Autoregressive Models for Sequences of Graphs
This paper proposes an autoregressive (AR) model for sequences of graphs, which generalises traditional AR models. A first novelty consists in formalising the AR model for a very general family of graphs, characterised by a variable topology, and attributes associated with nodes and edges. A graph neural network (GNN) is also proposed to learn the AR function associated with the graph-generating process (GGP), and subsequently predict the next graph in a sequence. The proposed method is compared with four baselines on synthetic GGPs, denoting a significantly better performance on all considered problems.
Code (2)
Tasks
Graph Neural NetworkSimilar Papers 제목 키워드 기반
Towards Fast Graph Generation via Autoregressive Noisy Filtration Modeling
Graph generative models often face a critical trade-off between learning complex distributions and achieving fast generation speed. We introduce Autoregressive Noisy Filtration Modeling (ANFM), a novel approach that addr…
Graph GenerationTopological Data AnalysisFlatten Graphs as Sequences: Transformers are Scalable Graph Generators
We introduce AutoGraph, a novel autoregressive framework for generating large attributed graphs using decoder-only transformers. At the core of our approach is a reversible "flattening" process that transforms graphs int…
DecoderGraph GenerationLanguage ModelingLanguage Modelling+1Scaling State-Space Models from Lines to Paragraphs: An Ablation of Mamba-based OCR
End-to-end OCR increasingly relies on autoregressive sequence models, where the quadratic cost of Transformer attention limits efficient transcription of long, paragraph-level text. State-Space Models (SSMs) such as Mamb…
Scaling Novel Graph Generation via Lightweight Structure-Guided Autoregressive Models
Generating realistic and diverse graphs is a key problem in machine learning, with applications in molecular discovery, circuit design, cybersecurity, and beyond. However, current graph generative models remain limited b…
Graph GenerationAutoregressive Models for Knowledge Graph Generation
Knowledge Graph (KG) generation requires models to learn complex semantic dependencies between triples while maintaining domain validity constraints. Unlike link prediction, which scores triples independently, generative…
Computational EfficiencyGraph GenerationLink Prediction