Computing Graph Edit Distance via Neural Graph Matching

Summary: GEDGNN jointly predicts graph edit distance and a node-matching matrix, then uses k-best matching to construct interpretable edit paths. It substantially improves GED accuracy over GNN regressors and Noah search across real and synthetic graphs. (summarized by gpt-5.6-luna on Jul 24 2026)

Paper ID: 13227
Venue: VLDB
Year: 2023
Pagerank: 7.4260662e-05
Overall Rank: 3,423 | 76.52%
DOI: 10.14778/3594512.3594514

Incoming Non-self Citations Over Time

Authors

1. Chengzhi Piao (Chinese University of Hong Kong)
2. Tingyang Xu (Tencent)
3. Xiangguo Sun (Chinese University of Hong Kong)
4. Yu Rong (Tencent)
5. Kangfei Zhao (Tencent)
6. Hong Cheng (Chinese University of Hong Kong)

BibTeX Citation

@article{piao_vldb23,
        title = {{Computing Graph Edit Distance via Neural Graph Matching}},
        author = {Piao, Chengzhi and Xu, Tingyang and Sun, Xiangguo and Rong, Yu and Zhao, Kangfei and Cheng, Hong},
        journal = {PVLDB},
        series = {{VLDB} '23},
        volume = {16},
        number = {8},
        pages = {1817--1829},
        doi = {10.14778/3594512.3594514},
        url = {https://doi.org/10.14778/3594512.3594514},
        year = {2023}
}

Incoming Citations (Sorted by Pagerank)

Showing 9 of 9 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
5,758	Fast Maximum Common Subgraph Search: A Redundancy-Reduced Backtracking Approach	2025	SIGMOD	6.0972035e-05
8,126	Computing Approximate Graph Edit Distance via Optimal Transport	2025	SIGMOD	5.4827332e-05
8,504	Enabling Window-Based Monotonic Graph Analytics with Reusable Transitional Results for Pattern-Consistent Queries	2024	VLDB	5.4132367e-05
10,521	Efficient GNN Training on Giant Graphs with Collective Batching and Scheduling	2026	VLDB	5.093636e-05
10,524	A Semantics-aware Approach for Graph Edit Distance Estimation over Knowledge Graphs	2026	VLDB	5.093636e-05
10,600	Chipmink: Efficient Delta Identification for Massive Object Graphs	2026	VLDB	5.093636e-05
10,764	Graph Edit Distance Estimation: A New Heuristic and A Holistic Evaluation of Learning-based Methods	2025	SIGMOD	5.093636e-05
10,939	Fused Gromov-Wasserstein Alignment for Graph Edit Distance Computation and Beyond	2025	VLDB	5.093636e-05
11,067	Machine Learning for Graph Data Management and Query Processing	2025	VLDB	5.093636e-05

Outgoing Citations (Sorted by Pagerank)

Showing 4 of 4 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
2,731	Neural Subgraph Counting with Wasserstein Estimator	2022	SIGMOD	8.1959181e-05
3,283	A Learned Sketch for Subgraph Counting	2021	SIGMOD	7.56675e-05
3,933	TaGSim: Type-aware Graph Similarity Learning and Computation	2022	VLDB	7.00884e-05
4,590	Entity Resolution with Hierarchical Graph Attention Networks	2022	SIGMOD	6.6150054e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	1,115	Comparing Stars: On Approximating Graph Edit Distance	2009	VLDB
2	6,149	Efficient Exact Subgraph Matching via GNN-based Path Dominance Embedding	2024	VLDB
3	11,756	Approximate Pattern Matching in Massive Graphs with Precision and Recall Guarantees	2020	SIGMOD
4	7,152	Boosting Graph Similarity Search through Pre-Computation	2021	SIGMOD
5	12,021	NED: An Inter-Graph Node Metric Based On Edit Distance	2017	VLDB
6	10,939	Fused Gromov-Wasserstein Alignment for Graph Edit Distance Computation and Beyond	2025	VLDB
7	10,524	A Semantics-aware Approach for Graph Edit Distance Estimation over Knowledge Graphs	2026	VLDB
8	3,933	TaGSim: Type-aware Graph Similarity Learning and Computation	2022	VLDB
9	8,126	Computing Approximate Graph Edit Distance via Optimal Transport	2025	SIGMOD
10	10,764	Graph Edit Distance Estimation: A New Heuristic and A Holistic Evaluation of Learning-based Methods	2025	SIGMOD