Leveraging Dynamic and Heterogeneous Workload Knowledge to Boost the Performance of Index Advisors
Summary: BALANCE handles dynamic, heterogeneous workloads by training lightweight index advisors (LIAs) on sequential similar-workload chunks, using policy-transfer to reuse policies and self-supervised contrastive embeddings for compact workload representations. Improves SWIRL by 10.03% while reducing training overhead by 35.7%. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Zijia Wang (Xiamen University)
- 2. Haoran Liu (Xiamen University)
- 3. Chen Lin (Xiamen University)
- 4. Zhifeng Bao (Royal Melbourne Institute of Technology)
- 5. Guoliang Li (Tsinghua University)
- 6. Tianqing Wang (Huawei)
BibTeX Citation
@article{wang_vldb24,
title = {{Leveraging Dynamic and Heterogeneous Workload Knowledge to Boost the Performance of Index Advisors}},
author = {Wang, Zijia and Liu, Haoran and Lin, Chen and Bao, Zhifeng and Li, Guoliang and Wang, Tianqing},
journal = {PVLDB},
series = {{VLDB} '24},
volume = {17},
number = {7},
pages = {1642--1654},
doi = {10.14778/3654621.3654631},
url = {https://doi.org/10.14778/3654621.3654631},
year = {2024}
}Incoming Citations (Sorted by Pagerank)
Showing 4 of 4 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 8,753 | A New Paradigm in Tuning Learned Indexes: A Reinforcement Learning Enhanced Approach | 2025 | SIGMOD | 5.2846898e-05 |
| 10,532 | Rainbow: Risk-aware Index Benefit Estimation Facing Out Of Distribution Workloads | 2026 | SIGMOD | 4.9793485e-05 |
| 10,681 | RIB: Robust Learning-based Index Benefit Estimation | 2026 | SIGMOD | 4.9793485e-05 |
| 10,832 | ReSequel: Robust LLM-assisted Query Rewriting and Optimization using Templatization and Sampling | 2026 | VLDB | 4.9793485e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 9 of 9 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 15 | How Good Are Query Optimizers, Really? | 2016 | VLDB | 0.00061066921 |
| 151 | An Efficient, Cost-Driven Index Selection Tool for Microsoft SQL Server | 1997 | VLDB | 0.00028672526 |
| 378 | AutoAdmin "What-if" Index Analysis Utility | 1998 | SIGMOD | 0.00019549382 |
| 460 | Query-based Workload Forecasting for Self-Driving Database Management Systems | 2018 | SIGMOD | 0.00017842695 |
| 479 | The Making of TPC-DS | 2006 | VLDB | 0.00017622471 |
| 751 | Automatic Physical Database Tuning: A Relaxation-based Approach | 2005 | SIGMOD | 0.0001425375 |
| 867 | Index Selection in a Self-Adaptive Data Base Management System | 1976 | SIGMOD | 0.00013371725 |
| 1,397 | Magic mirror in my hand, which is the best in the land? An Experimental Evaluation of Index Selection Algorithms | 2020 | VLDB | 0.00010789242 |
| 4,968 | Budget-aware Index Tuning with Reinforcement Learning | 2022 | SIGMOD | 6.3348803e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 3,697 | Learned Index: A Comprehensive Experimental Evaluation | 2023 | VLDB |
| 2 | 6,578 | Workload-Aware Indexing of Continuously Moving Objects | 2009 | VLDB |
| 3 | 2,636 | Are Updatable Learned Indexes Ready? | 2022 | VLDB |
| 4 | 848 | Benchmarking Learned Indexes | 2021 | VLDB |
| 5 | 4,968 | Budget-aware Index Tuning with Reinforcement Learning | 2022 | SIGMOD |
| 6 | 10,648 | HIRE: A Hybrid Learned Index for Robust and Efficient Performance under Mixed Workloads | 2026 | SIGMOD |
| 7 | 10,575 | High Performance or Low Memory? An Updatable Learned Index Framework for Time-Space Tradeoff | 2026 | SIGMOD |
| 8 | 4,711 | Learned Index Benefits: Machine Learning Based Index Performance Estimation | 2022 | VLDB |
| 9 | 10,489 | On Self-Designing Learned Indexes | 2026 | SIGMOD |
| 10 | 6,105 | Breaking It Down: An In-depth Study of Index Advisors | 2024 | VLDB |