ConRAD: Conformal Risk-Aware Neural Databases
Summary: ConRAD embeds conformal risk control in neural graph databases, deriving per-operator thresholds with finite-sample, distribution-free recall guarantees. Quantile scalarization and a conformal gate improve precision while bypassing unnecessary neural inference. (summarized by gpt-5.6-luna on Aug 28 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Sonia Horchidan (KTH Royal Institute of Technology)
- 2. Fabian Zeiher (KTH Royal Institute of Technology)
- 3. Xiangyu Shi (KTH Royal Institute of Technology)
- 4. Vasiliki Kalavri (Boston University)
- 5. Henrik Boström (KTH Royal Institute of Technology)
- 6. Ioannis Kontoyiannis (University of Cambridge)
- 7. Paris Carbone (KTH Royal Institute of Technology)
BibTeX Citation
@article{horchidan_vldb26,
title = {{ConRAD: Conformal Risk-Aware Neural Databases}},
author = {Horchidan, Sonia and Zeiher, Fabian and Shi, Xiangyu and Kalavri, Vasiliki and Boström, Henrik and Kontoyiannis, Ioannis and Carbone, Paris},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {11},
pages = {3511--3524},
doi = {10.14778/3836663.3836705},
url = {https://doi.org/10.14778/3836663.3836705},
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 19 of 19 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
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 10,213 | A Universal Question-Answering Platform for Knowledge Graphs | 2023 | SIGMOD |
| 2 | 11,238 | PlanRGCN: Predicting SPARQL Query Performance | 2025 | VLDB |
| 3 | 10,294 | Data-Agnostic Cardinality Learning from Imperfect Workloads | 2025 | VLDB |
| 4 | 7,363 | PerfGuard: Deploying ML-for-Systems without Performance Regressions, Almost! | 2021 | VLDB |
| 5 | 512 | NeuroCard: One Cardinality Estimator for All Tables | 2021 | VLDB |
| 6 | 10,798 | NeurIDA: Dynamic Modeling for Effective In-Database Analytics | 2026 | VLDB |
| 7 | 8,679 | Relational Deep Dive: Error-Aware Queries Over Unstructured Data | 2026 | VLDB |
| 8 | 6,469 | Cardinality Estimation over Knowledge Graphs with Embeddings and Graph Neural Networks | 2024 | SIGMOD |
| 9 | 10,868 | CONDA: A Connectivity-Aware Dynamic Index for Approximate Nearest Neighbor Search over Evolving Data | 2026 | VLDB |
| 10 | 10,834 | ConANN: Conformal Approximate Nearest Neighbor Search | 2026 | VLDB |