Papers
arxiv:2106.13200

Software for Dataset-wide XAI: From Local Explanations to Global Insights with Zennit, CoRelAy, and ViRelAy

Published on Feb 28, 2023
Authors:
,
,
,
,

Abstract

Three software packages—Zennit, CoRelAy, and ViRelAy—offer standardized, reproducible tools for attribution-based exploration and dataset-wide quantitative analysis of deep neural network predictions.

Deep Neural Networks (DNNs) are known to be strong predictors, but their prediction strategies can rarely be understood. With recent advances in Explainable Artificial Intelligence (XAI), approaches are available to explore the reasoning behind those complex models' predictions. Among post-hoc attribution methods, Layer-wise Relevance Propagation (LRP) shows high performance. For deeper quantitative analysis, manual approaches exist, but without the right tools they are unnecessarily labor intensive. In this software paper, we introduce three software packages targeted at scientists to explore model reasoning using attribution approaches and beyond: (1) Zennit - a highly customizable and intuitive attribution framework implementing LRP and related approaches in PyTorch, (2) CoRelAy - a framework to easily and quickly construct quantitative analysis pipelines for dataset-wide analyses of explanations, and (3) ViRelAy - a web-application to interactively explore data, attributions, and analysis results. With this, we provide a standardized implementation solution for XAI, to contribute towards more reproducibility in our field.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2106.13200 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2106.13200 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2106.13200 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.