Enregistré dans:
Détails bibliographiques
Auteurs principaux: Verma, Samidha, Goyal, Arushi, Mathur, Ananya, Anand, Ankit, Ranu, Sayan
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2505.02124
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866918008663834624
author Verma, Samidha
Goyal, Arushi
Mathur, Ananya
Anand, Ankit
Ranu, Sayan
author_facet Verma, Samidha
Goyal, Arushi
Mathur, Ananya
Anand, Ankit
Ranu, Sayan
contents Graph Edit Distance (GED) is a widely used metric for measuring similarity between two graphs. Computing the optimal GED is NP-hard, leading to the development of various neural and non-neural heuristics. While neural methods have achieved improved approximation quality compared to non-neural approaches, they face significant challenges: (1) They require large amounts of ground truth data, which is itself NP-hard to compute. (2) They operate as black boxes, offering limited interpretability. (3) They lack cross-domain generalization, necessitating expensive retraining for each new dataset. We address these limitations with GRAIL, introducing a paradigm shift in this domain. Instead of training a neural model to predict GED, GRAIL employs a novel combination of large language models (LLMs) and automated prompt tuning to generate a program that is used to compute GED. This shift from predicting GED to generating programs imparts various advantages, including end-to-end interpretability and an autonomous self-evolutionary learning mechanism without ground-truth supervision. Extensive experiments on seven datasets confirm that GRAIL not only surpasses state-of-the-art GED approximation methods in prediction quality but also achieves robust cross-domain generalization across diverse graph distributions.
format Preprint
id arxiv_https___arxiv_org_abs_2505_02124
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GRAIL: Graph Edit Distance and Node Alignment Using LLM-Generated Code
Verma, Samidha
Goyal, Arushi
Mathur, Ananya
Anand, Ankit
Ranu, Sayan
Machine Learning
Graph Edit Distance (GED) is a widely used metric for measuring similarity between two graphs. Computing the optimal GED is NP-hard, leading to the development of various neural and non-neural heuristics. While neural methods have achieved improved approximation quality compared to non-neural approaches, they face significant challenges: (1) They require large amounts of ground truth data, which is itself NP-hard to compute. (2) They operate as black boxes, offering limited interpretability. (3) They lack cross-domain generalization, necessitating expensive retraining for each new dataset. We address these limitations with GRAIL, introducing a paradigm shift in this domain. Instead of training a neural model to predict GED, GRAIL employs a novel combination of large language models (LLMs) and automated prompt tuning to generate a program that is used to compute GED. This shift from predicting GED to generating programs imparts various advantages, including end-to-end interpretability and an autonomous self-evolutionary learning mechanism without ground-truth supervision. Extensive experiments on seven datasets confirm that GRAIL not only surpasses state-of-the-art GED approximation methods in prediction quality but also achieves robust cross-domain generalization across diverse graph distributions.
title GRAIL: Graph Edit Distance and Node Alignment Using LLM-Generated Code
topic Machine Learning
url https://arxiv.org/abs/2505.02124