Graphon is a nonparametric model that generates graphs with arbitrary sizes and can be induced from graphs easily. Based on this model, we propose a novel algorithmic framework called \textit{graphon autoencoder} to build an interpretable and scalable graph generative model. This framework treats observed graphs as induced graphons in functional space and derives their latent representations by an encoder that aggregates Chebshev graphon filters. A linear graphon factorization model works as a decoder, leveraging the latent representations to reconstruct the induced graphons (and the corresponding observed graphs). We develop an efficient learning algorithm to learn the encoder and the decoder, minimizing the Wasserstein distance between the model and data distributions. This algorithm takes the KL divergence of the graph distributions conditioned on different graphons as the underlying distance and leads to a reward-augmented maximum likelihood estimation. The graphon autoencoder provides a new paradigm to represent and generate graphs, which has good generalizability and transferability.
翻译:图形是一个非参数模型, 生成具有任意大小的图形, 并且可以很容易地从图形中导出。 基于此模型, 我们提出一个叫做\ textit{graphon 自动编码器} 的新式算法框架, 以构建一个可解释和可缩放的图形基因化模型。 这个框架将观测到的图形作为功能空间中的引图解, 并通过一个总合Chebshev 图形过滤器的编码器得出其潜在图解。 一个线性图形化系数模型作为解码器发挥作用, 利用潜在图解来重建导图解( 和相应观测到的图表 ) 。 我们开发了一个高效的学习算法, 以学习编码器和解码器, 最大限度地减少模型和数据分布之间的瓦塞斯坦距离。 这个算法将不同图形分布的 KL 差异作为基本距离, 并导致一个有偿的放大最大可能性估计。 图形化图解解算器提供了一个新的模式, 以显示和生成图表, 具有良好的可概括性和可转移性 。