# Grad-Align+: Empowering Gradual Network Alignment Using Attribute Augmentation

arXiv: https://arxiv.org/abs/2208.11025 · HTML: https://mlsanity.com/paper/2208.11025/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 26 references that are in the map.
- First posted on arXiv 23 Aug 2022.

## Builds on (most cited first, 8 of 8)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [A Survey on Network Embedding](https://mlsanity.com/paper/1711.08752/) (2017)
- [REGAL: Representation Learning-based Graph Alignment](https://mlsanity.com/paper/1802.06257/) (2018)
- [Meta Diagram based Active Social Networks Alignment](https://mlsanity.com/paper/1902.04220/) (2019)
- [On the Power of Gradual Network Alignment Using Dual-Perception Similarities](https://mlsanity.com/paper/2201.10945/) (2022)

## Built on by (most cited first, 3 of 3)

- [WL-Align: Weisfeiler-Lehman Relabeling for Aligning Users across Networks via Regularized Representation Learning](https://mlsanity.com/paper/2212.14182/) (2022)
- [Centrality-Based Node Feature Augmentation for Robust Network Alignment](https://mlsanity.com/paper/2304.12751/) (2023)
- [NAEx: A Plug-and-Play Framework for Explaining Network Alignment](https://mlsanity.com/paper/2508.04731/) (2025)

## Abstract (arXiv)

Network alignment (NA) is the task of discovering node correspondences across different networks. Although NA methods have achieved remarkable success in a myriad of scenarios, their satisfactory performance is not without prior anchor link information and/or node attributes, which may not always be available. In this paper, we propose Grad-Align+, a novel NA method using node attribute augmentation that is quite robust to the absence of such additional information. Grad-Align+ is 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. Specifically, Grad-Align+ is composed of the following key components: 1) augmenting node attributes based on nodes' centrality measures, 2) calculating an embedding similarity matrix extracted from a graph neural network into which the augmented node attributes are fed, and 3) gradually discovering node pairs by calculating similarities between cross-network nodes with respect to the aligned cross-network neighbor-pair. Experimental results demonstrate that Grad-Align+ exhibits (a) superiority over benchmark NA methods, (b) empirical validation of our theoretical findings, and (c) the effectiveness of our attribute augmentation module.