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:2606. 11831v1 Announce Type: cross Abstract: Neural relational inference (NRI) methods discover interaction graphs from trajectories through variational reasoning on discrete potential edges.
By Qi Shao, Hao Guo, Jiawen Chen, Duxin Chen, Wenwu Yu
The paper introduces JSP-GFN, a Generative Flow Network that jointly infers the structure and parameters of a Bayesian Network. It sequentially generates a directed acyclic graph edge by edge and then samples the corresponding conditional probability parameters once the full structure is known. Experiments on simulated and real data show that JSP‑GFN accurately approximates the joint posterior and outperforms existing methods.
By Tristan Deleu, Mizu Nishikawa-Toomey, Jithendaraa Subramanian, Esmeralda S. Whitammer, Laurent Charlin, Yoshua Bengio
arXiv:2510. 03690v4 Announce Type: replace Abstract: Real-world graph datasets often arise from mixtures of populations, where graphs are generated by multiple distinct underlying distributions.
By Ali Azizpour, Reza Ramezanpour, Santiago Segarra
The paper investigates how alignment—both outer (choosing which graphs to pair) and inner (aligning node representatives)—affects permutation-equivariant graph flow matching. It connects inner alignment to transport on the graph quotient space and shows that quotient couplings can be lifted to aligned representatives, while symmetrization yields equivariant flow‑matching minimizers. Experiments on continuous graph and molecular generation demonstrate that appropriate alignment can simplify trajectories and improve few‑step generation, though the benefits vary with the type of alignment and computational budget.
By Moritz Piening, Christian Wald
arXiv:2609.07961v1 Announce Type: new
Abstract: Graph modeling, a crucial task for representing complex relationships in graph-structured data, has achieved significant success in recent years. Howev...
By Thanh-Dat Truong, Sarah Alharbi, Susan Gauch, Xinghui Zhao, Marios Savvides, Khoa Luu
arXiv:2609.39739v1 Announce Type: new
Abstract: Graph generative models increasingly rely on Graph Transformers (GT) to capture complex dependencies among nodes and edges. While deeper architectures...
By Luca Miglior, Alessio Gravina, Davide Bacciu
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:2602. 18084v2 Announce Type: replace Abstract: Equivariance is central to graph generative models, as it ensures the model respects the permutation symmetry of graphs.
By Benjamin Honor\'e, Alba Carballo-Castro, Yiming Qin, Pascal Frossard
arXiv:2607. 07510v1 Announce Type: cross Abstract: Generating signals on graphs requires permutation-equivariant models that exhibit stability with respect to relative structural perturbations.
By Martin Schmidt, Gonzalo Mateos
The paper introduces three distance‑based graph autoencoder variants that add structural penalties to the reconstruction loss. All models use a two‑layer Graph Convolutional Network encoder and a Euclidean‑distance decoder, with two node‑level regularizers: a hub penalty based on degree centrality and a penalty based on Natural Community Local Intrinsic Dimensionality (NC‑LID). Experiments on multiple dynamic graph datasets show that incorporating NC‑LID regularization consistently improves reconstruction performance compared to baselines without structural regularization and to the hub‑aware variant.
By Aleksandar Tom\v{c}i\'c, Milo\v{s} Savi\'c, Milo\v{s} Radovanovi\'c
arXiv:2608.21825v1 Announce Type: new
Abstract: Learning adjacency matrices from node-link images is a fundamental problem for recovering structured graph information from visual observations. Existi...
By Jiahao Xie, Guangmo Tong