Investigating Neighborhood Generation Methods for Explanations of Obscure Image Classifiers

摘要：

　　Given the wide use of machine learning approaches based on opaque prediction models,understanding the reasons behind decisions of black box decision systems is nowadays a crucial topic.We address the problem of providing meaningful explanations in the widely-applied image classification tasks.In particular,we explore the impact of changing the neighborhood generation function for a local interpretable modelagnostic explanator by proposing four different variants.All the proposed methods are based on a grid-based segmentation of the images,but each of them proposes a different strategy for generating the neighborhood of the image for which an explanation is required.A deep experimentation shows both improvements and weakness of each proposed approach.

作者: Riccardo Guidotti Anna Monreale Leonardo Cariaggi

作者单位: ISTI-CNR,Pisa,Italy;University of Pisa,Pisa,Italy University of Pisa,Pisa,Italy

会议类型: 国际会议

会议名称: The 23rd Pacific-Asia Conference on Knowledge Discovery and Data Mining (第23届亚太知识发现和数据挖掘国际会议(PAKDD2019)

会议地点: 澳门

会议语种:英文

页码: 55-68

在线出版日期: 2019-04-14（万方平台首次上网日期，不代表论文的发表时间）