paper-with-me

Papers

GRAN is superior to GraphRNN: node orderings, kernel- and graph embeddings-based metrics for graph generators

2023-07-13 · Ousmane Touat, Julian Stier, Pierre-Edouard Portier, Michael Granitzer

A wide variety of generative models for graphs have been proposed. They are used in drug discovery, road networks, neural architecture search, and program synthesis. Generating graphs has theoretical challenges, such as isomorphic representations -- evaluating how well a generative model performs is difficult. Which model to choose depending on the application domain? We extensively study kernel-based metrics on distributions of graph invariants and manifold-based and kernel-based metrics in graph embedding space. Manifold-based metrics outperform kernel-based metrics in embedding space. We use these metrics to compare GraphRNN and GRAN, two well-known generative models for graphs, and unveil the influence of node orderings. It shows the superiority of GRAN over GraphRNN - further, our proposed adaptation of GraphRNN with a depth-first search ordering is effective for small-sized graphs. A guideline on good practices regarding dataset selection and node feature initialization is provided. Our work is accompanied by open-source code and reproducible experiments.

📄 PDF Abstract BibTeX arXiv:2307.06709

Code (1)

otouat/gnnevaluationmetrics 공식 구현 pytorch

Tasks

Drug DiscoveryGraph EmbeddingNeural Architecture SearchProgram Synthesis

Similar Papers 제목 키워드 기반

GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models

2018-02-24 · ICML 2018 7 · Jiaxuan You, Rex Ying, Xiang Ren, William L. Hamilton 외

Modeling and generating graphs is fundamental for studying networks in biology, engineering, and social sciences. However, modeling complex distributions over graphs and then efficiently sampling from these distributions…

Graph Generation

Efficient Graph Generation with Graph Recurrent Attention Networks

2019-10-02 · NeurIPS 2019 12 · Renjie Liao, Yujia Li, Yang Song, Shenlong Wang 외

We propose a new family of efficient and expressive deep generative models of graphs, called Graph Recurrent Attention Networks (GRANs). Our model generates graphs one block of nodes and associated edges at a time. The b…

Graph Generation

A Deep Generative Model for the Simulation of Discrete Karst Networks

2025-06-11 · Dany Lauzon, Julien Straubhaar, Philippe Renard

The simulation of discrete karst networks presents a significant challenge due to the complexity of the physicochemical processes occurring within various geological and hydrogeological contexts over extended periods. Th…

Denoising

GraphRNN Revisited: An Ablation Study and Extensions for Directed Acyclic Graphs

2023-07-26 · Taniya Das, Mark Koch, Maya Ravichandran, Nikhil Khatri

GraphRNN is a deep learning-based architecture proposed by You et al. for learning generative models for graphs. We replicate the results of You et al. using a reproduced implementation of the GraphRNN architecture and e…

Cluster-wise Graph Transformer with Dual-granularity Kernelized Attention

2024-10-09 · Siyuan Huang, Yunchong Song, Jiayue Zhou, Zhouhan Lin

In the realm of graph learning, there is a category of methods that conceptualize graphs as hierarchical structures, utilizing node clustering to capture broader structural information. While generally effective, these m…

Graph LearningNode Clustering