LakeHelm: Zero-Shot Lakehouse Advisor for Joint Engine-Format Selection and Configuration
Summary: LakeHelm is a zero-shot advisor that jointly selects lakehouse execution engines, table formats, and configurations. Its dual-gate MoE models cross-subsystem interactions and, using synthetic workloads, generalizes to unseen queries without costly online tuning. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Zhongwei Xu (University of Michigan)
- 2. Siyuan Dong (University of Michigan)
- 3. Haotian Gong (University of Michigan)
- 4. Donna Pham (University of Michigan)
- 5. Lin Ma (University of Michigan)
BibTeX Citation
@article{xu_vldb26,
title = {{LakeHelm: Zero-Shot Lakehouse Advisor for Joint Engine-Format Selection and Configuration}},
author = {Xu, Zhongwei and Dong, Siyuan and Gong, Haotian and Pham, Donna and Ma, Lin},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {8},
pages = {1768--1781},
doi = {10.14778/3811243.3811250},
url = {https://doi.org/10.14778/3811243.3811250},
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