{"id":17218194,"url":"https://github.com/hbaniecki/robust-feature-effects","last_synced_at":"2025-08-09T20:24:07.367Z","repository":{"id":243357101,"uuid":"812211971","full_name":"hbaniecki/robust-feature-effects","owner":"hbaniecki","description":"Robustness of Global Feature Effect Explanations (ECML PKDD 2024)","archived":false,"fork":false,"pushed_at":"2024-08-26T16:23:32.000Z","size":1206,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-30T13:14:54.391Z","etag":null,"topics":["accumulated-local-effects","dalex","explainable-ai","explainable-machine-learning","explanatory-model-analysis","feature-attribution","iml","interpretable-machine-learning","partial-dependence-plot"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/2406.09069","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/hbaniecki.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-06-08T08:52:55.000Z","updated_at":"2024-08-26T16:23:35.000Z","dependencies_parsed_at":"2024-06-08T09:54:26.068Z","dependency_job_id":"2b1c7319-a32b-4f56-a7c3-9d78a59b7c53","html_url":"https://github.com/hbaniecki/robust-feature-effects","commit_stats":null,"previous_names":["hbaniecki/robust-feature-effects"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hbaniecki%2Frobust-feature-effects","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hbaniecki%2Frobust-feature-effects/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hbaniecki%2Frobust-feature-effects/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hbaniecki%2Frobust-feature-effects/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hbaniecki","download_url":"https://codeload.github.com/hbaniecki/robust-feature-effects/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245477868,"owners_count":20621888,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["accumulated-local-effects","dalex","explainable-ai","explainable-machine-learning","explanatory-model-analysis","feature-attribution","iml","interpretable-machine-learning","partial-dependence-plot"],"created_at":"2024-10-15T03:45:45.198Z","updated_at":"2025-03-25T14:24:14.172Z","avatar_url":"https://github.com/hbaniecki.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# On the Robustness of Global Feature Effect Explanations\n\nThis repository is a supplement to [the following paper](https://arxiv.org/abs/2406.09069):\n\n\u003e 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\n\n```bibtex\n@inproceedings{baniecki2024robustness,\n    title     = {On the Robustness of Global Feature Effect Explanations},\n    author    = {Hubert Baniecki and \n                 Giuseppe Casalicchio and \n                 Bernd Bischl and \n                 Przemyslaw Biecek},\n    booktitle = {ECML PKDD},\n    year      = {2024}\n}\n```\n\n### Install the environment\n\n1. `mamba env create -f env.yml`\n2. install [OpenXAI](https://github.com/AI4LIFE-GROUP/OpenXAI):\n    - download `https://github.com/AI4LIFE-GROUP/OpenXAI`\n    - remove version of `torch`\n    - `mamba activate robustfe`\n    - `pip install .`\n\n### Run the experiments\n\n- `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\n- `experiment2.ipynb`, `experiment2_plot.ipynb` perform experiments reported in Section 5.2\n- `results` directory contains metadata of results from running `experiment1.ipynb` and `experiment2.ipynb`\n\n\n### Check out also\n\nAdebayo et al. **[Sanity Checks for Saliency Maps](https://doi.org/10.48550/arXiv.1810.03292)**. NeurIPS 2018\n\nBaniecki et al. **[Fooling Partial Dependence via Data Poisoning](https://doi.org/10.1007/978-3-031-26409-2_8)**. ECML PKDD 2022\n\nGkolemis et al. **[RHALE: Robust and Heterogeneity-aware Accumulated Local Effects](https://doi.org/10.48550/arXiv.2309.11193)**. ECAI 2023\n\nLin et al. **[On the Robustness of Removal-Based Feature Attributions](https://doi.org/10.48550/arXiv.2306.07462)**. NeurIPS 2023","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhbaniecki%2Frobust-feature-effects","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhbaniecki%2Frobust-feature-effects","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhbaniecki%2Frobust-feature-effects/lists"}