DBScholar

Back to papers

Efficient Graph Embedding Generation and Update for Large-Scale Temporal Graph

Summary: Introduce Temporal-based Bipartite Graph and temporal preferential-attachment similarity (TPASim) to encode concurrent node activity for temporal graph embeddings. LTGE factorizes a 2m-sparse temporal matrix provably equivalent to dense TPASim (reducing complexity by n^2/m) and LTGEInc uses an incremental SVD with guarantees to update embeddings, scaling to 17M nodes/1.3B edges and outperforming prior temporal methods. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID
14436
Venue
VLDB
Year
2025
Pagerank
5.093636e-05
Overall Rank
11,108 | 23.79%
DOI
10.14778/3717755.3717756

Incoming Non-self Citations Over Time

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

Authors

BibTeX Citation

@article{song_vldb25,
        title = {{Efficient Graph Embedding Generation and Update for Large-Scale Temporal Graph}},
        author = {Song, Yifan and Chen, Xiaolong and Lin, Wenqing and Li, Jia and Zhang, Chen and Zhou, Yan and Chen, Lei and Tang, Jing},
        journal = {PVLDB},
        series = {{VLDB} '25},
        volume = {18},
        number = {4},
        pages = {929--942},
        doi = {10.14778/3717755.3717756},
        url = {https://doi.org/10.14778/3717755.3717756},
        year = {2025}
}

Incoming Citations (Sorted by Pagerank)

Showing 1 of 1 citing papers.

Rank Citing Paper Year Venue Pagerank
10,382 LLM-Powered Interactive Graph Search: A Scalable and Practical Approach 2026 SIGMOD 5.093636e-05
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