Learning Important Features Through Propagating Activation Differences

Avanti Shrikumar; Peyton Greenside; Anshul Kundaje

doi:https://doi.org/10.48550/arxiv.1704.02685

Learning Important Features Through Propagating Activation Differences

2017 · arXiv (Cornell University) · 2,379 citations · 9 from inside this corpus

Avanti Shrikumar, Peyton Greenside low, Anshul Kundaje

The source holds an abstract for this work, but its best open-access copy is under no open licence, which does not permit us to republish the text. Read it at the source below.

9 of 9 neighbouring works in this corpus. Blue is what this paper cites; orange is what cites it, and a dashed line is one neighbour citing another. Only the largest labels are drawn — every node carries its full title on hover.

this paper works it cites works citing it node size = global citations · hover for the full title

Citation edge evidence

Each row is directed from the citing work to the cited work. Source status remains readable without the interactive graph.

Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challe…→Learning Important Features Through Propagating Activation DifferencesLegacy edge — source detail unavailable
Grad-CAM++: Generalized Gradient-Based Visual Explanations for Deep Convolutional Networks→Learning Important Features Through Propagating Activation DifferencesLegacy edge — source detail unavailable
Explainable AI: A Review of Machine Learning Interpretability Methods→Learning Important Features Through Propagating Activation DifferencesLegacy edge — source detail unavailable
Axiomatic Attribution for Deep Networks→Learning Important Features Through Propagating Activation DifferencesLegacy edge — source detail unavailable
A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI→Learning Important Features Through Propagating Activation DifferencesLegacy edge — source detail unavailable
On the Opportunities and Risks of Foundation Models→Learning Important Features Through Propagating Activation DifferencesLegacy edge — source detail unavailable
TabNet: Attentive Interpretable Tabular Learning→Learning Important Features Through Propagating Activation DifferencesLegacy edge — source detail unavailable
Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications→Learning Important Features Through Propagating Activation DifferencesLegacy edge — source detail unavailable
Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks→Learning Important Features Through Propagating Activation DifferencesLegacy edge — source detail unavailable
A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI→Axiomatic Attribution for Deep NetworksLegacy edge — source detail unavailable
A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI→Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challe…Legacy edge — source detail unavailable
Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challe…→Axiomatic Attribution for Deep NetworksLegacy edge — source detail unavailable
Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks→Axiomatic Attribution for Deep NetworksLegacy edge — source detail unavailable
Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks→Grad-CAM++: Generalized Gradient-Based Visual Explanations for Deep Convolutional NetworksLegacy edge — source detail unavailable
Explainable AI: A Review of Machine Learning Interpretability Methods→Grad-CAM++: Generalized Gradient-Based Visual Explanations for Deep Convolutional NetworksLegacy edge — source detail unavailable
Explainable AI: A Review of Machine Learning Interpretability Methods→Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challe…Legacy edge — source detail unavailable
Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications→Axiomatic Attribution for Deep NetworksLegacy edge — source detail unavailable
TabNet: Attentive Interpretable Tabular Learning→Axiomatic Attribution for Deep NetworksLegacy edge — source detail unavailable
On the Opportunities and Risks of Foundation Models→Axiomatic Attribution for Deep NetworksLegacy edge — source detail unavailable
On the Opportunities and Risks of Foundation Models→Explainable AI: A Review of Machine Learning Interpretability MethodsLegacy edge — source detail unavailable

What cites it, inside the corpus

Paper	Year	Cited
Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challe…	2019	9,796
Grad-CAM++: Generalized Gradient-Based Visual Explanations for Deep Convolutional Networks	2018	3,219
Explainable AI: A Review of Machine Learning Interpretability Methods	2020	2,907
Axiomatic Attribution for Deep Networks	2017	2,650
A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI	2020	2,377
On the Opportunities and Risks of Foundation Models	2021	2,265
TabNet: Attentive Interpretable Tabular Learning	2021	1,700
Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications	2021	1,424
Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks	2020	1,378

Links

Download BibTeX · Download RIS · DOI · Open access copy · OpenAlex record

Topics

Explainable Artificial Intelligence (XAI)	Computer Science
Machine Learning and Data Classification	Computer Science
Machine Learning in Healthcare	Computer Science

Is this record sound?

complete

Nothing in this record contradicts itself and no field we check is missing.

supports3 author record(s) attached.
supports12 reference(s) recorded.
neutralThe DOI carries no year to check against.
supportsA title is present.

Provenance

Everything above was read from one stored OpenAlex payload, fetched 2026-09-04T03:58:49+00:00.

sha256 a2172c1bbe00c44b…