paper-with-me

홈 › Papers

Let There Be Order: Rethinking Ordering in Autoregressive Graph Generation

2023-05-24 · Jie Bu, Kazi Sajeed Mehrab, Anuj Karpatne

Conditional graph generation tasks involve training a model to generate a graph given a set of input conditions. Many previous studies employ autoregressive models to incrementally generate graph components such as nodes and edges. However, as graphs typically lack a natural ordering among their components, converting a graph into a sequence of tokens is not straightforward. While prior works mostly rely on conventional heuristics or graph traversal methods like breadth-first search (BFS) or depth-first search (DFS) to convert graphs to sequences, the impact of ordering on graph generation has largely been unexplored. This paper contributes to this problem by: (1) highlighting the crucial role of ordering in autoregressive graph generation models, (2) proposing a novel theoretical framework that perceives ordering as a dimensionality reduction problem, thereby facilitating a deeper understanding of the relationship between orderings and generated graph accuracy, and (3) introducing "latent sort," a learning-based ordering scheme to perform dimensionality reduction of graph tokens. Our experimental results showcase the effectiveness of latent sort across a wide range of graph generation tasks, encouraging future works to further explore and develop learning-based ordering schemes for autoregressive graph generation.

📄 PDF Abstract BibTeX arXiv:2305.15562

Code (1)

jayroxis/ordering-in-graph-generation 공식 구현 pytorch

Tasks

Dimensionality ReductionGraph Generation

Similar Papers 제목 키워드 기반

Learning-Order Autoregressive Models with Application to Molecular Graph Generation

2025-03-07 · Zhe Wang, Jiaxin Shi, Nicolas Heess, Arthur Gretton 외

Autoregressive models (ARMs) have become the workhorse for sequence generation tasks, since many problems can be modeled as next-token prediction. While there appears to be a natural ordering for text (i.e., left-to-righ…

Graph GenerationMolecular Graph Generation

Selecting Optimal Variable Order in Autoregressive Ising Models

2026-02-23 · Shiba Biswal, Marc Vuffray, Andrey Y. Lokhov arxiv

Autoregressive models enable tractable sampling from learned probability distributions, but their performance critically depends on the variable ordering used in the factorization via complexities of the resulting condit…

NEAT: Neighborhood-Guided, Efficient, Autoregressive Set Transformer for 3D Molecular Generation

2025-12-05 · Daniel Rose, Roxane Axel Jacob, Johannes Kirchmair, Thierry Langer arxiv

Transformer-based autoregressive models offer an efficient alternative to diffusion- and flow-matching-based approaches for generating 3D molecules. One challenge remains: standard transformer architectures require a seq…

Order Matters: Probabilistic Modeling of Node Sequence for Graph Generation

2021-06-11 · Xiaohui Chen, Xu Han, Jiajing Hu, Francisco J. R. Ruiz 외

A graph generative model defines a distribution over graphs. One type of generative model is constructed by autoregressive neural networks, which sequentially add nodes and edges to generate a graph. However, the likelih…

Graph GenerationVariational Inference

Pard: Permutation-Invariant Autoregressive Diffusion for Graph Generation

2024-02-06 · Lingxiao Zhao, Xueying Ding, Leman Akoglu

Graph generation has been dominated by autoregressive models due to their simplicity and effectiveness, despite their sensitivity to ordering. Yet diffusion models have garnered increasing attention, as they offer compar…

DenoisingGraph GenerationSensitivity