arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2202.06861cs.LG
收藏

Quantus:一个用于负责任评估神经网络解释及其他内容的可解释人工智能工具包

Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond

TU Berlin(柏林工业大学);Fraunhofer Heinrich-Hertz-Institute(弗劳恩霍夫海因里希·赫兹研究所);University of Potsdam(波茨坦大学);BIFOLD – Berlin Institute for the Foundations of Learning and Data(BIFOLD——柏林学习与数据基础研究所)

Anna Hedström, Leander Weber, Dilyara Bareeva, Daniel Krakowczyk, Franz Motzkus, Wojciech Samek, Sebastian Lapuschkin, Marina M. -C. Höhne

AI总结:

针对缺乏专注 XAI 评估工具的问题,本文提出 Python 工具包 Quantus,集成组织良好且持续扩充的解释评估指标与教程,以提升神经网络解释评估的透明度、效率和可复现性。

摘要:

解释方法的评估是一个尚未得到深入探索的研究课题,然而,由于可解释性被认为能够增强人们对人工智能的信任,因此有必要系统地审查和比较各种解释方法,以确认其正确性。迄今为止,尚不存在一个专注于 XAI 评估、能够让研究人员全面且快速地评估神经网络预测解释性能的工具。为提高该领域的透明度和可复现性,我们因此构建了 Quantus——一个用 Python 编写的综合性评估工具包,其中包含不断扩充且组织良好的评估指标集合,以及用于评估可解释方法的教程。该工具包已经过全面测试,并以开源许可证在 PyPi(或 https://github.com/understandable-machine-intelligence-lab/Quantus/)上提供。

英文摘要:

The evaluation of explanation methods is a research topic that has not yet been explored deeply, however, since explainability is supposed to strengthen trust in artificial intelligence, it is necessary to systematically review and compare explanation methods in order to confirm their correctness. Until now, no tool with focus on XAI evaluation exists that exhaustively and speedily allows researchers to evaluate the performance of explanations of neural network predictions. To increase transparency and reproducibility in the field, we therefore built Quantus -- a comprehensive, evaluation toolkit in Python that includes a growing, well-organised collection of evaluation metrics and tutorials for evaluating explainable methods. The toolkit has been thoroughly tested and is available under an open-source license on PyPi (or on https://github.com/understandable-machine-intelligence-lab/Quantus/).

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。

↑