Rethinking Flexible Graph Similarity Computation: One-step Alignment with Global Guidance
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911466233266176 |
|---|---|
| author | Liu, Zhouyang Liu, Ning Chen, Yixin He, Jiezhong Ma, Shuai Li, Dongsheng |
| author_facet | Liu, Zhouyang Liu, Ning Chen, Yixin He, Jiezhong Ma, Shuai Li, Dongsheng |
| contents | Graph Edit Distance (GED) is a widely used measure of graph similarity, valued for its flexibility in encoding domain knowledge through operation costs. However, existing learning-based approximation methods follow a modeling paradigm that decouples local candidate match selection from both operation costs and global dependencies between matches. This decoupling undermines their ability to capture the intrinsic flexibility of GED and often forces them to rely on costly iterative refinement to obtain accurate alignments. In this work, we revisit the formulation of GED and revise the prevailing paradigm, and propose Graph Edit Network (GEN), an implementation of the revised formulation that tightly integrates cost-aware expense estimation with globally guided one-step alignment. Specifically, GEN incorporates operation costs into node matching expenses estimation, ensuring match decisions respect the specified cost setting. Furthermore, GEN models match dependencies within and across graphs, capturing each match's impact on the overall alignment. These designs enable accurate GED approximation without iterative refinement. Extensive experiments on real-world and synthetic benchmarks demonstrate that GEN achieves up to a 37.8% reduction in GED predictive errors, while increasing inference throughput by up to 414x. These results highlight GEN's practical efficiency and the effectiveness of the revision. Beyond this implementation, our revision provides a principled framework for advancing learning-based GED approximation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_06533 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Rethinking Flexible Graph Similarity Computation: One-step Alignment with Global Guidance Liu, Zhouyang Liu, Ning Chen, Yixin He, Jiezhong Ma, Shuai Li, Dongsheng Machine Learning Artificial Intelligence Data Structures and Algorithms Graph Edit Distance (GED) is a widely used measure of graph similarity, valued for its flexibility in encoding domain knowledge through operation costs. However, existing learning-based approximation methods follow a modeling paradigm that decouples local candidate match selection from both operation costs and global dependencies between matches. This decoupling undermines their ability to capture the intrinsic flexibility of GED and often forces them to rely on costly iterative refinement to obtain accurate alignments. In this work, we revisit the formulation of GED and revise the prevailing paradigm, and propose Graph Edit Network (GEN), an implementation of the revised formulation that tightly integrates cost-aware expense estimation with globally guided one-step alignment. Specifically, GEN incorporates operation costs into node matching expenses estimation, ensuring match decisions respect the specified cost setting. Furthermore, GEN models match dependencies within and across graphs, capturing each match's impact on the overall alignment. These designs enable accurate GED approximation without iterative refinement. Extensive experiments on real-world and synthetic benchmarks demonstrate that GEN achieves up to a 37.8% reduction in GED predictive errors, while increasing inference throughput by up to 414x. These results highlight GEN's practical efficiency and the effectiveness of the revision. Beyond this implementation, our revision provides a principled framework for advancing learning-based GED approximation. |
| title | Rethinking Flexible Graph Similarity Computation: One-step Alignment with Global Guidance |
| topic | Machine Learning Artificial Intelligence Data Structures and Algorithms |
| url | https://arxiv.org/abs/2504.06533 |