发表机构
University of Novi Sad（诺威萨大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对动态图嵌入中图自编码器未考虑节点结构异质性的问题，提出含NC-LID正则化等的三种基于距离的GAE变体，经多数据集实验证实其可提升重构性能。
AI 中文摘要
图自编码器（GAEs）被广泛用于学习动态图的表示，但它们的优化目标通常未考虑节点间的结构异质性。我们提出三种基于距离的GAE变体，将结构惩罚纳入重构损失。所有变体共享一个两层图卷积网络编码器和一个欧氏距离解码器，采用基于距离的重构目标进行训练。我们为稀疏校正损失扩展了两个节点级正则化项：（i）基于度中心性的枢纽惩罚，（ii）基于自然社区局部本征维度（NC-LID）的惩罚。该研究的动机是先前将高NC-LID与嵌入质量降低关联的证据，所提方法旨在强调结构模糊节点的重构误差。在多个动态图数据集上的实验表明，纳入基于NC-LID的正则化，相比无结构正则化的基线和采用枢纽感知正则化的方法，能持续提升重构性能。这些发现凸显NC-LID是增强动态场景下基于距离的图自编码器的有用结构信号。
英文摘要
Graph autoencoders (GAEs) are widely used for learning representations of dynamic graphs. However, their optimisation objectives typically do not take structural heterogeneity across nodes into account. We propose three distance-based GAE variants that incorporate structural penalties into the reconstruction loss. All variants share a two-layer Graph Convolutional Network encoder and a Euclidean-distance decoder trained with distance-based reconstruction objectives. We extend sparsity-corrected loss with two node-level regularization terms: (i) a hub penalty based on degree centrality, and (ii) a penalty based on Natural Community Local Intrinsic Dimensionality (NC-LID). The paper is motivated by prior evidence linking high NC-LID to reduced embedding quality. The proposed methods are designed to emphasize reconstruction errors for structurally ambiguous nodes. Experiments on multiple dynamic graph data sets show that incorporating NC-LID-based regularization consistently improves reconstruction performance over the baseline without structural regularization and the method using hub-aware regularization. These findings highlight NC-LID as a useful structural signal for enhancing distance-based graph autoencoders in dynamic settings.
