More is Not Always Better: Exploring Early Repair of DNNs-Reference-Cited by-同舟云学术

More is Not Always Better: Exploring Early Repair of DNNs

Published:2024-04-20 Issue: Volume: Page:13-16
ISSN:
Container-title:Proceedings of the 5th IEEE/ACM International Workshop on Deep Learning for Testing and Testing for Deep Learning
language:
Short-container-title:

Author:

Mancu Andrei¹^ORCID,Laurent Thomas²^ORCID,Rieger Franz³^ORCID,Arcaini Paolo⁴^ORCID,Ishikawa Fuyuki⁴^ORCID,Rueckert Daniel⁵⁶^ORCID

Affiliation:

1. Technical University of Munich, Munich, Germany

2. JSPS @ National Institute of Informatics, Tokyo, Japan

3. Max Planck Institute for Biological Intelligence and Technical University of Munich, Munich, Germany

4. National Institute of Informatics, Tokyo, Japan

5. Klinikum rechts der Isar, Technical University of Munich, Munich, Germany

6. Department of Computing, Imperial College London, London, United Kingdom

Funder

JST-Mirai Program

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3643786.3648024

Reference21 articles.

1. DeepFD

2. Matias Duran, Xiao-Yi Zhang, Paolo Arcaini, and Fuyuki Ishikawa. 2021. What to Blame? On the Granularity of Fault Localization for Deep Neural Networks. In 2021 IEEE 32nd International Symposium on Software Reliability Engineering (ISSRE). 264--275.

3. Hasan Ferit Eniser, Simos Gerasimou, and Alper Sen. 2019. DeepFault: Fault Localization for Deep Neural Networks. In Fundamental Approaches to Software Engineering. Springer International Publishing, Cham, 171--191.

4. Ali Ghanbari, Deepak-George Thomas, Muhammad Arbab Arshad, and Hridesh Rajan. 2023. Mutation-based Fault Localization of Deep Neural Networks. In 2023 38th IEEE/ACM International Conference on Automated Software Engineering (ASE). 1301--1313.

5. Repairing DNN Architecture: Are We There Yet?