Text

Differentiated Explanation of Deep Neural Networks With Skewed Distributions

Over the last decade, deep neural networks (DNNs) are regarded as black-box methods, and their decisions are criticized for the lack of explainability. Existing attempts based on local explanations offer each input a visual saliency map, where the supporting features that contribute to the decision are emphasized with high relevance scores. In this paper, we improve the saliency map based on differentiated explanations, of which the saliency map not only distinguishes the supporting features from backgrounds but also shows the different degrees of importance of the various parts within the supporting features. To do this, we propose to learn a differentiated relevance estimator called DRE, where a carefully-designed distribution controller is introduced to guide the relevance scores towards right-skewed distributions. DRE can be directly optimized under pure classification losses, enabling higher faithfulness of explanations and avoiding non-trivial hyper-parameter tuning. The experimental results on three real-world datasets demonstrate that our differentiated explanations significantly improve the faithfulness with high explainability. Our code and trained models are available at https://github.com/fuweijie/DRE.

Ketersediaan

Informasi Detail

Judul Seri

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE; Vol.44 No.6 June 2022

No. Panggil

-

Penerbit

: .,

Deskripsi Fisik

p. 2909-2922

Bahasa

English

ISBN/ISSN

-

Klasifikasi

NONE

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

DEEP NEURAL NETWORKS
LOCAL EXPLANATION
RELEVANCE SCORES
DIFFERENTIATED SALIENCY MAPS

Info Detail Spesifik

10.1109/TPAMI.2021.3049784

Pernyataan Tanggungjawab

Weijie Fu, Meng Wang, Mengnan Du, Ninghao Liu, Shijie Hao, Xia Hu

Versi lain/terkait

Lampiran Berkas

Komentar