MoFlow: an invertible flow model for generating molecular graphs
-
Updated
Mar 14, 2023 - Python
MoFlow: an invertible flow model for generating molecular graphs
A Data-Driven Graph Generative Model for Temporal Interaction Networks
SCOTT: Synthesizing Curvature Operations and Topological Tools
DYnamic MOtif-NoDes (DYMOND) is a dynamic network generative model based on temporal motifs and node behavior.
Official implementation of the ANFM graph generative model (TMLR, 2026)
[NeurIPS 2024] Diffusion Twigs with Loop Guidance for Conditional Graph Generation
DYnamic Attributed Node rolEs (DYANE) is an attributed dynamic-network generative model based on temporal motifs and attributed node behavior.
This is the official implementation of the FLAGG framework as published in the 2026 JMLR paper "FLAGG: Flexible Autoregressive Graph Generation". The framework is highly customizable to create new combinations of autoregressive graph generative models with existing and yet-to-exist one-shot models.
To associate your repository with the graph-generative-model topic, visit your repo's landing page and select "manage topics."