Avoiding Discrimination through Causal Reasoning

Authors: Niki Kilbertus, Mateo Rojas Carulla, Giambattista Parascandolo, Moritz Hardt, Dominik Janzing, Bernhard Schölkopf

NeurIPS 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical Finally, we put forward natural causal non-discrimination criteria and develop algorithms that satisfy them. Our framework is limited by the assumption that we can construct a valid causal graph. The removal of proxy discrimination moreover depends on the functional form of the causal dependencies. We have focused on the conceptual and theoretical analysis, and experimental validations are beyond the scope of the present work.
Researcher Affiliation Academia Niki Kilbertus nkilbertus@tue.mpg.de Mateo Rojas-Carulla mrojas@tue.mpg.de Giambattista Parascandolo gparascandolo@tue.mpg.de Moritz Hardt hardt@berkeley.edu Dominik Janzing janzing@tue.mpg.de Bernhard Sch olkopf bs@tue.mpg.de Max Planck Institute for Intelligent Systems University of Cambridge Max Planck ETH Center for Learning Systems University of California, Berkeley
Pseudocode No The paper describes procedures in numbered steps within the text, but it does not present them as formal pseudocode or in a clearly labeled algorithm block.
Open Source Code No The paper does not provide any statement or link regarding the availability of open-source code for the described methodology.
Open Datasets No The paper is theoretical and focuses on conceptual and theoretical analysis; it does not report on experiments using datasets, thus no dataset availability information is provided.
Dataset Splits No The paper is theoretical and does not conduct empirical experiments; therefore, it does not specify dataset splits for training, validation, or testing.
Hardware Specification No The paper states that 'experimental validations are beyond the scope of the present work', thus no hardware specifications are mentioned.
Software Dependencies No The paper focuses on conceptual and theoretical analysis; it does not describe experimental implementations or list specific software dependencies with version numbers.
Experiment Setup No The paper states that 'experimental validations are beyond the scope of the present work', thus no experimental setup details like hyperparameters or training settings are provided.