概念发现的稀疏子空间聚类(SSCCD)

Mar, 2022

Sparse Subspace Clustering for Concept Discovery (SSCCD)

Johanna Vielhaben, Stefan Blücher, Nils Strodthoff

TL;DR通过稀疏子空间聚类的方法，探究概念基础解释和概念子空间作为深度学习模型行为的关键组成部分，从而更深入地理解模型行为。

Abstract

Concepts are key building blocks of higher level human understanding. explainable ai (XAI) methods have shown tremendous progress in recent years, however, local attribution methods do not allow to identify coherent mod