Search Results for author: Maximilian Schleich

Found 7 papers, 1 papers with code

Computing Rule-Based Explanations by Leveraging Counterfactuals

no code implementations31 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.

counterfactual

GeCo: Quality Counterfactual Explanations in Real Time

1 code implementation5 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.

counterfactual Decision Making

On the Tractability of SHAP Explanations

no code implementations18 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.

BIG-bench Machine Learning

Causality-based Explanation of Classification Outcomes

no code implementations15 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.

Classification General Classification

Rk-means: Fast Clustering for Relational Data

no code implementations11 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.

Clustering

Cannot find the paper you are looking for? You can Submit a new open access paper.