Scholarlink

<p>Explaining predictions of classifiers is a fundamental problem in eXplainable Artificial Intelligence (XAI). LIME (for Local Interpretable Model-agnostic Explanations) is a popular XAI technique able to explain any classifier by providing an interpretable model which approximates the black box locally to the instance under consideration. In order to build interpretable local models, LIME requires the user to explicitly define a space of interpretable components, also called artefacts, associated with the input instance. To reconstruct local black-box behaviour, the instance neighbourhood is explored by generating instance neighbours as random subsets of the provided artefacts. In this work, we note that the above-depicted strategy has a limitation given by the fact that the local explanation is limited to be expressed only in terms of object artefacts. To overcome this limitation, in this work we propose <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="521_2025_11227_Article_IEq1.gif" Format="GIF" Height="14" Rendition="HTML" Resolution="72" Type="Linedraw" Width="61" /> </InlineMediaObject> <EquationSource Format="TEX">\(\mathcal {S}{\text {-LIME}}\)</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mi mathvariant="script">S</mi> <mtext>-LIME</mtext> </mrow> </math></EquationSource> </InlineEquation>, a variant of the basic LIME method exploiting unsupervised learning to replace object artefacts with self-generated semantic features in neighbourhood generation. This characteristic enables our approach to sample instance neighbours in a more semantic-driven fashion and greatly reduces the bias associated with explanations. We demonstrate the applicability and effectiveness of our proposal in the text classification domain. We also present a further extension for textual data in which word groups are used to obtain richer explanations. Comparison with the baseline highlights the superior quality of the explanations obtained by adopting our strategy.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Improving local interpretable classifier explanations exploiting self-generated semantic features

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年5月2日

查看全文
  • Fabrizio Angiulli,
  • Fabio Fassetti,
  • Simona Nisticò

摘要

Explaining predictions of classifiers is a fundamental problem in eXplainable Artificial Intelligence (XAI). LIME (for Local Interpretable Model-agnostic Explanations) is a popular XAI technique able to explain any classifier by providing an interpretable model which approximates the black box locally to the instance under consideration. In order to build interpretable local models, LIME requires the user to explicitly define a space of interpretable components, also called artefacts, associated with the input instance. To reconstruct local black-box behaviour, the instance neighbourhood is explored by generating instance neighbours as random subsets of the provided artefacts. In this work, we note that the above-depicted strategy has a limitation given by the fact that the local explanation is limited to be expressed only in terms of object artefacts. To overcome this limitation, in this work we propose \(\mathcal {S}{\text {-LIME}}\) S -LIME , a variant of the basic LIME method exploiting unsupervised learning to replace object artefacts with self-generated semantic features in neighbourhood generation. This characteristic enables our approach to sample instance neighbours in a more semantic-driven fashion and greatly reduces the bias associated with explanations. We demonstrate the applicability and effectiveness of our proposal in the text classification domain. We also present a further extension for textual data in which word groups are used to obtain richer explanations. Comparison with the baseline highlights the superior quality of the explanations obtained by adopting our strategy.