用Transformer+位置编码实现更精准的图链接预测。
Generalized Graph Transformer Variational Autoencoder
- 引入广义图Transformer与变分自编码框架，无需消息传递
- 在多个基准数据集上ROC-AUC和平均精度均超越基线
- 适合关注图结构生成与自注意力机制的读者
图链接预测在图表示学习中长期是核心问题，涉及网络分析与生成建模。深度学习发展推动了复杂架构的出现以捕捉图数据中的关系依赖。本文提出广义图Transformer变分自编码器（GGT-VAE），将广义图Transformer架构与变分自编码器框架结合用于链接预测。与以往的GraphVAE、GCN或GNN方法不同，GGT-VAE利用Transformer风格的全局自注意力机制与拉普拉斯位置编码，在不依赖消息传递的前提下，将节点间的结构模式映射到潜在空间。在多个基准数据集上的实验表明，GGT-VAE在ROC-AUC与平均精度指标上均持续优于基线模型。据我们所知，这是首个在变分框架下探索以广义图Transformer为骨干进行图结构生成的研究。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。