Search events for 'nsf-dl-se-2019'
A Review and Refinement of Surprise Adequacy
deeptest2021 When: Tue 1 Jun 2021 11:00 - 11:20 People: Michael Weiss, Rwiddhi Chakraborty, Paolo Tonella
… Surprise Adequacy (SA) is one of the emerging and most promising adequacy criteria for Deep Learning (DL) testing. As an adequacy criterion, it has been used to assess the strength of DL test suites. In addition, it has also been used …
An Empirical Study on Deployment Faults of Deep Learning Based Mobile Applications
Technical Track When: Fri 28 May 2021 11:30 - 11:50Fri 28 May 2021 23:30 - 23:50 People: Zhenpeng Chen, Huihan Yao, Yiling Lou, Yanbin Cao, Yuanqiang Liu, Haoyu Wang, Xuanzhe Liu
… Deep learning (DL) is finding its way into a growing number of mobile software applications. These software applications, named as DL based mobile applications (abbreviated as \emph{mobile DL apps}) integrate DL models trained using large …
Denchmark: A Bug Benchmark of Deep Learning-related Software
Data Showcase When: Wed 19 May 2021 02:12 - 02:15 People: Misoo Kim, Youngkyoung Kim, Eunseok Lee
… A growing interest in deep learning (DL) has instigated a concomitant rise in DL-related software (DLSW). Therefore, the importance of DLSW quality has emerged … of DL. These studies indicate the necessity of automatic debugging techniques …
Distribution Awareness for AI System Testing
SRC - ACM Student Research Competition When: Tue 25 May 2021 11:30 - 13:30 People: David Berend
… As Deep Learning (DL) is continuously adopted in many safety critical … to the traditional software development process, testing the DL software to uncover its …. Although recent progress has been made in designing novel testing techniques for DL …
Measuring Discrimination to Boost Comparative Testing for Multiple Deep Learning Models
Technical Track When: Tue 25 May 2021 12:05 - 12:25Wed 26 May 2021 00:05 - 00:25 People: Linghan Meng, Yanhui Li, Lin Chen, Zhi Wang, Di Wu, Yuming Zhou, Baowen Xu
… The boom of DL technology leads to massive DL models built and shared, which facilitates the acquisition and reuse of DL models. For a given task, we encounter multiple DL models available with the same functionality, which are considered …
Graph-based Fuzz Testing for Deep Learning Inference Engines
Technical Track When: Wed 26 May 2021 11:20 - 11:40Wed 26 May 2021 23:20 - 23:40 People: Weisi Luo, Xiaoyue Run, Dong Chai, Jiang Wang, Chunrong Fang, Zhenyu Chen
… With the wide use of Deep Learning (DL) systems, academy and industry begin … assurance. However, existing testing techniques focus on the quality of DL models … a graph-based fuzz testing method to improve the quality of DL inference engines …
RobOT: Robustness-Oriented Testing for Deep Learning Systems
Technical Track When: Wed 26 May 2021 11:40 - 12:00Wed 26 - Thu 27 May 2021 People: Jingyi Wang, Jialuo Chen, Youcheng Sun, Xingjun Ma, Dongxia Wang, Jun Sun, Peng Cheng
… engineering techniques for the quality assurance of deep learning (DL) systems … (a.k.a.~bugs) of DL systems are found either by fuzzing or guided search … that the commonly used neuron coverage metrics by existing DL testing approaches …
An Empirical Study on the Usage of BERT Models for Code Completion
Technical Papers When: Tue 18 May 2021 10:09 - 10:13 People: Matteo Ciniselli, Nathan Cooper, Luca Pascarella, Denys Poshyvanyk, Massimiliano Di Penta, Gabriele Bavota
… -of-the-art deep learning (DL) models in supporting code completion at different … usually adopted when assessing DL generative models (i.e., BLEU score …
Studying the Usage of Text-To-Text Transfer Transformer to Support Code-Related Tasks
Technical Track When: Thu 27 May 2021 10:40 - 11:00Thu 27 May 2021 22:40 - 23:00 People: Antonio Mastropaolo, Simone Scalabrino, Nathan Cooper, David Nader Palacio, Denys Poshyvanyk, Rocco Oliveto, Gabriele Bavota
… Deep learning (DL) techniques are gaining more and more attention … used in four previous works that used DL techniques to: (i) fix bugs, (ii … in the four original papers proposing DL-based solutions for those four tasks. We …
What Are We Really Testing in Mutation Testing for Machine Learning? A Critical Reflection
NIER - New Ideas and Emerging Results When: Thu 27 May 2021 12:10 - 12:25Fri 28 May 2021 00:10 - 00:25 People: Annibale Panichella, Cynthia C. S. Liem
… learning (DL) in particular; researchers have proposed approaches, tools, and statistically sound heuristics to determine whether mutants in DL systems are killed … extent currently used mutation testing techniques in DL are actually in line …
An Empirical Study of Refactorings and Technical Debt in Machine Learning Systems
Technical Track When: Tue 25 May 2021 19:55 - 20:15Wed 26 May 2021 07:55 - 08:15 People: Yiming Tang, Raffi Khatchadourian, Mehdi Bagherzadeh, Rhia Singh, Ajani Stewart, Anita Raja
… Machine Learning (ML), including Deep Learning (DL), systems, i.e., those with ML capabilities, are pervasive in today’s data-driven society. Such systems are complex; they are comprised of ML models and many subsystems that support …