An empirical study of fault localisation techniques for deep neural networks
Informazioni aggiuntive
Autori
Tipo
Articolo pubblicato in rivista scientifica
Anno
2025
Lingua
Inglese
Sommario
With the increased popularity of Deep Neural Networks (DNNs), increases also the need for tools to assist developers in the DNN implementation, testing and debugging process. Several approaches have been proposed that automatically analyse and localise potential faults in DNNs under test. In this work, we evaluate and compare existing state-of-the-art fault localisation techniques, which operate based on both dynamic and static analysis of the DNN. The evaluation is performed on a benchmark consisting of both real faults obtained from bug reporting platforms and faulty models produced by a mutation tool. Our findings indicate that the usage of a single, specific ground truth (e.g. the human-defined one) for the evaluation of DNN fault localisation tools results in pretty low performance (maximum average recall of 0.33 and precision of 0.21). However, such figures increase when considering alternative, equivalent patches that exist for a given faulty DNN. The results indicate that DeepFD is the most effective tool, achieving an average recall of 0.55 and a precision of 0.37 on our benchmark.
Parole chiave
Deep learning, Real faults, Fault localisation
Periodico
Empirical Software Engineering
Volume
30
Numero ( Mese )
5
Pagine (o numero dell’articolo)
124
ISSN
1382-3256, 1573-7616
Diffusione
Licenza
CC BY
Visibilità
Pubblico
Status open access
Hybrid
