Dynamic Graphs widely exist in the real world, which carry complicated spatial and temporal feature patterns, challenging their representation learning. Dynamic Graph Neural Networks (DGNNs) have shown impressive predictive abilities by exploiting the intrinsic dynamics. However, DGNNs exhibit limited robustness, prone to adversarial attacks. This paper presents the novel Dynamic Graph Information Bottleneck (DGIB) framework to learn robust and discriminative representations. Leveraged by the Information Bottleneck (IB) principle, we first propose the expected optimal representations should satisfy the Minimal-Sufficient-Consensual (MSC) Condition. To compress redundant as well as conserve meritorious information into latent representation, DGIB iteratively directs and refines the structural and feature information flow passing through graph snapshots. To meet the MSC Condition, we decompose the overall IB objectives into DGIB$_{MS}$ and DGIB$_C$, in which the DGIB$_{MS}$ channel aims to learn the minimal and sufficient representations, with the DGIB$_{MS}$ channel guarantees the predictive consensus. Extensive experiments on real-world and synthetic dynamic graph datasets demonstrate the superior robustness of DGIB against adversarial attacks compared with state-of-the-art baselines in the link prediction task. To the best of our knowledge, DGIB is the first work to learn robust representations of dynamic graphs grounded in the information-theoretic IB principle.

翻译：动态图在现实世界中广泛存在，其承载着复杂的时空特征模式，给表示学习带来了挑战。动态图神经网络通过利用内在动态特性展现出强大的预测能力。然而，动态图神经网络的鲁棒性有限，容易受到对抗性攻击。本文提出一种新颖的动态图信息瓶颈框架，用于学习鲁棒且具有判别性的表示。基于信息瓶颈原理，我们首先提出期望的最优表示应满足最小-充分-共识条件。为将冗余信息压缩并将有价值信息保留到潜在表示中，动态图信息瓶颈通过迭代引导和精炼通过图快照的结构与特征信息流。为满足最小-充分-共识条件，我们将整体信息瓶颈目标分解为动态图信息瓶颈$_{MS}$和动态图信息瓶颈$_{C}$，其中动态图信息瓶颈$_{MS}$通道致力于学习最小且充分的表示，而动态图信息瓶颈$_{C}$通道则保证预测共识。在真实世界与合成动态图数据集上的大量实验表明，相比现有最优基线模型，动态图信息瓶颈在链路预测任务中针对对抗性攻击展现出卓越的鲁棒性。据我们所知，动态图信息瓶颈是首个基于信息论信息瓶颈原理学习动态图鲁棒表示的工作。