arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.13076cs.AIcs.CYcs.LG
收藏

黑箱模型解释方法的基准测试与综述

Benchmarking and Survey of Explanation Methods for Black Box Models

Scuola Normale Superiore(高等师范学院);ISTI-CNR(意大利国家研究委员会信息科学与技术研究所);Largo Bruno Pontecorvo(布鲁诺·蓬特科沃广场)

Francesco Bodria, Fosca Giannotti, Riccardo Guidotti, Francesca Naretto, Dino Pedreschi, Salvatore Rinzivillo

摘要:

黑箱模型在人工智能中的广泛应用,增强了对解释方法的需求,以揭示这些模糊的模型如何达成特定的决策。检索解释是揭示可能的偏见和解决实际或道德问题的基础。目前,文献中充满了各种不同解释的方法。我们根据返回的解释类型对解释方法进行了分类。我们提出了最新的和广泛使用的解释,我们显示了一个直观的比较解释和定量基准。

英文摘要:

The widespread adoption of black-box models in Artificial Intelligence has enhanced the need for explanation methods to reveal how these obscure models reach specific decisions. Retrieving explanations is fundamental to unveil possible biases and to resolve practical or ethical issues. Nowadays, the literature is full of methods with different explanations. We provide a categorization of explanation methods based on the type of explanation returned. We present the most recent and widely used explainers, and we show a visual comparison among explanations and a quantitative benchmarking.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑