Dynamic graphs exhibit intertwined spatio-temporal evolutionary patterns, widely existing in the real world. Nevertheless, the structure incompleteness, noise, and redundancy result in poor robustness for Dynamic Graph Neural Networks (DGNNs). Dynamic Graph Structure Learning (DGSL) offers a promising way to optimize graph structures. However, aside from encountering unacceptable quadratic complexity, it overly relies on heuristic priors, making it hard to discover underlying predictive patterns. How to efficiently refine the dynamic structures, capture intrinsic dependencies, and learn robust representations, remains under-explored. In this work, we propose the novel DG-Mamba, a robust and efficient Dynamic Graph structure learning framework with the Selective State Space Models (Mamba). To accelerate the spatio-temporal structure learning, we propose a kernelized dynamic message-passing operator that reduces the quadratic time complexity to linear. To capture global intrinsic dynamics, we establish the dynamic graph as a self-contained system with State Space Model. By discretizing the system states with the cross-snapshot graph adjacency, we enable the long-distance dependencies capturing with the selective snapshot scan. To endow learned dynamic structures more expressive with informativeness, we propose the self-supervised Principle of Relevant Information for DGSL to regularize the most relevant yet least redundant information, enhancing global robustness. Extensive experiments demonstrate the superiority of the robustness and efficiency of our DG-Mamba compared with the state-of-the-art baselines against adversarial attacks.

翻译：动态图展现出时空交织的演化模式，广泛存在于现实世界中。然而，结构不完整性、噪声和冗余导致动态图神经网络（DGNNs）的鲁棒性较差。动态图结构学习（DGSL）为优化图结构提供了一种有前景的途径。然而，除了面临不可接受的二次复杂度外，它过度依赖启发式先验，难以发现潜在的预测模式。如何高效地优化动态结构、捕获内在依赖关系并学习鲁棒表示，仍有待深入探索。在本工作中，我们提出了新颖的DG-Mamba，这是一个基于选择性状态空间模型（Mamba）的鲁棒高效动态图结构学习框架。为加速时空结构学习，我们提出了一种核化动态消息传递算子，将二次时间复杂度降低至线性。为捕获全局内在动态，我们将动态图建立为一个自包含的状态空间模型系统。通过利用跨快照图邻接矩阵对系统状态进行离散化，我们借助选择性快照扫描实现了长距离依赖关系的捕获。为使学习到的动态结构更具信息表达力，我们为DGSL提出了自监督的相关信息原则，以正则化最相关且最冗余的信息，从而增强全局鲁棒性。大量实验证明，在对抗攻击下，我们的DG-Mamba在鲁棒性和效率方面均优于现有最先进的基线方法。