Network alignment (NA) is the task of discovering node correspondences across multiple networks using topological and/or feature information of given networks. Although NA methods have achieved remarkable success in a myriad of scenarios, their effectiveness is not without additional information such as prior anchor links and/or node features, which may not always be available due to privacy concerns or access restrictions. To tackle this practical challenge, we propose Grad-Align+, a novel NA method built upon a recent state-of-the-art NA method, the so-called Grad-Align, that gradually discovers only a part of node pairs until all node pairs are found. In designing Grad-Align+, we account for how to augment node features in the sense of performing the NA task and how to design our NA method by maximally exploiting the augmented node features. To achieve this goal, we develop Grad-Align+ consisting of three key components: 1) centrality-based node feature augmentation (CNFA), 2) graph neural network (GNN)-aided embedding similarity calculation alongside the augmented node features, and 3) gradual NA with similarity calculation using the information of aligned cross-network neighbor-pairs (ACNs). Through comprehensive experiments, we demonstrate that Grad-Align+ exhibits (a) the superiority over benchmark NA methods by a large margin, (b) empirical validations as well as our theoretical findings to see the effectiveness of CNFA, (c) the influence of each component, (d) the robustness to network noises, and (e) the computational efficiency.

翻译：网络对齐（NA）是利用给定网络的拓扑和/或特征信息发现多个网络间节点对应关系的任务。尽管NA方法已在诸多场景中取得显著成功，但其有效性往往依赖于额外信息（如先验锚点链接和/或节点特征），而这些信息可能因隐私保护或访问限制而无法获取。为应对这一实际挑战，我们提出Grad-Align+，一种基于最新最先进的NA方法（即Grad-Align）的新型NA方法——该方法通过逐步发现部分节点对，直至找到所有节点对。在设计Grad-Align+时，我们着重考虑如何在执行NA任务的意义上增强节点特征，以及如何通过最大化利用增强后的节点特征来设计NA方法。为此，我们构建了包含三个关键组件的Grad-Align+：1）基于中心性的节点特征增强（CNFA），2）图神经网络（GNN）辅助的嵌入相似度计算（结合增强节点特征），3）利用已对齐跨网络邻居对（ACNs）信息进行相似度计算的渐进式NA。通过全面实验，我们证明Grad-Align+展现出：（a）相比基准NA方法的显著优越性；（b）支持CNFA有效性的理论发现与实验验证；（c）各组件的影响分析；（d）对网络噪声的鲁棒性；（e）计算高效性。