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 2203.06043cs.LGcs.AIstat.ML
收藏

用于概念发现的稀疏子空间聚类算法(SSCCD)

Sparse Subspace Clustering for Concept Discovery (SSCCD)

Fraunhofer Heinrich-Hertz-Institute(弗劳恩霍夫海因里希·赫兹研究所);TU Berlin(柏林工业大学);Oldenburg University(奥尔登堡大学)

Johanna Vielhaben, Stefan Blücher, Nils Strodthoff

摘要:

概念是人类更高层次理解的关键组成部分。近年来,可解释人工智能(XAI)方法取得了巨大的进展,然而,局部归因方法不允许识别跨样本的连贯模型行为,因此错过了这一重要组成部分。在这项工作中,我们研究了基于概念的解释,并提出了一个新的定义概念的低维子空间的隐藏特征层。我们新颖地应用稀疏子空间聚类来发现这些概念子空间。展望未来,我们从概念子空间的本地化输入(概念)地图方面获得见解,展示如何量化概念相关性,最后,评估概念之间的相似性和可转移性。我们经验证明了建议的稀疏子空间聚类概念发现(SSCCD)方法的各种不同的图像分类任务的合理性。这种方法可以更深入地了解实际模型的行为,而这些行为在传统的输入级热图中仍然是隐藏的。

英文摘要:

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 model behavior across samples and therefore miss this essential component. In this work, we study concept-based explanations and put forward a new definition of concepts as low-dimensional subspaces of hidden feature layers. We novelly apply sparse subspace clustering to discover these concept subspaces. Moving forward, we derive insights from concept subspaces in terms of localized input (concept) maps, show how to quantify concept relevances and lastly, evaluate similarities and transferability between concepts. We empirically demonstrate the soundness of the proposed Sparse Subspace Clustering for Concept Discovery (SSCCD) method for a variety of different image classification tasks. This approach allows for deeper insights into the actual model behavior that would remain hidden from conventional input-level heatmaps.

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。

↑