DBScholar

Back to papers

TaGSim: Type-aware Graph Similarity Learning and Computation

Summary: TaGSim enables fine-grained GED approximation by separately modeling the transformative effects of node/edge insertions, deletions, and relabelings. Type-aware embeddings and neural estimators deliver accurate, efficient similarity computation, outperforming prior methods on five real-world datasets. (summarized by gpt-5.6-luna on Jul 24 2026)

Paper ID
13001
Venue
VLDB
Year
2022
Pagerank
7.00884e-05
Overall Rank
3,933 | 73.02%
DOI
10.14778/3489496.3489513

Incoming Non-self Citations Over Time

Authors

BibTeX Citation

@article{bai_vldb22,
        title = {{TaGSim: Type-aware Graph Similarity Learning and Computation}},
        author = {Bai, Jiyang and Zhao, Peixiang},
        journal = {PVLDB},
        series = {{VLDB} '22},
        volume = {15},
        number = {2},
        pages = {335--347},
        doi = {10.14778/3489496.3489513},
        url = {https://doi.org/10.14778/3489496.3489513},
        year = {2022}
}

Incoming Citations (Sorted by Pagerank)

Showing 5 of 5 citing papers.

Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 1 of 1 cited papers.

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

Rank Cited Paper Year Venue Pagerank
1,115 Comparing Stars: On Approximating Graph Edit Distance 2009 VLDB 0.00012117375
Previous Page 1 / 1 Next

Semantically Similar Papers