DBScholar

Back to papers

GENTI: GPU-powered Walk-based Subgraph Extraction for Scalable Representation Learning on Dynamic Graphs

Summary: GENTI accelerates walk-based subgraph extraction for dynamic-graph representation learning by asynchronously separating CPU neighbor sampling from GPU subgraph gathering. Specialized dynamic storage yields up to 30× extraction and 26× end-to-end speedups, scaling to 1.3B edges. (summarized by gpt-5.6-luna on Jul 24 2026)

Paper ID
13645
Venue
VLDB
Year
2024
Pagerank
5.7990641e-05
Overall Rank
6,695 | 54.07%
DOI
10.14778/3665844.3665856

Incoming Non-self Citations Over Time

Authors

BibTeX Citation

@article{yu_vldb24,
        title = {{GENTI: GPU-powered Walk-based Subgraph Extraction for Scalable Representation Learning on Dynamic Graphs}},
        author = {Yu, Zihao and Liao, Ningyi and Luo, Siqiang},
        journal = {PVLDB},
        series = {{VLDB} '24},
        volume = {17},
        number = {9},
        pages = {2269--2278},
        doi = {10.14778/3665844.3665856},
        url = {https://doi.org/10.14778/3665844.3665856},
        year = {2024}
}

Incoming Citations (Sorted by Pagerank)

Showing 5 of 5 citing papers.

Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 10 of 10 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