Relative attributing propagation: Interpreting the comparative contributions of individual units in deep neural networks

Woo Jeoung Nam, Shir Gur, Jaesik Choi, Lior Wolf, Seong Whan Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

As Deep Neural Networks (DNNs) have demonstrated superhuman performance in a variety of fields, there is an increasing interest in understanding the complex internal mechanisms of DNNs. In this paper, we propose Relative Attributing Propagation (RAP), which decomposes the output predictions of DNNs with a new perspective of separating the relevant (positive) and irrelevant (negative) attributions according to the relative influence between the layers. The relevance of each neuron is identified with respect to its degree of contribution, separated into positive and negative, while preserving the conservation rule. Considering the relevance assigned to neurons in terms of relative priority, RAP allows each neuron to be assigned with a bi-polar importance score concerning the output: from highly relevant to highly irrelevant. Therefore, our method makes it possible to interpret DNNs with much clearer and attentive visualizations of the separated attributions than the conventional explaining methods. To verify that the attributions propagated by RAP correctly account for each meaning, we utilize the evaluation metrics: (i) Outside-inside relevance ratio, (ii) Segmentation mIOU and (iii) Region perturbation. In all experiments and metrics, we present a sizable gap in comparison to the existing literature.

Original languageEnglish
Title of host publicationAAAI 2020 - 34th AAAI Conference on Artificial Intelligence
PublisherAAAI press
Pages2501-2508
Number of pages8
ISBN (Electronic)9781577358350
Publication statusPublished - 2020
Event34th AAAI Conference on Artificial Intelligence, AAAI 2020 - New York, United States
Duration: 2020 Feb 72020 Feb 12

Publication series

NameAAAI 2020 - 34th AAAI Conference on Artificial Intelligence

Conference

Conference34th AAAI Conference on Artificial Intelligence, AAAI 2020
Country/TerritoryUnited States
CityNew York
Period20/2/720/2/12

ASJC Scopus subject areas

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Relative attributing propagation: Interpreting the comparative contributions of individual units in deep neural networks'. Together they form a unique fingerprint.

Cite this