Node Feature Augmentation Vitaminizes Network Alignment

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.