From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Achtibat, Reduan, Dreyer, Maximilian, Eisenbraun, Ilona, Bosse, Sebastian, Wiegand, Thomas, Samek, Wojciech, Lapuschkin, Sebastian
Format: Preprint
Veröffentlicht: 2022
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913187276783616
author Achtibat, Reduan
Dreyer, Maximilian
Eisenbraun, Ilona
Bosse, Sebastian
Wiegand, Thomas
Samek, Wojciech
Lapuschkin, Sebastian
author_facet Achtibat, Reduan
Dreyer, Maximilian
Eisenbraun, Ilona
Bosse, Sebastian
Wiegand, Thomas
Samek, Wojciech
Lapuschkin, Sebastian
contents The field of eXplainable Artificial Intelligence (XAI) aims to bring transparency to today's powerful but opaque deep learning models. While local XAI methods explain individual predictions in form of attribution maps, thereby identifying where important features occur (but not providing information about what they represent), global explanation techniques visualize what concepts a model has generally learned to encode. Both types of methods thus only provide partial insights and leave the burden of interpreting the model's reasoning to the user. In this work we introduce the Concept Relevance Propagation (CRP) approach, which combines the local and global perspectives and thus allows answering both the "where" and "what" questions for individual predictions. We demonstrate the capability of our method in various settings, showcasing that CRP leads to more human interpretable explanations and provides deep insights into the model's representation and reasoning through concept atlases, concept composition analyses, and quantitative investigations of concept subspaces and their role in fine-grained decision making.
format Preprint
id arxiv_https___arxiv_org_abs_2206_03208
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation
Achtibat, Reduan
Dreyer, Maximilian
Eisenbraun, Ilona
Bosse, Sebastian
Wiegand, Thomas
Samek, Wojciech
Lapuschkin, Sebastian
Machine Learning
Artificial Intelligence
The field of eXplainable Artificial Intelligence (XAI) aims to bring transparency to today's powerful but opaque deep learning models. While local XAI methods explain individual predictions in form of attribution maps, thereby identifying where important features occur (but not providing information about what they represent), global explanation techniques visualize what concepts a model has generally learned to encode. Both types of methods thus only provide partial insights and leave the burden of interpreting the model's reasoning to the user. In this work we introduce the Concept Relevance Propagation (CRP) approach, which combines the local and global perspectives and thus allows answering both the "where" and "what" questions for individual predictions. We demonstrate the capability of our method in various settings, showcasing that CRP leads to more human interpretable explanations and provides deep insights into the model's representation and reasoning through concept atlases, concept composition analyses, and quantitative investigations of concept subspaces and their role in fine-grained decision making.
title From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2206.03208