# ReLU Networks for Exact Generation of Similar Graphs

Source: [ReLU Networks for Exact Generation of Similar Graphs](<https://www.sota2.com/research/paper/69d5e13d7d0172140ec75c95>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-09T05:00:13.067Z

Authors: Mamoona Ghafoor, Tatsuya Akutsu

Published: 2026-04-07T14:31:19.000Z

## Abstract

Generation of graphs constrained by a specified graph edit distance from a source graph is important in applications such as cheminformatics, network anomaly synthesis, and structured data augmentation. Despite the growing demand for such constrained generative models in areas including molecule design and network perturbation analysis, the neural architectures required to provably generate graphs within a bounded graph edit distance remain largely unexplored. In addition, existing graph generative models are predominantly data-driven and depend heavily on the availability and quality of training data, which may result in generated graphs that do not satisfy the desired edit distance constraints. In this paper, we address these challenges by theoretically characterizing ReLU neural networks capable of generating graphs within a prescribed graph edit distance from a given graph. In particular, we show the existence of constant depth and O(n^2 d) size ReLU networks that deterministically generate graphs within edit distance d from a given input graph with n vertices, eliminating reliance on training data while guaranteeing validity of the generated graphs. Experimental evaluations demonstrate that the proposed network successfully generates valid graphs for instances with up to 1400 vertices and edit distance bounds up to 140, whereas baseline generative models fail to generate graphs with the desired edit distance. These results provide a theoretical foundation for constructing compact generative models with guaranteed validity.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Graph Generation on Vertex-labeled Synthetic Graphs (test)](<https://www.sota2.com/research/sota/graph-generation-on-vertex-labeled-synthetic-graphs-test.md>): Graph generation; Vertex-labeled Synthetic Graphs (test); Edge Count (N\_\|E\|): 500.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.05929>)

[PDF](<https://arxiv.org/pdf/2604.05929.pdf>)