Discrete Graph Auto-Encoder

Yoann Boget, Magda Gregorova, Alexandros Kalousis

Abstract:

Despite advances in generative methods, accurately modeling the distribution of graphs remains a challenging task primarily because of the absence of predefined or inherent unique graph representation.
Two main strategies have emerged to tackle this issue: 1) restricting the number of possible representations by sorting the nodes, or 2) using permutation-invariant/equivariant functions, specifically Graph Neural Networks (GNNs).

In this paper, we introduce a new framework named Discrete Graph Auto-Encoder (DGAE), which leverages the strengths of both strategies and mitigate their respective limitations. In essence, we propose a strategy in 2 steps. We first use a permutation-equivariant auto-encoder to convert graphs into sets of discrete latent node representations, each node being represented by a sequence of quantized vectors. In the second step, we sort the sets of discrete latent representations and learn their distribution with a specifically designed auto-regressive model based on the Transformer architecture.

Through multiple experimental evaluations, we demonstrate the competitive performances of our model in comparison to the existing state-of-the-art across various datasets. Various ablation studies support the interest of our method.

Submission Length: Long submission (more than 12 pages of main content)

Previous TMLR Submission Url: 1808

Changes Since Last Submission: Re-compile the document to fit the margin requirement

Code: https://github.com/yoboget/dgae

Assigned Action Editor: ~Giannis_Nikolentzos1

Submission Number: 1824