Towards Robust Interpretability with Self-Explaining Neural Networks

Authors: David Alvarez Melis, Tommi Jaakkola

NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results across various benchmark datasets show that our framework offers a promising direction for reconciling model complexity and interpretability. We carry out quantitative evaluation on three classification settings: (i) MNIST digit recognition, (ii) benchmark UCI datasets [13] and (iii) Propublica s COMPAS Recidivism Risk Score datasets.
Researcher Affiliation Academia David Alvarez-Melis CSAIL, MIT dalvmel@mit.edu Tommi S. Jaakkola CSAIL, MIT tommi@csail.mit.edu
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide a link to open-source code for the described methodology or explicitly state its release. The only GitHub link mentioned is for the COMPAS dataset, not the authors' code.
Open Datasets Yes We carry out quantitative evaluation on three classification settings: (i) MNIST digit recognition, (ii) benchmark UCI datasets [13] and (iii) Propublica s COMPAS Recidivism Risk Score datasets.1 github.com/propublica/compas-analysis/
Dataset Splits No The paper does not provide specific details on training, validation, or test dataset splits (e.g., percentages, sample counts, or citations to predefined splits for their experiments).
Hardware Specification No The paper does not provide any specific hardware details such as GPU models, CPU models, or cloud computing specifications used for running the experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers (e.g., library or solver names with version numbers).
Experiment Setup No The paper discusses aspects of the model design like the regularization parameter λ, but it does not provide specific experimental setup details such as learning rates, batch sizes, optimizers, or number of training epochs.