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)
Incoming Non-self Citations Over Time
Authors
- 1. Jure Leskovec (Stanford University)
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 |
|---|---|---|---|---|
| 6,963 | Fully Dynamic Algorithms for Graph Databases with Edge Differential Privacy | 2025 | PODS | 5.6328879e-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
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 8,839 | Machine Learning for Data Management: Problems and Solutions | 2018 | SIGMOD |
| 2 | 9,027 | Generating Flexible Workloads for Graph Databases | 2016 | VLDB |
| 3 | 11,427 | Panel on Neural Relational Data: Tabular Foundation Models, LLMs... or both? | 2025 | VLDB |
| 4 | 6,384 | Natural Language Interfaces for Databases with Deep Learning | 2023 | VLDB |
| 5 | 10,739 | Database Views as Explanations for Relational Deep Learning | 2026 | VLDB |
| 6 | 10,154 | Structure-Aware Machine Learning over Multi-Relational Databases | 2021 | SIGMOD |
| 7 | 13,781 | The Power of Summarization in Graph Mining and Learning: Smaller Data, Faster Methods, More Interpretability | 2021 | VLDB |
| 8 | 11,008 | iPDB: SQL with ML and LLM Predicates (Towards a Database Engine for AI) | 2026 | VLDB |
| 9 | 4,557 | Databases Unbound: Querying All of the World’s Bytes with AI | 2024 | VLDB |
| 10 | 9,073 | Machine Learning for Graph Data Management and Query Processing | 2025 | VLDB |