FLAGG: Flexible Autoregressive Graph Generation
2026-06-03 • Machine Learning
Machine Learning
AI summaryⓘ
The authors discuss two main ways to create graphs with AI: one-shot models that generate everything at once, and sequential models that build graphs step-by-step. Each way works better for certain kinds of graphs but not all. They propose a new method called FLAGG that splits the graph into parts and generates each part using one-shot models in a sequence. This approach combines the advantages of both methods, and their tests show FLAGG produces better quality graphs than just one-shot or sequential methods alone.
graph generationone-shot modelssequential modelsautoregressiveFLAGGstochastic node removalinsertion modelsampling qualityDiGress
Authors
Samuel Cognolato, Alessandro Sperduti, Luciano Serafini
Abstract
The Deep Graph Generation's panorama spans two extremes: one-shot and sequential models. The former generates nodes and edges jointly, while the latter samples them autoregressively. Each method performs better in different graph domains depending on size and topology, but neither is applicable to all graph categories. For instance, one-shot methods struggle with generating large graphs, while sequential methods underperform on smaller graphs. A possible way to overcome these limitations is to flexibly combine the two methods in a unique system. In this work, we propose the FLAGG (Flexible Autoregressive Graph Generation) framework, which sequentially generates portions of graphs with one-shot models. FLAGG can apply any one-shot model to make it autoregressive, allowing flexibility in choosing the sequential policy. This policy is specified through a stochastic node removal process, which an Insertion Model learns to reverse. We evaluate FLAGG with the DiGress one-shot model on several data sets of different graph sizes and domains. We show that the approach outperforms both one-shot and autoregressive baselines in terms of sampling quality.