Discrete Graph Auto-Encoder. (arXiv:2306.07735v2 [cs.LG] UPDATED)

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 …

advances arxiv auto cs.lg distribution encoder functions generative graph graph representation graphs issue modeling representation sorting strategies