Вход на сайт

Просмотр новости

Найдите то, что Вас интересует

FLAGG: Flexible Autoregressive Graph Generation

Дата публикации: 17-08-2026 20:26:00


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.

Схожие новости

#Наименование новостиТональностьИнформативностьДата публикации
1 Approximation-Free Differentiable Oblique Decision Trees 09.617-08-2026
2Архитектурный паттерн «LangGraph, гибридный RAG + Сигнатурный движок»: универсальный граф для потоковых данных09.1102-08-2026
3 Error Analyses of Auto-Regressive Video Diffusion Models 010.6117-08-2026
4 Learning general conditional independence structures via the neighbourhood lattice 06.7917-08-2026
5 Graph-based Clustering Revisited: A Relaxation of Kernel k-Means Perspective 010.9417-08-2026
6RAG vs GraphRAG: When Agents Hallucinate Answers01007-03-2026
7RAG vs. Agentic RAG: Architecture, Tradeoffs, and How to Choose07.7729-07-2026
8Как я построил Graph RAG систему с точностью 96.7% за 5 дней: от научных статей до production-ready пайплайна020.8925-02-2026
9Monitoring LangGraph agents with Datadog: a practical guide04.9529-05-2026

Классификация: Пресс-релизы. Схожих патентов: 0. Схожих новостей: 9. Тональность: 0. Информативность: 6.46. Источник: jmlr.org.