DBScholar

Back to papers

Breaking Structural Isolation: Scalable Graph Clustering via Community-Aware Sampling and Structural Entropy

Summary: SCISE addresses structural isolation in mini-batch graph contrastive clustering via constrained structural entropy and community-aware sampling. Its StructCL module preserves higher-order topology by refining intra-batch edge weights, yielding stronger large-scale clustering. (summarized by gpt-5.6-luna on Aug 28 2026)

Paper ID
heaa1f4f5189a49f1
Venue
VLDB
Year
2026
Pagerank
-
Overall Rank
13,585 | 8.67%
DOI
10.14778/3836663.3836704

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

BibTeX Citation

@article{zhang_vldb26,
        title = {{Breaking Structural Isolation: Scalable Graph Clustering via Community-Aware Sampling and Structural Entropy}},
        author = {Zhang, Jingyun and Peng, Hao and Li, Jianxin and Li, Angsheng and Yu, Philip S.},
        journal = {PVLDB},
        series = {{VLDB} '26},
        volume = {19},
        number = {11},
        pages = {3497--3510},
        doi = {10.14778/3836663.3836704},
        url = {https://doi.org/10.14778/3836663.3836704},
        year = {2026}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank Citing Paper Year Venue Pagerank
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 0 of 0 cited papers.

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

Rank Cited Paper Year Venue Pagerank
Previous Page 1 / 1 Next

Semantically Similar Papers