Neural Network Attributions: A Causal Perspective

Authors: Aditya Chattopadhyay, Piyushi Manupriya, Anirban Sarkar, Vineeth N Balasubramanian

ICML 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We report experimental results on both simulated and real datasets showcasing the promise and usefulness of the proposed algorithm.
Researcher Affiliation Academia 1Center for Imaging Science, Johns Hopkins University, Baltimore, USA. 2Department of Computer Science and Engineering, Indian Institute of Technology Hyderabad, Telangana, India.
Pseudocode Yes Appendix A.4.1 presents a detailed algorithm/pseudocode along with its complexity analysis.
Open Source Code No The paper does not provide concrete access to the source code for the methodology described in this paper. No specific repository link or explicit code release statement is found.
Open Datasets Yes A 3-layer neural network (with relu() activation functions) was trained on the Iris dataset (Dheeru & Karra Taniskidou, 2017). We used a publicly available NASA Dashlink flight dataset (https://c3.nasa.gov/dashlink/projects/85/) to train a single hidden layer LSTM. we train a conditional (Kingma et al., 2014) β-VAE (Higgins et al., 2016) on MNIST data.
Dataset Splits No The paper does not provide specific dataset split information (exact percentages, sample counts, citations to predefined splits, or detailed splitting methodology) needed to reproduce the data partitioning. It mentions "training data" and "test sequences" but no explicit validation set or split ratios.
Hardware Specification No The paper does not provide specific hardware details such as exact GPU/CPU models, processor types, or memory amounts used for running its experiments.
Software Dependencies No The paper mentions software like 'TensorFlow' and 'PyTorch' in its references, and specific activation functions like 'relu()' and 'sigmoid()', but does not provide specific version numbers for these or other key software dependencies required to replicate the experiments.
Experiment Setup Yes A 3-layer neural network (with relu() activation functions) was trained on the Iris dataset. A Gated Recurrent Unit (GRU) with a single input, hidden and output neuron with sigmoid() activations is used to learn the pattern. β was set to 10. The latent variables were modeled as 10 discrete variables (for each digit class) [c0, c1, ..., c9] ... and 10 continuous variables ... [z0, z1, z2, ..., z9].