GRAIL trains graph predictors via imitation learning by modeling generation as sequential decisions on partial graph embeddings, matching or exceeding prior methods on 18 benchmarks.
Learning Deep Generative Models of Graphs
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
abstract
Graphs are fundamental data structures which concisely capture the relational structure in many important real-world domains, such as knowledge graphs, physical and social interactions, language, and chemistry. Here we introduce a powerful new approach for learning generative models over graphs, which can capture both their structure and attributes. Our approach uses graph neural networks to express probabilistic dependencies among a graph's nodes and edges, and can, in principle, learn distributions over any arbitrary graph. In a series of experiments our results show that once trained, our models can generate good quality samples of both synthetic graphs as well as real molecular graphs, both unconditionally and conditioned on data. Compared to baselines that do not use graph-structured representations, our models often perform far better. We also explore key challenges of learning generative models of graphs, such as how to handle symmetries and ordering of elements during the graph generation process, and offer possible solutions. Our work is the first and most general approach for learning generative models over arbitrary graphs, and opens new directions for moving away from restrictions of vector- and sequence-like knowledge representations, toward more expressive and flexible relational data structures.
citation-role summary
background 1
citation-polarity summary
years
2026 6roles
background 1polarities
background 1representative citing papers
A new discrete diffusion model for scene graph generation from text captures object-relation dependencies via hierarchical constraints and training-free conditioning, yielding better graph metrics and downstream image alignment than prior baselines.
Large-scale graph language models acquire structural regularities beyond memorization, with subgraph rank correlations persisting after bootstrap and novel-subset controls, especially for high-frequency patterns.
A post-extraction ontology correction pipeline for neuro-symbolic KG construction reduces LLM token usage while improving consistency and preserving QA quality.
PlantPose combines learned graph generation with classical tree-enforcing algorithms and a large mixed real/synthetic dataset to estimate arbitrary plant skeletons from varied image styles including out-of-domain cases.
A genetic algorithm refines output graphs from a WGAN-GNN framework, consistently lowering combined MMD relative to the base generator.
citing papers explorer
-
Dependency-Aware Discrete Diffusion for Scene Graph Generation
A new discrete diffusion model for scene graph generation from text captures object-relation dependencies via hierarchical constraints and training-free conditioning, yielding better graph metrics and downstream image alignment than prior baselines.