https://github.com/hbaniecki/robust-feature-effects

Robustness of Global Feature Effect Explanations (ECML PKDD 2024)
https://github.com/hbaniecki/robust-feature-effects

accumulated-local-effects dalex explainable-ai explainable-machine-learning explanatory-model-analysis feature-attribution iml interpretable-machine-learning partial-dependence-plot

Last synced: 19 days ago
JSON representation

Robustness of Global Feature Effect Explanations (ECML PKDD 2024)

• Host: GitHub
• URL: https://github.com/hbaniecki/robust-feature-effects
• Owner: hbaniecki
• License: mit
• Created: 2024-06-08T08:52:55.000Z (7 months ago)
• Default Branch: main
• Last Pushed: 2024-08-26T16:23:32.000Z (4 months ago)
• Last Synced: 2024-10-16T03:45:48.822Z (2 months ago)
• Topics: accumulated-local-effects, dalex, explainable-ai, explainable-machine-learning, explanatory-model-analysis, feature-attribution, iml, interpretable-machine-learning, partial-dependence-plot
• Language: Jupyter Notebook
• Homepage: https://arxiv.org/abs/2406.09069
• Size: 1.15 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# On the Robustness of Global Feature Effect Explanations

This repository is a supplement to [the following paper](https://arxiv.org/abs/2406.09069):

> Hubert Baniecki, Giuseppe Casalicchio, Bernd Bischl, Przemyslaw Biecek. *On the Robustness of Global Feature Effect Explanations*. **ECML PKDD 2024** https://arxiv.org/abs/2406.09069

```bibtex

@inproceedings{baniecki2024robustness,

    title     = {On the Robustness of Global Feature Effect Explanations},

    author    = {Hubert Baniecki and 

                 Giuseppe Casalicchio and 

                 Bernd Bischl and 

                 Przemyslaw Biecek},

    booktitle = {ECML PKDD},

    year      = {2024}

}

```

### Install the environment

1. `mamba env create -f env.yml`

2. install [OpenXAI](https://github.com/AI4LIFE-GROUP/OpenXAI):

    - download `https://github.com/AI4LIFE-GROUP/OpenXAI`

    - remove version of `torch`

    - `mamba activate robustfe`

    - `pip install .`

### Run the experiments

- `experiment1.ipynb` uses the algorithm [(Baniecki et al., 2022)](https://doi.org/10.1007/978-3-031-26409-2_8) implemented in `src` to perform experiments reported in Section 5.1

- `experiment2.ipynb`, `experiment2_plot.ipynb` perform experiments reported in Section 5.2

- `results` directory contains metadata of results from running `experiment1.ipynb` and `experiment2.ipynb`

### Check out also

Adebayo et al. **[Sanity Checks for Saliency Maps](https://doi.org/10.48550/arXiv.1810.03292)**. NeurIPS 2018

Baniecki et al. **[Fooling Partial Dependence via Data Poisoning](https://doi.org/10.1007/978-3-031-26409-2_8)**. ECML PKDD 2022

Gkolemis et al. **[RHALE: Robust and Heterogeneity-aware Accumulated Local Effects](https://doi.org/10.48550/arXiv.2309.11193)**. ECAI 2023

Lin et al. **[On the Robustness of Removal-Based Feature Attributions](https://doi.org/10.48550/arXiv.2306.07462)**. NeurIPS 2023