ModelSpeX: Model Specification Using Explainable Artificial Intelligence Methods

Udo Schlegel, Eren Cakmak, Daniel A. Keim
<span title="">2020</span> <i title="The Eurographics Association"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/f6tzaq6uljh4dc3tzmkvrwhto4" style="color: black;">Workshop on Machine Learning Methods in Visualisation for Big Data</a> </i> &nbsp;
Explainable artificial intelligence (XAI) methods aim to reveal the non-transparent decision-making mechanisms of black-box models. The evaluation of insight generated by such XAI methods remains challenging as the applied techniques depend on many factors (e.g., parameters and human interpretation). We propose ModelSpeX, a visual analytics workflow to interactively extract human-centered rule-sets to generate model specifications from black-box models (e.g., neural networks). The workflow
more &raquo; ... es to reason about the underlying problem, to extract decision rule sets, and to evaluate the suitability of the model for a particular task. An exemplary usage scenario walks an analyst trough the steps of the workflow to show the applicability.
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2312/mlvis.20201100">doi:10.2312/mlvis.20201100</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/mlvis-ws/SchlegelCK20.html">dblp:conf/mlvis-ws/SchlegelCK20</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/o6knz2x4uvfatovlmpx6nsipia">fatcat:o6knz2x4uvfatovlmpx6nsipia</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220117185337/https://diglib.eg.org/xmlui/bitstream/handle/10.2312/mlvis20201100/007-011.pdf;jsessionid=3539749DB130A12C064684DA6B591E4E?sequence=1" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/a5/ba/a5bab4002aff80762c8d7938d702c7fb8a213249.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2312/mlvis.20201100"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>