English

Generalized Graph Transformer Variational Autoencoder

Machine Learning 2025-12-02 v1 Artificial Intelligence

Abstract

Graph link prediction has long been a central problem in graph representation learning in both network analysis and generative modeling. Recent progress in deep learning has introduced increasingly sophisticated architectures for capturing relational dependencies within graph-structured data. In this work, we propose the Generalized Graph Transformer Variational Autoencoder (GGT-VAE). Our model integrates Generalized Graph Transformer Architecture with Variational Autoencoder framework for link prediction. Unlike prior GraphVAE, GCN, or GNN approaches, GGT-VAE leverages transformer style global self-attention mechanism along with laplacian positional encoding to model structural patterns across nodes into a latent space without relying on message passing. Experimental results on several benchmark datasets demonstrate that GGT-VAE consistently achieves above-baseline performance in terms of ROC-AUC and Average Precision. To the best of our knowledge, this is among the first studies to explore graph structure generation using a generalized graph transformer backbone in a variational framework.

Keywords

Cite

@article{arxiv.2512.00612,
  title  = {Generalized Graph Transformer Variational Autoencoder},
  author = {Siddhant Karki},
  journal= {arXiv preprint arXiv:2512.00612},
  year   = {2025}
}