Title

layout: true
<slide-template title="QuCUN Status Seminar, 18th November 2024" subtitle="QC4DB: Accelerating Relational Database Management Systems via Quantum Computing"></slide-template>

---

class: title-slide, center, middle

<title-slide titletype="18th November 2024" title="QuCUN Status Seminar" modulenumber="Munich" subtitle="QC4DB: Accelerating Relational Database Management Systems via Quantum Computing"></title-slide>

---
<h1 style="line-height:32px">.darkblue[QC4DB: .small-font36[Accelerating Relational Database Management Systems via Quantum Computing]]</h1>

.more-more-condensed[
<table class="result tablesmallpadding small-font">
<tbody>
<tr>
<th>Name:</th>
<td colspan="2">.darkblue[QC4DB]: Accelerating Relational Database Management Systems via Quantum Computing</td>
</tr>
<tr>
<th>Proj. Web:</th>
<td colspan="2"><a href="https://www.quantentechnologien.de/forschung/foerderung/anwendungsnetzwerk-fuer-das-quantencomputing/qc4db.html" target="_blank">Project Website@Quantentechnologien</a></td>
</tr>
<tr>
<th>Funded by:</th>
<td colspan="2">BMBF, Fördermaßnahme .darkblue[Anwendungsnetzwerk] für das Quantencomputing</td>
</tr>
<tr>
<th>Duration:</th>
<td colspan="2">3 years, 1.1.2022 - 30.6.2025 (extended)</td>
</tr>
<tr>
<th>Volume:</th>
<td colspan="2">1.8M Euros</td>
</tr>
<tr>
<th>Topics:</th>
<td colspan="2">.darkblue[Optimizing] an open source relational .darkblue[database] management system <ul class="no-margin"><li>.darkblue[Queries]</li><li>.darkblue[Transaction Schedules]</li></ul></td>
</tr>
<tr>
<th>Partners:</th>
<td style="width:48%"><img src="../../img/keynotes/qc/UzL.jpg" align="bottom" width="300px"></img> (Coord.)</td>
<td><img src="../../img/keynotes/qc/QB.jpg" align="top" width="200px"></img></td>
</tr>
<tr>
<th>Expertises:</th>
<td>Hardware-Acceleration of Databases</td>
<td>Room Temperature Diamond Quantum Accelerators/qbOS</td>
</tr>
<tr>
<th>Website:</th>
<td><a href="https://www.ifis.uni-luebeck.de/~groppe/" target="_blank">https://www.ifis.uni-luebeck.de/~groppe/</a></td>
<td><a href="https://quantumbrilliance.com/" target="_blank">https://quantumbrilliance.com/</a></td>
</tr>
</tbody>
</table>
]

---
# .darkblue[Timeline of Activities]

<div class="textcenter">
<img src="../../img/qc4db/Timeline2022-2024.svg" align="top" width="100%"></img>
</div>
.more-more-condensed.darkblue[
<table>
<tbody>
<tr><td>
<ul><li>11 Papers</li>
<li>5 Workshops</li>
<li>2 Tutorials</li>
<li>5 Posters</li>
</ul>
</td>
<td>
<ul><li>2 Panels</li>
<li>2 Keynotes</li>
<li>5 Invited Talks</li>
<li>1 Special Issue in Journals</li>
</ul>
</td>
</tr>
</tbody>
</table>
]

---
# .darkblue[Number of Citations] .darkgray[(18.11.2024)]

.reference[according to Google Scholar]

.more-more-condensed[
<table class="result tablesmallpadding">
<tbody>
<tr>
<th>#Citations</th><th>Publication</th>
</tr>
<tr>
<td class="small-font">28</td><td class="smaller-font">Quantum machine learning: Foundation, new techniques, and opportunities for database research</td>
</tr>
<tr>
<td class="small-font">24</td><td class="smaller-font">Constructing optimal bushy join trees by solving qubo problems on quantum hardware and simulators</td>
</tr>
<tr>
<td class="small-font">21</td><td class="smaller-font">Opportunities for quantum acceleration of databases: optimization of queries and transaction schedules</td>
</tr>
<tr>
<td class="small-font">12</td><td class="smaller-font">Quantum machine learning for join order optimization using variational quantum circuits</td>
</tr>
<tr>
<td class="small-font">15</td><td class="smaller-font">Index Tuning with Machine Learning on Quantum Computers for Large-Scale Database Applications</td>
</tr>
<tr>
<td class="small-font">6</td><td class="smaller-font">Quantum data management and quantum machine learning for data management: State-of-the-art and open challenges</td>
</tr>
<tr>
<td class="small-font">1</td><td class="smaller-font">Hype or Heuristic? Quantum Reinforcement Learning for Join Order Optimisation</td>
</tr>
<tr>
<td class="small-font">1</td><td class="smaller-font">Quantum Join Ordering by Splitting the Search Space of QUBO Problems</td>
</tr>
<tr>
<td class="small-font">0</td><td class="smaller-font">ReJOOSp: Reinforcement Learning for Join Order Optimization in SPARQL</td>
</tr>
<tr>
<td class="small-font">2</td><td class="smaller-font">Supervised Learning on Relational Databases with Quantum Graph Neural Networks</td>
</tr>
<tr>
<td class="small-font">0</td><td class="smaller-font">QCE'24 Tutorial: Quantum Annealing - Emerging Exploration for Database Optimization</td>
</tr>
<tr>
<td>$\Sigma$: 110</td><td class="small-font">in total</td>
</tr>
</tbody>
</table>
]

---
# Importance of .darkblue[Collaboration]

.more-more-condensed[
- .darkblue[Collaboration Workshop] <span class="darkgray">in Nov. 2022</span>, Participants: Groups of<ol><li><span class="darkblue">Prof. Jiaheng Lu (University of Helsinki, Finland)</span></li><li><span class="darkblue">Prof. Wolfgang Mauerer (OTH Regensburg, Germany)</span></li><li><span class="darkblue">Prof. Le Gruenwald (University of Oklahoma, USA)</span></li><li><span class="darkblue">Dr. Florian Preis (Quantum Brilliance, Germany)</span><li><span class="darkblue">Prof. S. Groppe (University of Lübeck, Germany)</span></li><li>...</li></ol>
- .darkblue[Collaboration Activities] <span class="darkgray">("result" of the collaboration workshop)</span>
  - 4 <span class="darkblue">Workshops</span>: <span class="darkblue">QDSM@VLDB '23</span>/<span class="darkblue">'24</span> <span class="darkgray">(Org.: 1., 2., 3., 5.)</span>, <span class="darkblue">BiDEDE@SIGMOD'23</span> <span class="darkgray">(Org.: 3., 5.)</span>, <span class="darkblue">QData@SIGMOD'24</span> <span class="darkgray">(Org.: 4., Steering Committee: 2., 5.)</span>
  - 2 <span class="darkblue">Tutorials</span>: <span class="darkblue">SIGMOD'23</span> <span class="darkgray">(1., 2., 5.)</span>, <span class="darkblue">IEEE QCE'24</span> <span class="darkgray">(1., 2., 5.)</span>
  - 6 <span class="darkblue">Papers</span>: <span class="darkblue">IEEE QCE'24</span> <span class="darkgray">(2., 5.)</span>, <span class="darkblue">SIGMOD'23</span> <span class="darkgray">(1., 2., 5.)</span>, <span class="darkblue">QDSM@VLDB'23</span> <span class="darkgray">(3., 5.)</span>, <span class="darkblue">BiDEDE@SIGMOD'23</span> <span class="darkgray">(3., 5.)</span>, <span class="darkblue">VLDB'23</span> <span class="darkgray">(3., 4., 5.)</span>, <span class="darkblue">EAI ICISML'22</span> <span class="darkgray">(3., 5.)</span>
- <span class="darkblue">Other Collaborations:</span>
  - 2 <span class="darkblue">Papers: QDSM@VLDB'24</span> <span class="darkgray">(5., Martin Vogrin,  University of Maribor, Slovenia)</span>, <span class="darkblue">BDCC 8(7)</span> <span class="darkgray">(5., Shridevi Krishnakumar, VIT Chennai, India)</span>
]

---
# Using .darkblue[Hardware Accelerator] for optimizing Queries / Transaction Schedules
.reference[<a href="https://doi.org/10.1145/3410566.3410593" target="_blank">[BG20a]</a> <a href="http://nbn-resolving.de/urn:nbn:de:101:1-2020112218332015343957" target="_blank">[BG20b]</a>  <a href="https://doi.org/10.1145/3472163.3472164" target="_blank">[GG21]</a>]

---
# .darkblue[Planned Contributions]

---
# .darkblue[Transaction Scheduling]

.reference[<a href="https://doi.org/10.14778/3598581.3598603" target="_blank">VLDB'23</a>]

.more-more-condensed.no-margin[
- Design choice: .darkblue[Fast quantum] exact methods .darkblue[and] good .darkblue[heuristics] for scalable optimization times
]
<table class="no-margin">
<tbody>
<tr>
<td>
.more-more-condensed.no-margin[
- .darkblue[Classical]
  - .darkblue[Dynamic Programming | Random Search | Simulated Annealing .darkgray[(SA)] | Genetic Algorithm .darkgray[(GA)] | Ant Colony Optimization .darkgray[(ACO)]]
- .darkblue[Quantum]
  - .darkblue[Maximum Independent Set | Quantum Evolutionary Algorithms] .darkgray[(QEA) (several variants: Binary | (Cultural (QCEA)) Multi-State)] .darkblue[| QUBO | Grover]
]
</td>
<td style="width:60%;vertical-align:top">
<div class="textcenter">
<img src="../../img/qc4db/TS_QEA.png" align="top" class="fullwidth"></img>
</div>
</td>
</tr>
</tbody>
</table>

---
# .darkblue[QML for Join Ordering]

.reference[Single-Step: <a href="https://doi.org/10.1145/3579142.3594299" target="_blank">BiDEDE@SIGMOD'23</a> <a href="https://doi.org/10.14778/3598581.3598603" target="_blank">VLDB'23</a> <a href="https://doi.org/10.1145/3555041.3589404" target="_blank">SIGMOD'23</a> Multi-Step (cooperation with OTH Regensburg): <a href="https://doi.org/10.48550/arXiv.2405.07770" target="_blank">QCE'24</a>]

.more-more-condensed.no-margin[
- Design choice: .darkblue[Predict best join order based on] real .darkblue[execution times] .darkgray[in contrast to estimated costs (EC)]
  - can .darkblue[beat exact methods] like dynamic programming (DP) based on EC
- Single-Step: .darkblue[Real-world queries] .darkgray[(ErgastF1 Benchmark/PostgreSQL)]
  - .darkblue[join orders with faster execution than DP (2.8%) and GEQO (11.2%)]
  - close to classical ML like RTOS (6%) / best join orders (16.8%)
]
<table>
<tbody>
<tr>
<td style="width:50%">
<div class="textcenter">
<img src="../../img/keynotes/bv/SingleVsMultiStepJoinOrdering.svg" align="top" class="fullwidth"></img>
</div>
</td>
<td style="width:50%">
<div class="textcenter">
<img src="../../img/keynotes/bv/QMLJOO.svg" align="top" class="fullwidth"></img>
</div>
</td>
</tr>
</tbody>
</table>

---
# .darkblue[Join Ordering as QUBO Problem]

.reference[<a href="https://doi.org/10.1145/3579142.3594298" target="_blank">BiDEDE@SIGMOD'23</a> Partitioning the Search Space: <a href="https://doi.org/10.1007/s13222-024-00468-3" target="_blank">Datenbank-Spektrum 24(1): 21-32, 2024</a>]

.more-more-condensed.no-margin[
- Design choice: .darkblue[Direct Join Costs] .darkgray[in contrast to calculated costs]
  - .darkblue[Estimated costs for .bold[each] join]  .darkblue[$\Rightarrow$ better join order]
  - .darkblue[Runtime] complexity .darkblue[$O(2^m-m)$ with $m$ relations] to join .darkblue[optimal] for join ordering based on direct costs
     - <span class="darkblue">Classical</span> runtime: <span class="darkblue">$O(3^m-2^{m+1})$</span> using dynamic programming
- .darkblue[Real-world queries] .darkgray[(ErgastF1 Benchmark/PostgreSQL)]
]
<table>
<tbody>
<tr>
<td style="width:55%">
<div class="textcenter">
<img src="../../img/keynotes/bv/QAResults.svg" align="top" class="fullwidth"></img>
</div>
</td>
<td style="width:45%">
<div class="textcenter">
<img src="../../img/keynotes/bv/QAResultsSelectivity.svg" align="top" class="fullwidth"></img>
</div>
</td>
</tr>
</tbody>
</table>

---
# .darkblue[QML for Cardinality Estimation]

.reference[MSCN (multi-set convolutional network): <a href="http://cidrdb.org/cidr2019/papers/p101-kipf-cidr19.pdf" target="_blank">Kipf et al. Learned cardinalities: Estimating correlated joins with deep learning, CIDR 2019</a>]

.more-more-condensed.no-margin[
- Design choice: .darkblue[Predict correction factor] of a Cardinality Estimator
  - .darkblue[Cardinality Predictor:PostgreSQL|MSCN|Hybrid Quantum Classical Network]
  - .darkblue[Cardinality Correction: Hybrid Quantum Classical Network]
- Queries of JOB-light Benchmark
]

---
# .darkblue[Transaction Scheduling Optimisation Server]

<img src="../../img/qc4db/TSOS.svg" align="top" class="fullwidth"></img>
.more-more-condensed[
- .darkblue[Demonstrator]
  - .darkblue[fully quantum .bold[versus] fully classical]
]

---
# .darkblue[Demonstrator]

.reference[Link to demo: <a href="https://qc4db.quantum-brilliance.com/" target="_blank">https://qc4db.quantum-brilliance.com/</a>]

.more-more-condensed[
- .darkblue[is publicly available] at the .darkblue[Quantum Brilliance web-page]...<br/>
<video class="fullwidth" controls>
  <source src="../../img/qc4db/quantum_demo.mp4" type="video/mp4">
Your browser does not support the video tag.
</video>
]

---
# .darkblue[QC4DB Team]

.more-more-condensed[
<table class="result tablesmallpadding">
<tbody>
<tr>
<th style="width:20%">Partner:</th><th style="width:40%">University of Lübeck</th><th style="width:40%">Quantum Brilliance GmbH</th>
</tr>
<tr>
<th>Project Leaders:</th><td>Prof. Dr. rer. nat. habil.<br/>.darkblue[Sven Groppe] (Coordinator)</td><td>Dr. .darkblue[Florian Preis]<br/>Dr. .darkblue[Stefan Prestel]<br/>Dr. .darkblue[Farida Shagieva]</td>
</tr>
<tr>
<th>Project Employees:</th><td>.darkblue[Tobias Winker<br/>Umut Çalıkyılmaz<br/>Nitin Nayak<br/>Benjamin Warnke]</td><td>.darkblue[Daanish Arya]<br/>Dr. .darkblue[John Helm]<br/>Dr. .darkblue[Johannes Kuhlmann]<br/>Dr. .darkblue[Jeremy Rodriguez]<br/></td>
</tr>
</tbody>
</table>
]