Graph Neural Networks (GNNs) have achieved promising performance in a variety of graph-focused tasks. Despite their success, however, existing GNNs suffer from two significant limitations: a lack of interpretability in results due to their black-box nature, and an inability to learn representations of varying orders. To tackle these issues, we propose a novel \textbf{M}odel-\textbf{a}gnostic \textbf{G}raph Neural \textbf{Net}work (MaGNet) framework, which is able to effectively integrate information of various orders, extract knowledge from high-order neighbors, and provide meaningful and interpretable results by identifying influential compact graph structures. In particular, MaGNet consists of two components: an estimation model for the latent representation of complex relationships under graph topology, and an interpretation model that identifies influential nodes, edges, and node features. Theoretically, we establish the generalization error bound for MaGNet via empirical Rademacher complexity, and demonstrate its power to represent layer-wise neighborhood mixing. We conduct comprehensive numerical studies using simulated data to demonstrate the superior performance of MaGNet in comparison to several state-of-the-art alternatives. Furthermore, we apply MaGNet to a real-world case study aimed at extracting task-critical information from brain activity data, thereby highlighting its effectiveness in advancing scientific research.

翻译：图神经网络（GNNs）在各种图相关任务中取得了显著成效。然而，尽管取得了成功，现有GNNs存在两个重要局限性：由于其黑箱特性导致结果缺乏可解释性，以及无法学习不同阶次的表示。为解决这些问题，我们提出了一种新颖的**模型无关图神经网络**（MaGNet）框架，该框架能够有效整合各阶信息，从高阶邻居中提取知识，并通过识别具影响力的紧凑图结构提供有意义且可解释的结果。具体而言，MaGNet由两部分组成：一个用于图拓扑下复杂关系潜在表示的估计模型，以及一个识别具影响力的节点、边和节点特征的解释模型。理论上，我们通过经验Rademacher复杂度建立了MaGNet的泛化误差界，并展示了其逐层邻域混合的表示能力。我们利用模拟数据进行了全面的数值研究，证明MaGNet与几种最先进替代方法相比具有优越性能。此外，我们将MaGNet应用于一个真实案例研究——从脑活动数据中提取任务关键信息，从而凸显其在推动科学研究方面的有效性。