https://github.com/ai4healthuol/preddiff-interactions
Public code repository accompanying "PredDiff: Explanations and Interactions from Conditional Expectations"
Science Score: 23.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
○codemeta.json file
-
○.zenodo.json file
-
✓DOI references
Found 2 DOI reference(s) in README -
✓Academic publication links
Links to: sciencedirect.com -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (6.3%) to scientific vocabulary
Last synced: 9 months ago
·
JSON representation
Repository
Public code repository accompanying "PredDiff: Explanations and Interactions from Conditional Expectations"
Basic Info
- Host: GitHub
- Owner: AI4HealthUOL
- License: mit
- Language: Jupyter Notebook
- Default Branch: master
- Size: 12.6 MB
Statistics
- Stars: 5
- Watchers: 1
- Forks: 1
- Open Issues: 1
- Releases: 0
Created almost 4 years ago
· Last pushed over 3 years ago
https://github.com/AI4HealthUOL/preddiff-interactions/blob/master/
# *PredDiff*: Explanations and Interactions from Conditional Expectations
This repository provides resources to reproduce results from the paper:
[*PredDiff*: Explanations and Interactions from Conditional Expectations](https://www.sciencedirect.com/science/article/pii/S000437022200114X)
```
@article{bluecher2022,
title = {PredDiff: Explanations and Interactions from Conditional Expectations},
journal = {Artificial Intelligence},
volume = {312},
pages = {103774},
year = {2022},
doi = {https://doi.org/10.1016/j.artint.2022.103774},
author = {Stefan Blcher and Johanna Vielhaben and Nils Strodthoff},
}
```
We provide ready-to-run jupyter notebooks, which apply *PredDiff* on different datasets
* **Synthetic regression** (`synthetic_dataset.ipynb`): (Interaction) relevances for a regressor on the synthetic dataset discussed in the paper
* **MNIST** (`mnist.ipynb`): (Interaction) relevances for a classifier trained on MNIST seen as a tabular dataset
* **NHANES** (`nhanes.ipynb`): (Interaction) relevances for a classifier trained on the NHANES (mortality regression) dataset
# Requirements
Install dependencies from `pred_diff.yml` by running `conda env create -f pred_diff.yml` and activate the environment via `conda activate pred_diff`
Owner
- Name: AI4HealthUOL
- Login: AI4HealthUOL
- Kind: organization
- Location: Germany
- Website: https://uol.de/en/ai4health
- Twitter: nstrodt
- Repositories: 6
- Profile: https://github.com/AI4HealthUOL
Public repositories of the AI4Health Division at Oldenburg University