arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.08641cs.LG
收藏

两全其美:用人类可理解的概念进行本地和全球解释

Best of both worlds: local and global explanations with human-understandable concepts

Google Research(谷歌研究院);Google Health(谷歌健康);DeepMind(深度思维)

Jessica Schrouff, Sebastien Baur, Shaobo Hou, Diana Mincu, Eric Loreaux, Ralph Blanes, James Wexler, Alan Karthikesalingam, Been Kim

摘要:

可解释性技术旨在提供模型决策背后的基本原理,通常通过解释个体预测(局部解释,例如“为什么这个患者被诊断患有这种疾病”)或一类预测(全局解释,例如“为什么这组患者通常被诊断患有这种疾病”)。虽然有许多方法专注于其中之一,但很少有框架能够以一致的方式提供局部和全局解释。在这项工作中,我们结合了两个强大的现有技术,一个本地(集成代理,IG)和一个全球(测试与概念激活矢量),提供本地和全球的概念为基础的解释。我们首先使用两个具有已知基础事实的合成数据集来检查我们的想法,并进一步使用基准自然图像数据集进行演示。我们使用各种概念,目标类,模型架构和IG参数(例如基线)来测试我们的方法。我们表明,我们的方法提高了全球的解释香草TCAV相比,地面真理,并提供了有用的本地见解。最后,用户研究表明,该方法的有用性相比,没有或全球的解释。我们希望我们的工作为在许多现有的本地和全球方法之间建立桥梁提供了一个步骤,以获得两个世界的最佳效果。

英文摘要:

Interpretability techniques aim to provide the rationale behind a model's decision, typically by explaining either an individual prediction (local explanation, e.g. 'why is this patient diagnosed with this condition') or a class of predictions (global explanation, e.g. 'why is this set of patients diagnosed with this condition in general'). While there are many methods focused on either one, few frameworks can provide both local and global explanations in a consistent manner. In this work, we combine two powerful existing techniques, one local (Integrated Gradients, IG) and one global (Testing with Concept Activation Vectors), to provide local and global concept-based explanations. We first sanity check our idea using two synthetic datasets with a known ground truth, and further demonstrate with a benchmark natural image dataset. We test our method with various concepts, target classes, model architectures and IG parameters (e.g. baselines). We show that our method improves global explanations over vanilla TCAV when compared to ground truth, and provides useful local insights. Finally, a user study demonstrates the usefulness of the method compared to no or global explanations only. We hope our work provides a step towards building bridges between many existing local and global methods to get the best of both worlds.

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。

↑