arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.13655cs.LG
收藏

Gransformer:基于Transformer的图生成

Gransformer: Transformer-based Graph Generation

Sharif University of Technology(谢里夫理工大学)

Ahmad Khajenezhad, Seyed Ali Osia, Mahmood Karimian, Hamid Beigy

AI总结:

本文提出Gransformer,一种基于Transformer的图生成算法,通过修改编码器、引入基于消息传递的自回归熟悉度度量、使用掩码自编码器进行密度估计及BFS节点排序技术,在合成和真实数据集上实现了与循环模型和图卷积网络相当的性能。

摘要:

Transformer已广泛应用于自然语言处理和机器视觉等各种任务中。本文提出了Gransformer,一种基于Transformer的图生成算法。我们修改了Transformer编码器以利用给定图的结构信息。注意力机制被调整以考虑每对节点之间边的存在与否。我们还引入了一种基于图的节点对熟悉度度量,适用于注意力和位置编码。这种熟悉度度量基于消息传递算法,并包含图的结构信息。此外,该度量是自回归的,使我们的模型能够在单次前向传递中获得必要的条件概率。在输出层,我们还使用掩码自编码器进行密度估计,以高效建模连接到每个节点的依赖边的顺序生成。此外,我们提出了一种技术,通过使用BFS节点排序来防止模型生成与前置节点无连接的孤立节点。我们使用合成和真实世界数据集评估该方法,并将其与相关方法进行比较,包括循环模型和图卷积网络。实验结果表明,所提出的方法与这些方法性能相当。

英文摘要:

Transformers have become widely used in various tasks, such as natural language processing and machine vision. This paper proposes Gransformer, an algorithm based on Transformer for generating graphs. We modify the Transformer encoder to exploit the structural information of the given graph. The attention mechanism is adapted to consider the presence or absence of edges between each pair of nodes. We also introduce a graph-based familiarity measure between node pairs that applies to both the attention and the positional encoding. This measure of familiarity is based on message-passing algorithms and contains structural information about the graph. Also, this measure is autoregressive, which allows our model to acquire the necessary conditional probabilities in a single forward pass. In the output layer, we also use a masked autoencoder for density estimation to efficiently model the sequential generation of dependent edges connected to each node. In addition, we propose a technique to prevent the model from generating isolated nodes without connection to preceding nodes by using BFS node orderings. We evaluate this method using synthetic and real-world datasets and compare it with related ones, including recurrent models and graph convolutional networks. Experimental results show that the proposed method performs comparatively to these methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑