From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation
Nature Machine Intelligence (year 2023, volume 5, pages 1006-1019) 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 i...
Saved in:
Main Authors | , , , , , , |
---|---|
Format | Journal Article |
Language | English |
Published |
07.06.2022
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Nature Machine Intelligence (year 2023, volume 5, pages 1006-1019) 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. |
---|---|
DOI: | 10.48550/arxiv.2206.03208 |