About Me

I am a Postdoctoral Scholar in the Paul G. Allen School of Computer Science & Engineering at the University of Washington, where I work with Prof. Dan Suciu. I received my PhD in Computer Science from the University of Oxford, where I was a member of the FDB research group led by Prof. Dan Olteanu. My research lies at the interface of databases and machine learning. In particular, I investigate how the learning of models can be improved by exploiting the structure and semantics of the underlying database.

Before the PhD, I received a MSc in Computer Science from Oxford and a BSc in Economics and Computational Mathematics from The American University of Paris.

Research and Publications

In my research, I aim to unify database systems and analytics engines into one highly optimised database-centric analytics engine, which can efficiently compute machine learning models over large-scale relational databases. Such a system can exploit the relational structure of the database to (1) avoid redundancy in data representation and computation, and (2) learn potentially more accurate machine learning models with low runtime complexity guarantees. For real applications in the retail and advertisement domains, the system can learn a host of machine learning models orders of magnitude faster than state-of-the-art competitors like TensorFlow and scikit-learn. For more information, please check out the publications listed below or get in touch.


GeCo: Quality Counterfactual Explanations in Real Time. [code] Conference
Maximilian Schleich, Zixuan Geng, Yihong Zhang, Dan Suciu.
arXiv report 2101.01292, 2020.

On the Tractability of SHAP Explanations. Conference
Guy Van den Broeck, Anton Lykov, Maximilian Schleich, Dan Suciu.
In AAAI 2021. arXiv report 2009.08634, 2020. Distinguished paper award.

Functional Aggregate Queries with Additive Inequalities. Journal
Mahmoud Abo Khamis, Ryan R. Curtin, Benjamin Moseley, Hung Q. Ngo, XuanLong Nguyen, Dan Olteanu, and Maximilian Schleich.
In ACM Transactions on Database Systems (TODS), 45(4), pages 1-41, 2020. Special issue of best papers at PODS 2019.
arXiv report 1812.09526, September 2020.

LMFAO: An engine for batches of group-by aggregates. [code] Demo
Maximilian Schleich and Dan Olteanu.
In Very Large Data Bases (PVLDB), (Demo Track), 13(12), 2020.


Causality-based Explanation of Classification Outcomes. [talk] Workshop
Leopoldo Bertossi, Jordan Li, Maximilian Schleich, Dan Suciu, Zografoula Vagena.
In ACM SIGMOD DEEM Workshop, pages 1–10, 2020.

Learning Models over Relational Data using Sparse Tensors and Functional Dependencies. Journal
Mahmoud Abo Khamis, Hung Ngo, XuanLong Nguyen, Dan Olteanu, and Maximilian Schleich.
In ACM Transactions on Database Systems (TODS), 45(2), pages 1-66, 2020. Special issue of best papers at PODS 2018.
arXiv report 1703.04780, Nov 2018.

Rk-means: Fast Clustering for Relational Data. Conference
Ryan Curtin, Ben Moseley, Hung Q. Ngo, XuanLong Nguyen, Dan Olteanu, Maximilian Schleich.
In Artificial Intelligence and Statistics (AISTATS), pages 2742-2752, 2020.
arXiv report 1910.04939, October 2019.

Multi-Layer Optimizations for End-to-End Data Analytics. Conference
Amir Shaikhha, Maximilian Schleich, Alexandru Ghita, and Dan Olteanu.
In Code Generation and Optimization (CGO), pages 145–157, San Diego, February 2020.
arXiv report 2001.03541, January 2020.

Learning Models over Relational Data: A Brief Tutorial. Conference
Maximilian Schleich, Dan Olteanu, Mahmoud Abo-Khamis, Hung Q. Ngo, and XuanLong Nguyen.
In Scalable Uncertainty Management (SUM), Compiègne, December 2019.
arXiv report 1911.06577, December 2019.

A Layered Aggregate Engine for Analytics Workloads. Conference [code]
Maximilian Schleich, Dan Olteanu, Mahmoud Abo-Khamis, Hung Q. Ngo, and XuanLong Nguyen.
In ACM SIGMOD, Amsterdam, July 2019.
Updated version in arXiv report 1906.08687, June 2019.

On Functional Aggregate Queries with Additive Inequalities. Conference
M. Abo Khamis, R. Curtin, B. Moseley, H. Ngo, X. Nguyen, D. Olteanu and M. Schleich.
In ACM Principles of Database Systems (PODS), Amsterdam, July 2019.
Extended version in arXiv report 1812.09526, April 2019.

AC/DC: In-Database Learning Thunderstruck. Workshop
Mahmoud Abo Khamis, Hung Q. Ngo, XuanLong Nguyen, Dan Olteanu, and Maximilian Schleich.
In 2nd Workshop on Data Management for End-to-End Machine Learning (DEEM@SIGMOD), Houston, June 2018.
arXiv report 1803.07480, Mar 2018.

In-Database Learning with Sparse Tensors. [slides] Conference
Mahmoud Abo Khamis, Hung Ngo, XuanLong Nguyen, Dan Olteanu, and Maximilian Schleich.
In ACM Principles of Database Systems (PODS), Houston, June 2018.
arXiv report 1703.04780, March 2017.

In-Database Factorized Learning. Workshop
Hung Ngo, XuanLong Nguyen, Dan Olteanu, and Maximilian Schleich.
In Alberto Mendelzon Workshop (AMW), Montevideo, June 2017.
Extended version in arXiv report 1703.04780.

Factorized Databases. Journal
Dan Olteanu and Maximilian Schleich.
In SIGMOD Record (Database Principles Column), vol. 45, no. 2, June 2016.

F: Regression Models over Factorized Views. [poster] Demo
Dan Olteanu and Maximilian Schleich.
In Very Large Data Bases (PVLDB), 9(13), New Delhi, Sept 2016.

Learning Linear Regression Models over Factorized Joins. [poster] Conference
Maximilian Schleich and Dan Olteanu and Radu Ciucanu.
In SIGMOD, San Francisco, June 2016.