From ada19d007d990298f76b8db3600d1d2c825adb78 Mon Sep 17 00:00:00 2001 From: Hubert Baniecki Date: Thu, 3 Oct 2024 17:11:10 +0200 Subject: [PATCH 1/2] add citation (#241) --- README.md | 12 +++++++++++- docs/source/index.rst | 13 +++++++++++++ 2 files changed, 24 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 23ddbc9c..27f9bf60 100644 --- a/README.md +++ b/README.md @@ -94,4 +94,14 @@ The documentation of ``shapiq`` can be found at https://shapiq.readthedocs.io ## 💬 Citation -If you **enjoy** `shapiq` consider starring ⭐ the repository. +If you use the `shapiq` package, please cite our [NeurIPS paper](https://arxiv.org/abs/2410.01649): + +```html +@inproceedings{muschalik2024shapiq, + title = {shapiq: Shapley Interactions for Machine Learning}, + author = {Maximilian Muschalik and Hubert Baniecki and Fabian Fumagalli and + Patrick Kolpaczki and Barbara Hammer and Eyke H\"{u}llermeier}, + booktitle = {NeurIPS}, + year = {2024} +} +``` \ No newline at end of file diff --git a/docs/source/index.rst b/docs/source/index.rst index 697b1f0b..82a57b9f 100644 --- a/docs/source/index.rst +++ b/docs/source/index.rst @@ -3,6 +3,19 @@ The ``shapiq`` Python package Shapley Interaction Quantification (``shapiq``) is a Python package for (1) approximating any-order Shapley interactions, (2) benchmarking game-theoretical algorithms for machine learning, (3) explaining feature interactions of model predictions. ``shapiq`` extends the well-known `shap `_ package for both researchers working on game theory in machine learning, as well as the end-users explaining models. SHAP-IQ extends individual Shapley values by quantifying the **synergy** effect between entities (aka **players** in the jargon of game theory) like explanatory features, data points, or weak learners in ensemble models. Synergies between players give a more comprehensive view of machine learning models. +If you use the ``shapiq`` package, please cite our `NeurIPS paper `_: + +.. code:: + + @inproceedings{muschalik2024shapiq, + title = {shapiq: Shapley Interactions for Machine Learning}, + author = {Maximilian Muschalik and Hubert Baniecki and Fabian Fumagalli and + Patrick Kolpaczki and Barbara Hammer and Eyke H\"{u}llermeier}, + booktitle = {NeurIPS}, + year = {2024} + } + + Contents ~~~~~~~~ From 65daf5b59471e319c930738ed41b3b7c0ff23931 Mon Sep 17 00:00:00 2001 From: Maximilian Date: Fri, 4 Oct 2024 10:31:17 +0200 Subject: [PATCH 2/2] ran code-formatter --- README.md | 4 ++-- docs/source/index.rst | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 27f9bf60..bbb5bc9c 100644 --- a/README.md +++ b/README.md @@ -99,9 +99,9 @@ If you use the `shapiq` package, please cite our [NeurIPS paper](https://arxiv.o ```html @inproceedings{muschalik2024shapiq, title = {shapiq: Shapley Interactions for Machine Learning}, - author = {Maximilian Muschalik and Hubert Baniecki and Fabian Fumagalli and + author = {Maximilian Muschalik and Hubert Baniecki and Fabian Fumagalli and Patrick Kolpaczki and Barbara Hammer and Eyke H\"{u}llermeier}, booktitle = {NeurIPS}, year = {2024} } -``` \ No newline at end of file +``` diff --git a/docs/source/index.rst b/docs/source/index.rst index 82a57b9f..7732cc9c 100644 --- a/docs/source/index.rst +++ b/docs/source/index.rst @@ -9,7 +9,7 @@ If you use the ``shapiq`` package, please cite our `NeurIPS paper