Toward Scalable and Unified Example-Based Explanation and Outlier Detection

When neural networks are employed for high-stakes decision-making, it is desirable that they provide explanations for their prediction in order for us to understand the features that have contributed to the decision. At the same time, it is important to flag potential outliers for in-depth verificat...

Description complète

Détails bibliographiques
Publié dans:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 31(2022) vom: 12., Seite 525-540
Auteur principal: Chong, Penny (Auteur)
Autres auteurs: Cheung, Ngai-Man, Elovici, Yuval, Binder, Alexander
Format: Article en ligne
Langue:English
Publié: 2022
Accès à la collection:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Sujets:Journal Article
LEADER 01000caa a22002652c 4500
001 NLM333307070
003 DE-627
005 20250302165300.0
007 cr uuu---uuuuu
008 231225s2022 xx |||||o 00| ||eng c
024 7 |a 10.1109/TIP.2021.3127847  |2 doi 
028 5 2 |a pubmed25n1110.xml 
035 |a (DE-627)NLM333307070 
035 |a (NLM)34793299 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Chong, Penny  |e verfasserin  |4 aut 
245 1 0 |a Toward Scalable and Unified Example-Based Explanation and Outlier Detection 
264 1 |c 2022 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 20.12.2021 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a When neural networks are employed for high-stakes decision-making, it is desirable that they provide explanations for their prediction in order for us to understand the features that have contributed to the decision. At the same time, it is important to flag potential outliers for in-depth verification by domain experts. In this work we propose to unify two differing aspects of explainability with outlier detection. We argue for a broader adoption of prototype-based student networks capable of providing an example-based explanation for their prediction and at the same time identify regions of similarity between the predicted sample and the examples. The examples are real prototypical cases sampled from the training set via a novel iterative prototype replacement algorithm. Furthermore, we propose to use the prototype similarity scores for identifying outliers. We compare performance in terms of the classification, explanation quality and outlier detection of our proposed network with baselines. We show that our prototype-based networks extending beyond similarity kernels deliver meaningful explanations and promising outlier detection results without compromising classification accuracy 
650 4 |a Journal Article 
700 1 |a Cheung, Ngai-Man  |e verfasserin  |4 aut 
700 1 |a Elovici, Yuval  |e verfasserin  |4 aut 
700 1 |a Binder, Alexander  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society  |d 1992  |g 31(2022) vom: 12., Seite 525-540  |w (DE-627)NLM09821456X  |x 1941-0042  |7 nnas 
773 1 8 |g volume:31  |g year:2022  |g day:12  |g pages:525-540 
856 4 0 |u http://dx.doi.org/10.1109/TIP.2021.3127847  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 31  |j 2022  |b 12  |h 525-540