Fairwashing explanations with off-manifold detergent

Authors: Christopher Anders, Plamen Pasliev, Ann-Kathrin Dombrowski, Klaus-Robert Müller, Pan Kessel

ICML 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We validate our theoretical predictions in detailed experiments for various explanation methods, classifier architectures, and datasets, as well as for different tasks.
Researcher Affiliation Academia 1Machine Learning Group, Technische Universit at Berlin, Germany 2Max-Planck-Institut f ur Informatik, Saarbr ucken, Germany 3Department of Brain and Cognitive Engineering, Korea University, Seoul, Korea.
Pseudocode No The paper does not contain any sections explicitly labeled "Pseudocode" or "Algorithm", nor does it present structured code-like blocks.
Open Source Code Yes The code for all our experiments is publicly available at https://github.com/fairwashing/fairwashing.
Open Datasets Yes Datasets: We consider the MNIST, Fashion MNIST, and CIFAR10 datasets. We use the standard training and test sets for our analysis.
Dataset Splits Yes We use the standard training and test sets for our analysis.
Hardware Specification Yes This is computationally expensive and takes about 48h using four Tesla P100 GPUs.
Software Dependencies No The paper mentions using "standard deep learning libraries" (e.g., Kokhlikyan et al., 2019; Alber et al., 2019; Ancona et al., 2018) but does not specify exact version numbers for any software dependencies.
Experiment Setup Yes We train the model g by minimizing the standard cross entropy loss for classification. The manipulated model g is then trained by minimizing the loss (11) for a given target explanation ht. This target was chosen to have the shape of the number 42. For more details about the architectures and training, we refer to the Appendix D.