Mourad Khayati

Senior Researcher

Room	C433
Address	Bd de Pérolles 90 1700 Fribourg Switzerland
E-Mail	mkhayati [AT] exascale.info
Phone	+41 26 300 8460
Fax	+41 26 300 9726

News

Brief Bio

Mourad Khayati is a Senior researcher at the Department of Computer Science of the University of Fribourg, Switzerland. He obtained his PhD from the University of Zurich, Switzerland, under the supervision of Prof. Michael Böhlen. His research interests include Time Series analytics, data cleaning and recovery of missing values. His time series benchmark won the VLDB 2020 Most Reproducible Paper Award.

Open Source Software

ImputeBench: Time Series Imputation Benchmark (paper_vldb20, code)
RecovDB: Time Series Repair inside MonetDB (paper_icde19, code, GUI)
CDRec: Recovery of Missing Blocks in Time Series using CD (paper_icde14, code, GUI)

Teaching & Projects

Teaching:
- Fall 2020: Data Science Seminar
- Spring 2020: Social Media Analytics (No course for Spring 2021)
Projects:
- ProvDS (D-A-CH project): Main lead, 1.06.2018-31.05.2021
- FashionBrain (H2020 European project), Technical lead, 1.1.2017-31.12.2019

Student Supervision

PhD

I co-supervise the following PhD students: Artem Lutov (finished), Ines Arous (Ongoing) and Abdelouahab Khelifati (Ongoing).

MSc/BSc

I supervise(d) the following Master and Bachelor students:

Ongoing theses:
- Benchmark of Time Series Prediction Techniques [pdf].
- Comparison of Synthetic Time Series Data Generation Techniques [pdf].
- A Configuration-Free Repair of Time Series [pdf].
Completed theses:
- Louis Müller, MSc 2021: Multiclass Classification of Open-ended Answers.
- Gabriela-Carmen Voroneanu, MSc 2021: Benchmark of Time Series Management Systems using Analytical Queries.
- Adrian Hänni, MSc 2020: Correlation-based Anomaly Detection in Time Series.
- Mili Biswas, MSc 2019: Incremental Enrichment of Taxonomies using Transfer Learning.
- Ahana Malik, MSc 2018: Trend Prediction on Fashion Data.
- Leutrim Kaleci, MSc 2017: Modeling the Evolution of Fashion Trends using Matrix Factorization Techniques.
- Oliver Stapleton, MSc 2017: Real-Time Centroid Decomposition of Streams of Time Series.
- Zakhar Tymchenko, BSc 2017: Empirical Comparison of Incremental Matrix Decomposition Techniques.
- Laura Rettig , MSc 2016: Online Anomaly Detection over Big Data Streams, Best Thesis Award.
- Qian Liu , MSc 2016: Implemetation of Centroid Decomposition Algorithm on Big Data Platforms - a Comparison Between Spark and Flink.
- Eszter Börzsönyi, MSc 2013: Evaluating the Optimality of Centroid Decomposition [uzh].
- Jonathan Nagel, MSc 2013: Decomposition of Time Series Subsequences [uzh].
- Michał Kołtonik, MSc 2010: LDBE Project [uzh].

Selected Publications (DBLP)

Mourad Khayati, Ines Arous, Zakhar Tymchenko, and Philippe Cudré-Mauroux. “ORBITS: Online Recovery of Missing Blocks in Multiple Time Series Streams.” In Proceedings of the VLDB Endowment, Vol. 14, 2021. Bibtex PDF Code
ORBITS: Online Recovery of Missing Blocks in Multiple Time Series Streams

Mourad Khayati, Ines Arous, Zakhar Tymchenko, and Philippe Cudré-Mauroux. “ORBITS: Online Recovery of Missing Blocks in Multiple Time Series Streams.” In Proceedings of the VLDB Endowment, Vol. 14, 2021.
```
@inproceedings{khayati2021vldb,
  author = {Khayati, Mourad and Arous, Ines and Tymchenko, Zakhar and Cudr{\'{e}}{-}Mauroux, Philippe},
  title = {ORBITS: Online Recovery of Missing Blocks in Multiple Time Series Streams},
  booktitle = {Proceedings of the VLDB Endowment},
  volume = {14},
  number = {3},
  year = {2021},
  code = {https://github.com/eXascaleInfolab/orbits},
  url = {http://www.vldb.org/pvldb/vol14/p294-khayati.pdf}
}
```
×
Ines Arous, Jie Yang, Mourad Khayati, and Philippe Cudré-Mauroux. “Peer Grading the Peer Reviews: A Dual-Role Approach for Lightening the Scholarly Paper Review Process.” In Proceedings of the Web Conference (WWW 2021). Ljubljana, Slovenia, 2021. Bibtex PDF Code
Peer Grading the Peer Reviews: A Dual-Role Approach for Lightening the Scholarly Paper Review Process

Ines Arous, Jie Yang, Mourad Khayati, and Philippe Cudré-Mauroux. “Peer Grading the Peer Reviews: A Dual-Role Approach for Lightening the Scholarly Paper Review Process.” In Proceedings of the Web Conference (WWW 2021). Ljubljana, Slovenia, 2021.
```
@inproceedings{arous2021www,
  title = {Peer Grading the Peer Reviews: A Dual-Role Approach for Lightening the Scholarly Paper Review Process},
  author = {Arous, Ines and Yang, Jie and Khayati, Mourad and Cudr{\'e}-Mauroux, Philippe},
  booktitle = {Proceedings of the Web Conference (WWW 2021)},
  year = {2021},
  address = {Ljubljana, Slovenia},
  url = {https://exascale.info/assets/pdf/arous2021www.pdf},
  code = {https://github.com/eXascaleInfolab/pgpr}
}
```
×
Abdelouahab Khelifati, Mourad Khayati, Philippe Cudré-Mauroux, Adrian Hänni, Qian Liu, and Manfred Hauswirth. “VADETIS: An Explainable Evaluator for Anomaly Detection Techniques.” In Proceedings of the IEEE International Conference on Data Engineering (ICDE 2021). Demo Track. Greece, 2021. Bibtex PDF Code
VADETIS: An Explainable Evaluator for Anomaly Detection Techniques

Abdelouahab Khelifati, Mourad Khayati, Philippe Cudré-Mauroux, Adrian Hänni, Qian Liu, and Manfred Hauswirth. “VADETIS: An Explainable Evaluator for Anomaly Detection Techniques.” In Proceedings of the IEEE International Conference on Data Engineering (ICDE 2021). Demo Track. Greece, 2021.
```
@inproceedings{khelifati2021icde,
  title = {VADETIS: An Explainable Evaluator for Anomaly Detection Techniques},
  author = {Khelifati, Abdelouahab and Khayati, Mourad and Cudr{\'{e}}{-}Mauroux, Philippe and Hänni, Adrian and Liu, Qian and Hauswirth, Manfred},
  booktitle = {Proceedings of the IEEE International Conference on Data Engineering (ICDE 2021). Demo Track},
  year = {2021},
  address = {Greece},
  url = {https://exascale.info/assets/pdf/vadetis-icde2021.pdf},
  code = {https://github.com/eXascaleInfolab/vadetis.git}
}
```
×
Mourad Khayati, Alberto Lerner, Zakhar Tymchenko, and Philippe Cudré-Mauroux. “Mind the Gap: An Experimental Evaluation of Imputation of Missing Values Techniques in Time Series.” In Proceedings of the VLDB Endowment, Vol. 13, 2020. Bibtex PDF Code Award
Mind the Gap: An Experimental Evaluation of Imputation of Missing Values Techniques in Time Series

Mourad Khayati, Alberto Lerner, Zakhar Tymchenko, and Philippe Cudré-Mauroux. “Mind the Gap: An Experimental Evaluation of Imputation of Missing Values Techniques in Time Series.” In Proceedings of the VLDB Endowment, Vol. 13, 2020.
```
@inproceedings{khayati2020vldb,
  author = {Khayati, Mourad and Lerner, Alberto and Tymchenko, Zakhar and Cudr{\'{e}}{-}Mauroux, Philippe},
  title = {Mind the Gap: An Experimental Evaluation of Imputation of Missing Values Techniques in Time Series},
  booktitle = {Proceedings of the VLDB Endowment},
  volume = {13},
  number = {5},
  year = {2020},
  code = {https://github.com/eXascaleInfolab/bench-vldb20},
  url = {http://www.vldb.org/pvldb/vol13/p768-khayati.pdf},
  award = {https://vldb2020.org/vldb-2020-awards.html}
}
```
×

Ines Arous, Jie Yang, Mourad Khayati, and Philippe Cudré-Mauroux. “OpenCrowd: A Human-AI Collaborative Approach for Finding Social Influencers via Open-Ended Answers Aggregation.” In Proceedings of the Web Conference (WWW 2020). Taipei, Taiwan, 2020. Bibtex Slides PDF Code Video

OpenCrowd: A Human-AI Collaborative Approach for Finding Social Influencers via Open-Ended Answers Aggregation

@inproceedings{arous2020www,
  title = {OpenCrowd: A Human-AI Collaborative Approach for Finding Social Influencers via Open-Ended Answers Aggregation},
  author = {Arous, Ines and Yang, Jie and Khayati, Mourad and Cudr{\'e}-Mauroux, Philippe},
  booktitle = {Proceedings of the Web Conference (WWW 2020)},
  year = {2020},
  address = {Taipei, Taiwan},
  url = {https://exascale.info/assets/pdf/arous2020www.pdf},
  note = {https://exascale.info/assets/pdf/arous2020www-slides.pdf},
  video = {https://www.youtube.com/watch?v=LOPgd-8TS-k&list=PLJNwhMK_V7EwEzlo9exv6COBKA3MQ28KW&index=3&ab_channel=TheWebConference2020Web},
  code = {https://github.com/eXascaleInfolab/OpenCrowd}
}

Mourad Khayati, Philippe Cudré-Mauroux, and Michael H. Böhlen. “Scalable Recovery of Missing Blocks in Time Series with High and Low Cross-Correlations.” In International Journal of Knowledge and Information Systems (KAIS), 2019. Bibtex PDF Code
Scalable Recovery of Missing Blocks in Time Series with High and Low cross-Correlations

Mourad Khayati, Philippe Cudré-Mauroux, and Michael H. Böhlen. “Scalable Recovery of Missing Blocks in Time Series with High and Low Cross-Correlations.” In International Journal of Knowledge and Information Systems (KAIS), 2019.
```
@inproceedings{khayati2019kais,
  author = {Khayati, Mourad and Cudr{\'e}-Mauroux, Philippe and B{\"o}hlen, Michael H.},
  title = {Scalable Recovery of Missing Blocks in Time Series with High and Low cross-Correlations},
  booktitle = {International Journal of Knowledge and Information Systems (KAIS)},
  year = {2019},
  url = {https://rdcu.be/b32bv},
  code = {https://github.com/eXascaleInfolab/2019_kais-bench}
}
```
×
Ines Arous, Mourad Khayati, Philippe Cudré-Mauroux, Ying Zhang, Martin Kersten, and Svetlin Stalinlov. “RecovDB: Accurate and Efficient Missing Blocks Recovery for Large Time Series.” In Proceedings of the IEEE International Conference on Data Engineering (ICDE 2019). Demo Track. Macau, China, 2019. Bibtex PDF Code Poster Tool
RecovDB: accurate and efficient missing blocks recovery for large time series

Ines Arous, Mourad Khayati, Philippe Cudré-Mauroux, Ying Zhang, Martin Kersten, and Svetlin Stalinlov. “RecovDB: Accurate and Efficient Missing Blocks Recovery for Large Time Series.” In Proceedings of the IEEE International Conference on Data Engineering (ICDE 2019). Demo Track. Macau, China, 2019.
```
@inproceedings{arous2019icde,
  title = {RecovDB: accurate and efficient missing blocks recovery for large time series},
  author = {Arous, Ines and Khayati, Mourad and Cudr{\'e}-Mauroux, Philippe and Zhang, Ying and Kersten, Martin and Stalinlov, Svetlin},
  booktitle = {Proceedings of the IEEE International Conference on Data Engineering (ICDE 2019). Demo Track},
  year = {2019},
  address = {Macau, China},
  url = {https://exascale.info/assets/pdf/recovdb19.pdf},
  code = {https://github.com/eXascaleInfolab/2018-RecovDB},
  poster = {https://exascale.info/assets/pdf/recovdb2019poster.pdf},
  tool = {https://exascale.info/projects/recovdb/}
}
```
×
Artem Lutov, Mourad Khayati, and Philippe Cudré-Mauroux. “Clubmark: A Parallel Isolation Framework for Benchmarking and Profiling Clustering Algorithms on NUMA Architectures.” In 2018 IEEE International Conference on Data Mining (ICDM), Demo Track, Singapore, Singapore, November 17-20, 2018, 1481–86, 2018. Bibtex Slides PDF
Clubmark: A Parallel Isolation Framework for Benchmarking and Profiling Clustering Algorithms on NUMA Architectures

Artem Lutov, Mourad Khayati, and Philippe Cudré-Mauroux. “Clubmark: A Parallel Isolation Framework for Benchmarking and Profiling Clustering Algorithms on NUMA Architectures.” In 2018 IEEE International Conference on Data Mining (ICDM), Demo Track, Singapore, Singapore, November 17-20, 2018, 1481–86, 2018.
```
@inproceedings{clubmark18,
  author = {Lutov, Artem and Khayati, Mourad and Cudr{\'{e}}{-}Mauroux, Philippe},
  title = {Clubmark: {A} Parallel Isolation Framework for Benchmarking and Profiling Clustering Algorithms on {NUMA} Architectures},
  booktitle = {2018 {IEEE} International Conference on Data Mining (ICDM), Demo Track, Singapore, Singapore, November 17-20, 2018},
  pages = {1481--1486},
  year = {2018},
  doi = {10.1109/ICDMW.2018.00212},
  url = {https://exascale.info/assets/pdf/icdm18_clubmark.pdf},
  note = {https://www.slideshare.net/ArtemVL/clubmark-a-parallel-isolation-framework-for-benchmarking-and-profiling-clustering-algorithms-icdm18-demo-poster}
}
```
×
Mourad Khayati, Philippe Cudré-Mauroux, and Michael H. Böhlen. “Using Lowly Correlated Time Series to Recover Missing Values in Time Series: a Comparison between SVD and CD.” In Advances in Spatial and Temporal Databases - 15th International Symposium, SSTD 2015, Seoul, South Korea, August 26-28, 2015. Proceedings, 2015. Bibtex PDF
Using Lowly Correlated Time Series to Recover Missing Values in Time Series: a Comparison between SVD and CD

Mourad Khayati, Philippe Cudré-Mauroux, and Michael H. Böhlen. “Using Lowly Correlated Time Series to Recover Missing Values in Time Series: a Comparison between SVD and CD.” In Advances in Spatial and Temporal Databases - 15th International Symposium, SSTD 2015, Seoul, South Korea, August 26-28, 2015. Proceedings, 2015.
```
@conference{DBLP:conf/ssd/KhMB15,
  title = {Using Lowly Correlated Time Series to Recover Missing Values in Time Series: a Comparison between SVD and CD},
  booktitle = {Advances in Spatial and Temporal Databases - 15th International Symposium, {SSTD} 2015, Seoul, South Korea, August 26-28, 2015. Proceedings},
  year = {2015},
  author = {Khayati, Mourad and Cudr{\'e}-Mauroux, Philippe and B{\"o}hlen, Michael H.},
  url = {https://exascale.info/assets/pdf/khayati_sstd15.pdf}
}
```
×
Mourad Khayati, Michael H. Böhlen, and Johann Gamper. “Memory-Efficient Centroid Decomposition for Long Time Series.” In IEEE 30th International Conference on Data Engineering, Chicago, ICDE 2014, IL, USA, March 31 - April 4, 2014, 100–111, 2014. Bibtex PDF Code
Memory-efficient centroid decomposition for long time series

Mourad Khayati, Michael H. Böhlen, and Johann Gamper. “Memory-Efficient Centroid Decomposition for Long Time Series.” In IEEE 30th International Conference on Data Engineering, Chicago, ICDE 2014, IL, USA, March 31 - April 4, 2014, 100–111, 2014.
```
@conference{DBLP:conf/icde/KhayatiBG14,
  title = {Memory-efficient centroid decomposition for long time series},
  booktitle = { {IEEE} 30th International Conference on Data Engineering, Chicago, {ICDE} 2014, IL, USA, March 31 - April 4, 2014},
  year = {2014},
  pages = {100{\textendash}111},
  doi = {10.1109/ICDE.2014.6816643},
  url = {https://exascale.info/assets/pdf/khayati_ICDE14.pdf},
  author = {Khayati, Mourad and B{\"o}hlen, Michael H. and Gamper, Johann},
  code = {https://github.com/eXascaleInfolab/cdrec}
}
```
×