DBScholar

Back to papers

Databases as Graphs: Predictive Queries for Declarative Machine Learning

Summary: Kumo provides a SQL-like Predictive Query language that compiles relational schemas into a heterogeneous hypergraph abstraction. Distributed GNNs trained on that graph auto-learn cross-table embeddings for in‑DB predictions, eliminating manual feature engineering and enabling scalable production ML. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID
1936
Venue
PODS
Year
2023
Pagerank
5.3817447e-05
Overall Rank
8,702 | 40.30%
DOI
10.1145/3584372.3589939

Incoming Non-self Citations Over Time

Authors

BibTeX Citation

@inproceedings{leskovec_pods23,
        address = {New York, NY, USA},
        series = {{PODS} '23},
        title = {{Databases as Graphs: Predictive Queries for Declarative Machine Learning}},
        url = {https://dl.acm.org/doi/10.1145/3584372.3589939},
        doi = {10.1145/3584372.3589939},
        booktitle = {Proceedings of the {ACM} {SIGMOD} Symposium on {Principles} of {Database} {Systems}},
        publisher = {Association for Computing Machinery},
        author = {Leskovec, Jure},
        year = {2023}
}

Incoming Citations (Sorted by Pagerank)

Showing 1 of 1 citing papers.

Rank Citing Paper Year Venue Pagerank
6,826 Fully Dynamic Algorithms for Graph Databases with Edge Differential Privacy 2025 PODS 5.7621757e-05
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