arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2501.13133cs.LGcs.AI
收藏

基于扩散生成模型的图表示学习

Graph Representation Learning with Diffusion Generative Models

Daniel Wesego

AI总结:

针对扩散模型因图的离散性难以应用于图结构数据的问题,提出在自编码器框架内训练离散扩散模型,结合编码器输出与解码器首步隐藏嵌入提取图表征,验证了离散扩散模型用于图表示学习的可行性。

摘要:

扩散模型凭借对复杂数据分布的精准拟合能力,已成为图像、视频等多种数据模态下性能最优的生成模型。与VAE(变分自编码器)、GAN(生成对抗网络)等传统生成方法不同,扩散模型采用渐进式去噪流程,通过多步迭代将噪声转化为有意义的数据,这种渐进式机制提升了模型的表达能力与生成质量。不仅如此,研究证实扩散模型在学习生成样本的过程中,还能从数据中提取有价值的表征。尽管扩散模型成果显著,但其在图结构数据上的应用仍有待深入探索,核心原因在于图的离散性要求使用与其他领域连续方法不同的离散扩散过程。本研究利用扩散模型的表征能力为图数据学习有效嵌入,通过在自编码器框架内训练离散扩散模型,实现适配图结构数据独有特性的高效自编码与表征学习。我们从编码器输出与解码器首时间步隐藏嵌入的组合中提取表征。该方法验证了离散扩散模型应用于图表示学习的潜力,代码可访问https://github.com/DanielMitiku/Graph-Representation-Learning-with-Diffusion-Generative-Models获取。

英文摘要:

Diffusion models have established themselves as state-of-the-art generative models across various data modalities, including images and videos, due to their ability to accurately approximate complex data distributions. Unlike traditional generative approaches such as VAEs and GANs, diffusion models employ a progressive denoising process that transforms noise into meaningful data over multiple iterative steps. This gradual approach enhances their expressiveness and generation quality. Not only that, diffusion models have also been shown to extract meaningful representations from data while learning to generate samples. Despite their success, the application of diffusion models to graph-structured data remains relatively unexplored, primarily due to the discrete nature of graphs, which necessitates discrete diffusion processes distinct from the continuous methods used in other domains. In this work, we leverage the representational capabilities of diffusion models to learn meaningful embeddings for graph data. By training a discrete diffusion model within an autoencoder framework, we enable both effective autoencoding and representation learning tailored to the unique characteristics of graph-structured data. We extract the representation from the combination of the encoder's output and the decoder's first time step hidden embedding. Our approach demonstrates the potential of discrete diffusion models to be used for graph representation learning. The code can be found at https://github.com/DanielMitiku/Graph-Representation-Learning-with-Diffusion-Generative-Models

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。

↑