diff --git a/CITATION.cff b/CITATION.cff index 2100c0e..d250e7d 100644 --- a/CITATION.cff +++ b/CITATION.cff @@ -1,8 +1,7 @@ - cff-version: 1.2.0 title: >- - Software for Dataset-wide XAI: From Local Explanations to - Global Insights with Zennit, CoRelAy, and ViRelAy + Software for dataset-wide XAI: From local explanations to + global insights with Zennit, CoRelAy, and ViRelAy message: >- If you use this software, please cite it using the metadata from this file. @@ -11,49 +10,76 @@ authors: - given-names: Christopher J. family-names: Anders orcid: 'https://orcid.org/0000-0003-3295-8486' + affiliation: RIKEN Center for Advanced Intelligence Project - given-names: David family-names: Neumann orcid: 'https://orcid.org/0000-0003-1907-8329' + affiliation: >- + Fraunhofer Institute for Telecommunications, + Heinrich-Hertz-Institut, HHI - given-names: Wojciech family-names: Samek orcid: 'https://orcid.org/0000-0002-6283-3265' + affiliation: >- + Fraunhofer Institute for Telecommunications, + Heinrich-Hertz-Institut, HHI - given-names: Klaus-Robert family-names: Müller orcid: 'https://orcid.org/0000-0002-3861-7685' + affiliation: Technische Universität Berlin - given-names: Sebastian family-names: Lapuschkin orcid: 'https://orcid.org/0000-0002-0762-7258' + affiliation: >- + Fraunhofer Institute for Telecommunications, + Heinrich-Hertz-Institut, HHI identifiers: - type: doi - value: 10.48550/arXiv.2106.13200 - description: arXiv Preprint + value: 10.1371/journal.pone.0336683 + description: DOI - type: url - value: 'https://arxiv.org/abs/2106.13200' - description: arXiv Preprint -repository-code: 'https://github.com/virelay/corelay.git' -url: 'https://corelay.readthedocs.io/en/latest/' + value: >- + https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0336683 + description: PLOS One +repository-code: 'https://github.com/virelay/virelay.git' +url: 'https://virelay.readthedocs.io/en/latest/' abstract: >- - Deep Neural Networks (DNNs) are known to be strong - predictors, but their prediction strategies can rarely be - understood. With recent advances in Explainable Artificial - Intelligence (XAI), approaches are available to explore - the reasoning behind those complex models' predictions. - Among post-hoc attribution methods, Layer-wise Relevance - Propagation (LRP) shows high performance. For deeper - quantitative analysis, manual approaches exist, but - without the right tools they are unnecessarily labor - intensive. In this software paper, we introduce three - software packages targeted at scientists to explore model - reasoning using attribution approaches and beyond: (1) - Zennit - a highly customizable and intuitive attribution - framework implementing LRP and related approaches in - PyTorch, (2) CoRelAy - a framework to easily and quickly - construct quantitative analysis pipelines for dataset-wide - analyses of explanations, and (3) ViRelAy - a - web-application to interactively explore data, - attributions, and analysis results. With this, we provide - a standardized implementation solution for XAI, to - contribute towards more reproducibility in our field. + The predictive capabilities of Deep Neural Networks (DNNs) + are well-established, yet the underlying mechanisms + driving these predictions often remain opaque. The advent + of Explainable Artificial Intelligence (XAI) has + introduced novel methodologies to explore the reasoning + behind complex model predictions of complex models. Among + post-hoc attribution methods, Layer-wise Relevance + Propagation (LRP) has demonstrated notable adaptability + and performance for explaining individual predictions – + provided the method is used to its full potential. For + deeper dataset-wide and quantitative analyses, however, + the manual inspection of individual attribution maps + remains unnecessarily labor-intensive and time consuming. + While several approaches for dataset-wide XAI-analyses + have been proposed, unified and accessible implementations + of such tools are still lacking. Furthermore, there is a + notable absence of dedicated visualization and analysis + software to support stakeholders in interpreting both + local and global XAI results effectively. This gap + underscores the need for comprehensive software tools that + facilitate both granular and holistic understanding of + model behavior, as well as easing the adaptability of XAI + in applications and the sciences. To address these + challenges, we present three software packages designed to + facilitate the exploration of model reasoning using + attribution approaches and beyond: (1) Zennit – a highly + customizable and intuitive attribution framework + implementing LRP and related methods in PyTorch, (2) + CoRelAy – a framework to easily and quickly construct + quantitative analysis pipelines for dataset-wide analyses + of explanations, and (3) ViRelAy – an interactive + web-application for exploring data, attributions, and + analysis results. By providing a standardized + implementation for XAI, we aim to promote reproducibility + in our field and empower scientists and practitioners to + uncover the intricacies of complex model behavior. keywords: - Explainable Artificial Intelligence - XAI @@ -64,4 +90,9 @@ keywords: - Zennit - CoRelAy - ViRelAy -license: GPL-3.0-or-later AND LGPL-3.0-or-later +license: + - GPL-3.0-or-later + - LGPL-3.0-or-later +commit: 8c9b9286ab4bf8ec59eafdceda6bb009c72e4b76 +version: 1.0.0 +date-released: '2025-08-06' diff --git a/README.md b/README.md index e327796..0474382 100644 --- a/README.md +++ b/README.md @@ -29,16 +29,19 @@ For more information about CoRelAy, getting started guides, in-depth tutorials, If you find CoRelAy useful for your research, why not cite our related [paper](https://arxiv.org/abs/2106.13200): ```bibtex -@article{anders2021software, - author = {Anders, Christopher J. and +@article{bibliography:software-for-dataset-wide-xai, + author = {Anders, {Christopher J.} and Neumann, David and Samek, Wojciech and - Müller, Klaus-Robert and + Müller, {Klaus-Robert} and Lapuschkin, Sebastian}, - title = {Software for Dataset-wide XAI: From Local Explanations to Global Insights with {Zennit}, {CoRelAy}, and {ViRelAy}}, - year = {2021}, - volume = {abs/2106.13200}, - journal = {CoRR} + title = {Software for {dataset-wide} {XAI}: From local explanations to global insights with Zennit, {CoRelAy}, and {ViRelAy}}, + year = {2026}, + month = jan, + journal = {{PLOS} One}, + volume = {21}, + number = {1}, + pages = {1--38} } ``` diff --git a/src/corelay/processor/distance.py b/src/corelay/processor/distance.py index cdaff9b..6d1ff82 100644 --- a/src/corelay/processor/distance.py +++ b/src/corelay/processor/distance.py @@ -56,12 +56,10 @@ class SciPyPDist(Distance): * "pnorm" * "jaccard", "jacc", "ja", "j" * "jensenshannon", "js" - * "kulczynski1" * "mahalanobis", "mahal", "mah" * "rogerstanimoto" * "russellrao" * "seuclidean", "se", "s" - * "sokalmichener" * "sokalsneath" * "sqeuclidean", "sqe", "sqeuclid" * "yule" @@ -124,7 +122,6 @@ def function(self, data: typing.Any) -> typing.Any: 'j', 'jensenshannon', 'js', - 'kulczynski1', 'mahalanobis', 'mahal', 'mah', @@ -133,7 +130,6 @@ def function(self, data: typing.Any) -> typing.Any: 'seuclidean', 'se', 's', - 'sokalmichener', 'sokalsneath', 'sqeuclidean', 'sqe', diff --git a/tests/linters/cspell/.cspell.json b/tests/linters/cspell/.cspell.json index 5811756..08d76de 100644 --- a/tests/linters/cspell/.cspell.json +++ b/tests/linters/cspell/.cspell.json @@ -148,6 +148,7 @@ "ifmat", "imgmath", "incollection", + "Institut", "intersphinx", "issn", "issuetitle", @@ -191,6 +192,7 @@ "pdist", "pearsonr", "Pickler", + "PLOS", "Plugboards", "pnorm", "posargs", @@ -203,6 +205,7 @@ "rcfile", "reftypes", "regionref", + "RIKEN", "rodolphebarbanneau", "rogerstanimoto", "russellrao", @@ -224,6 +227,7 @@ "SSIM", "synset", "tamasfe", + "Technische", "testpaths", "texlive", "toarray", @@ -234,6 +238,7 @@ "ufunc", "Ulrike", "umap", + "Universität", "urldate", "varnames", "vimrc",