The paper introduces xVGAE, a hierarchical variational graph autoencoder designed for exchangeable graphs. Leveraging the Aldous-Hoover theorem, the model uses a graph-level latent variable, exchangeable node-specific latent variables, and a graphon function to learn and generate graph distributions efficiently. Experiments demonstrate that xVGAE produces high-quality graphs quickly while capturing key structural properties of the training data.
By Daniele Micheletti, Federica Zoe Ricci, Erik B. Sudderth
arXiv:2610.19781v1 Announce Type: cross
Abstract: We introduce SNACK, a string representation for probabilistic graph generation that enables sequence models to generate and model graphs with discret...
By Hohyun Kim, Hyesung Kim, Min-hwan Oh, Seunggeun Lee
GraphK introduces an encoder‑sampler‑decoder framework that generates variable‑size graphs efficiently. It learns permutation‑invariant latent representations and samples new node embeddings via maximum likelihood, enabling both upscaling and downscaling of graph size. Edge construction uses KDTree‑based top‑k neighbor search in latent space, reducing computational cost while capturing graph properties.
By Resul Tugay, Eren Olu\u{g}, Elif Ak, Sule Gunduz Oguducu
The paper introduces Variational Bayesian Flow Network (VBFN), a graph generation model that lifts Bayesian updates to a joint Gaussian belief family with structured precisions, enabling coupled node and edge updates in a single fusion step. By constructing sample‑agnostic sparse precisions from a representation‑induced dependency graph, VBFN avoids label leakage while enforcing node‑edge consistency. Experiments on synthetic and molecular graph datasets show that VBFN improves fidelity and diversity over baseline methods.
By Yida Xiong, Jiameng Chen, Xiuwen Gong, Jia Wu, Shirui Pan, Wenbin Hu
arXiv:2509. 22468v2 Announce Type: replace-cross Abstract: High-quality molecular representations are essential for property prediction and molecular design, yet large labeled datasets remain scarce.
By Boshra Ariguib, Mathias Niepert, Andrei Manolache
arXiv:2603. 23398v3 Announce Type: replace-cross Abstract: Generative modeling of discrete data, such as graphs, underpins many scientific and industrial applications, including molecular discovery and materials design.
By Michal Balcerak, Suprosanna Shit, Chinmay Prabhakar, Sebastian Kaltenbach, Michael S. Albergo, Yilun Du, Bjoern Menze
The paper introduces concept bottlenecks into deep graph generators to enhance interpretability and steerability in molecular graph generation. By embedding human-interpretable concepts, the authors demonstrate improved distributional fidelity (lower FCD) while maintaining validity and uniqueness. They also present a Concept Controller optimization method for steering generation, evaluated within a one-shot molecular graph generation framework.
By Sarabeshwar Balaji, Ritesh Kumar, Lav R. Varshney
arXiv:2605. 16836v2 Announce Type: replace-cross Abstract: Hypergraphs provide a principled framework for modeling polyadic interactions, with applications in recommendation systems, social networks, and molecular modeling.
By Xinyi Hong, Shuntuo Xu, Zhou Yu
arXiv:2606. 04287v1 Announce Type: cross Abstract: Generating realistic and diverse graphs is a key problem in machine learning, with applications in molecular discovery, circuit design, cybersecurity, and beyond.
By Alessio Barboni, Massimiliano Lupo Pasini, Bishal Lakha, Edoardo Serra
arXiv:2603. 08825v2 Announce Type: replace-cross Abstract: Discrete graph generation has emerged as a powerful paradigm for modeling graph-structured data, yet state of the art models often rely on Graph Transformers or higher order architectures.
By Jay Revolinsky, Harry Shomer, Jiliang Tang
arXiv:2607. 09277v1 Announce Type: new Abstract: Three-dimensional (3D) molecule generation has been dominated by diffusion models, which achieve strong generation quality but typically require the molecular size to be specified a priori.
By Federico Ottomano, Gaopeng Ren, Yingzhen Li, Kim E. Jelfs, Alex M. Ganose
Embedded Graph Flows (EGF) is a generative model for categorical graphs that learns continuous embeddings for node and unordered-edge categories and uses a permutation‑equivariant graph transformer to transport Gaussian noise toward these embeddings. A terminal readout then maps the embeddings back to discrete graph categories. EGF achieves competitive performance on molecular benchmarks, outperforming other methods on QM9 and maintaining low maximum mean discrepancy on ZINC250k.
By Ethan Ma, Zihan Wang, Chris Siu Yeung Chow, Xinguo Feng, Qingqing Li, Rui Jiang, Naipeng Dong, Guangdong Bai