Maximilian Schleich — accepted AI-conference papers

2021

On the Tractability of SHAP Explanations

Guy Van den Broeck, Anton Lykov, Maximilian Schleich, Dan Suciu

AAAI 2021technical

SHAP explanations are a popular feature-attribution mechanism for explainable AI. They use game-theoretic notions to measure the influence of individual features on the prediction of a machine learning model. Despite a lot of recent interest from both academia and industry, it is not known whether S…

Cited by 323 Source ↗PDF ↗Scholar ↗

2020

Rk-means: Fast Clustering for Relational Data

Ryan Curtin, Benjamin Moseley, Hung Ngo, XuanLong Nguyen, Dan Olteanu, Maximilian Schleich

AISTATS 2020poster

Conventional machine learning algorithms cannot be applied until a data matrix is available to process. 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…

Cited by 22 Source ↗PDF ↗Scholar ↗