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 2206.05075cs.LGcs.AI
收藏

具有生成模型的同构反事实

Diffeomorphic Counterfactuals with Generative Models

Berlin Institute of Technology (TU Berlin)(柏林工业大学);Korea University(高丽大学);Max Planck Institut für Informatik(马克斯·普朗克信息学研究所);Google Research(谷歌研究院)

Ann-Kathrin Dombrowski, Jan E. Gerken, Klaus-Robert Müller, Pan Kessel

摘要:

反事实可以以人类可解释的方式解释神经网络的分类决策。我们提出了一个简单而有效的方法来产生这样的反事实。更具体地说,我们执行一个合适的同构坐标变换,然后在这些坐标中执行梯度上升,以找到被归类为一个指定的目标类具有很大的信心的反事实。我们提出了两种方法来利用生成模型来构建这样合适的坐标系,无论是精确的或近似的同构。我们从理论上分析的生成过程中使用黎曼微分几何和验证质量的生成的反事实使用各种定性和定量的措施。

英文摘要:

Counterfactuals can explain classification decisions of neural networks in a human interpretable way. We propose a simple but effective method to generate such counterfactuals. More specifically, we perform a suitable diffeomorphic coordinate transformation and then perform gradient ascent in these coordinates to find counterfactuals which are classified with great confidence as a specified target class. We propose two methods to leverage generative models to construct such suitable coordinate systems that are either exactly or approximately diffeomorphic. We analyze the generation process theoretically using Riemannian differential geometry and validate the quality of the generated counterfactuals using various qualitative and quantitative measures.

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。

↑