Towards Unsupervised Training of Matching-based Graph Edit Distance Solver via Preference-aware GAN

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huang, Wei, Wang, Hanchen, Wen, Dong, Ma, Shaozhen, Zhang, Wenjie, Lin, Xuemin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912643782017024
author Huang, Wei
Wang, Hanchen
Wen, Dong
Ma, Shaozhen
Zhang, Wenjie
Lin, Xuemin
author_facet Huang, Wei
Wang, Hanchen
Wen, Dong
Ma, Shaozhen
Zhang, Wenjie
Lin, Xuemin
contents Graph Edit Distance (GED) is a fundamental graph similarity metric widely used in various applications. However, computing GED is an NP-hard problem. Recent state-of-the-art hybrid GED solver has shown promising performance by formulating GED as a bipartite graph matching problem, then leveraging a generative diffusion model to predict node matching between two graphs, from which both the GED and its corresponding edit path can be extracted using a traditional algorithm. However, such methods typically rely heavily on ground-truth supervision, where the ground-truth node matchings are often costly to obtain in real-world scenarios. In this paper, we propose GEDRanker, a novel unsupervised GAN-based framework for GED computation. Specifically, GEDRanker consists of a matching-based GED solver and introduces an interpretable preference-aware discriminator. By leveraging preference signals over different node matchings derived from edit path lengths, the discriminator can guide the matching-based solver toward generating high-quality node matching without the need for ground-truth supervision. Extensive experiments on benchmark datasets demonstrate that our GEDRanker enables the matching-based GED solver to achieve near-optimal solution quality without any ground-truth supervision.
format Preprint
id arxiv_https___arxiv_org_abs_2506_01977
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Unsupervised Training of Matching-based Graph Edit Distance Solver via Preference-aware GAN
Huang, Wei
Wang, Hanchen
Wen, Dong
Ma, Shaozhen
Zhang, Wenjie
Lin, Xuemin
Machine Learning
Artificial Intelligence
Graph Edit Distance (GED) is a fundamental graph similarity metric widely used in various applications. However, computing GED is an NP-hard problem. Recent state-of-the-art hybrid GED solver has shown promising performance by formulating GED as a bipartite graph matching problem, then leveraging a generative diffusion model to predict node matching between two graphs, from which both the GED and its corresponding edit path can be extracted using a traditional algorithm. However, such methods typically rely heavily on ground-truth supervision, where the ground-truth node matchings are often costly to obtain in real-world scenarios. In this paper, we propose GEDRanker, a novel unsupervised GAN-based framework for GED computation. Specifically, GEDRanker consists of a matching-based GED solver and introduces an interpretable preference-aware discriminator. By leveraging preference signals over different node matchings derived from edit path lengths, the discriminator can guide the matching-based solver toward generating high-quality node matching without the need for ground-truth supervision. Extensive experiments on benchmark datasets demonstrate that our GEDRanker enables the matching-based GED solver to achieve near-optimal solution quality without any ground-truth supervision.
title Towards Unsupervised Training of Matching-based Graph Edit Distance Solver via Preference-aware GAN
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2506.01977