no code implementations • 31 Oct 2022 • Zixuan Geng, Maximilian Schleich, Dan Suciu
We prove a Duality Theorem, showing that rule-based and counterfactual-based explanations are dual to each other, then use this observation to develop an efficient algorithm for computing rule-based explanations, which uses the counterfactual-based explanation as an oracle.
1 code implementation • 5 Jan 2021 • Maximilian Schleich, Zixuan Geng, Yihong Zhang, Dan Suciu
Machine learning is increasingly applied in high-stakes decision making that directly affect people's lives, and this leads to an increased demand for systems to explain their decisions.
no code implementations • 18 Sep 2020 • Guy Van den Broeck, Anton Lykov, Maximilian Schleich, Dan Suciu
First, we consider fully-factorized data distributions, and show that the complexity of computing the SHAP explanation is the same as the complexity of computing the expected value of the model.
no code implementations • 15 Mar 2020 • Leopoldo Bertossi, Jordan Li, Maximilian Schleich, Dan Suciu, Zografoula Vagena
We propose a simple definition of an explanation for the outcome of a classifier based on concepts from causality.
no code implementations • 10 Jan 2020 • Amir Shaikhha, Maximilian Schleich, Alexandru Ghita, Dan Olteanu
We consider the problem of training machine learning models over multi-relational data.
no code implementations • 11 Oct 2019 • Ryan Curtin, Ben Moseley, Hung Q. Ngo, XuanLong Nguyen, Dan Olteanu, Maximilian Schleich
When the data matrix needs to be obtained from a relational database via a feature extraction query, the computation cost can be prohibitive, as the data matrix may be (much) larger than the total input relation size.
no code implementations • 22 Dec 2018 • Mahmoud Abo Khamis, Ryan R. Curtin, Benjamin Moseley, Hung Q. Ngo, XuanLong Nguyen, Dan Olteanu, Maximilian Schleich
This new width is sandwiched between the submodular and the fractional hypertree widths.