DBScholar

Back to papers

Efficient Unsupervised Community Search with Pre-trained Graph Transformer

Summary: TransZero: pre-trained graph Transformer for zero-label community search, using personalization and link self-supervised losses to learn node embeddings. Query uses embedding similarity plus an expected-gain criterion for threshold-free extraction; efficient unsupervised algorithms yield superior performance on 10 datasets. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID
13641
Venue
VLDB
Year
2024
Pagerank
5.3624668e-05
Overall Rank
8,821 | 39.49%
DOI
10.14778/3665844.3665853

Incoming Non-self Citations Over Time

Authors

BibTeX Citation

@article{wang_vldb24,
        title = {{Efficient Unsupervised Community Search with Pre-trained Graph Transformer}},
        author = {Wang, Jianwei and Wang, Kai and Lin, Xuemin and Zhang, Wenjie and Zhang, Ying},
        journal = {PVLDB},
        series = {{VLDB} '24},
        volume = {17},
        number = {9},
        pages = {2227--2240},
        doi = {10.14778/3665844.3665853},
        url = {https://doi.org/10.14778/3665844.3665853},
        year = {2024}
}

Incoming Citations (Sorted by Pagerank)

Showing 8 of 8 citing papers.

Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 15 of 15 cited papers.

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

Previous Page 1 / 1 Next

Semantically Similar Papers