix as well as the downstream semi-supervised node classification simultaneously. We also explore a low-rank approximation model for further reducing the time complexity. Empirical evaluations show the superior efficacy and robustness of the proposed model over all baseline methods.

翻译：图神经网络（GNNs）通过依赖固定的图数据作为输入，已在多种实际应用中取得了巨大成功。然而，初始输入图可能因信息稀缺、噪声、对抗攻击或图拓扑结构、特征与真实标签分布之间的差异，而在特定下游任务中并非最优。本文提出了一种双层优化方法，通过同时直接学习个性化PageRank传播矩阵以及下游半监督节点分类任务，来学习最优图结构。我们还探索了一种低秩近似模型以进一步降低时间复杂度。实验评估表明，所提出的模型在所有基线方法上展现出优越的有效性和鲁棒性。