T-GAE: Transferable Graph Autoencoder for Network Alignment

TL;DR

T-GAE introduces a transferable graph autoencoder that enables efficient, out-of-distribution network alignment without retraining, outperforming existing methods in accuracy and speed on large-scale real-world graphs.

Contribution

The paper proposes T-GAE, a novel transferable GNN-based autoencoder framework that improves network alignment efficiency and accuracy without retraining on new graphs.

Findings

T-GAE outperforms state-of-the-art methods by up to 50.8%.

Reduces training time by 90% on large-scale networks.

Proves GNN embeddings can surpass spectral methods in alignment accuracy.

Abstract

Network alignment is the task of establishing one-to-one correspondences between the nodes of different graphs. Although finding a plethora of applications in high-impact domains, this task is known to be NP-hard in its general form. Existing optimization algorithms do not scale up as the size of the graphs increases. While being able to reduce the matching complexity, current GNN approaches fit a deep neural network on each graph and requires re-train on unseen samples, which is time and memory inefficient. To tackle both challenges we propose T-GAE, a transferable graph autoencoder framework that leverages transferability and stability of GNNs to achieve efficient network alignment on out-of-distribution graphs without retraining. We prove that GNN-generated embeddings can achieve more accurate alignment compared to classical spectral methods. Our experiments on real-world benchmarks demonstrate that T-GAE outperforms the state-of-the-art optimization method and the best GNN approach by up to 38.7% and 50.8%, respectively, while being able to reduce 90% of the training time when matching out-of-distribution large scale networks. We conduct ablation studies to highlight the effectiveness of the proposed encoder architecture and training objective in enhancing the expressiveness of GNNs to match perturbed graphs. T-GAE is also proved to be flexible to utilize matching algorithms of different complexities. Our code is available at https://github.com/Jason-Tree/T-GAE.