The growing application of deep neural networks in safety-critical domains makes the analysis of faults that occur in such systems of enormous importance. In this paper we introduce a large taxonomy of faults in deep learning (DL) systems. We have manually analysed 1059 artefacts gathered from GitHub commits and issues of projects that use the most popular DL frameworks (TensorFlow, Keras and PyTorch) and from related Stack Overflow posts. Structured interviews with 20 researchers and practitioners describing the problems they have encountered in their experience have enriched our taxonomy with a variety of additional faults that did not emerge from the other two sources. Our final taxonomy was validated with a survey involving an additional set of 21 developers, confirming that almost all fault categories (13/15) were experienced by at least 50% of the survey participants.
Tue 7 JulDisplayed time zone: (UTC) Coordinated Universal Time change
08:05 - 09:05 | I5-Deep Learning Testing and DebuggingTechnical Papers / Demonstrations at Goguryeo Chair(s): Pooyan Jamshidi University of South Carolina | ||
08:05 12mTalk | DISSECTOR: Input Validation for Deep Learning Applications by Crossing-layer DissectionTechnical Technical Papers Huiyan Wang State Key Lab. for Novel Software Tech. and Dept. of Comp. Sci. and Tech., Nanjing University, Nanjing, China, Jingwei Xu Nanjing University, Chang Xu Nanjing University, Xiaoxing Ma Nanjing University, Jian Lu Nanjing University | ||
08:17 12mTalk | White-box Fairness Testing through Adversarial Sampling Technical Papers Peixin Zhang Zhejiang University, Jingyi Wang National University of Singapore, Singapore, Jun Sun Singapore Management University, Guoliang Dong Computer College of Zhejiang University, Xinyu Wang Zhejiang University, Xingen Wang Zhejiang University, Jin Song Dong National University of Singapore, Dai Ting Huawei Corporation | ||
08:29 3mTalk | FeatureNET: Diversity-driven Generation of Deep Learning ModelsDemo Demonstrations Salah Ghamizi SntT - University of Luxembourg, Maxime Cordy SnT, University of Luxembourg, Mike Papadakis University of Luxembourg, Yves Le Traon University of Luxembourg | ||
08:32 3mTalk | EvalDNN: A Toolbox for Evaluating Deep Neural Network ModelsDemo Demonstrations Yongqiang TIAN The Hong Kong University of Science and Technology, Zhihua Zeng Zhejiang University, Ming Wen Huazhong University of Science and Technology, China, Yepang Liu Southern University of Science and Technology, Tzu-yang Kuo The Hong Kong University of Science and Technology, Shing-Chi Cheung Department of Computer Science and Engineering, The Hong Kong University of Science and Technology | ||
08:35 12mTalk | Taxonomy of Real Faults in Deep Learning Systems Technical Papers Nargiz Humbatova Università della Svizzera italiana, Gunel Jahangirova Università della Svizzera italiana, Gabriele Bavota Università della Svizzera italiana, Vincenzo Riccio Università della Svizzera italiana, Andrea Stocco Università della Svizzera italiana, Paolo Tonella Università della Svizzera italiana | ||
08:47 12mTalk | An Empirical Study on Program Failures of Deep Learning Jobs Technical Papers Ru Zhang Microsoft Research, Wencong Xiao Alibaba, Hongyu Zhang University of Newcastle, Australia, Yu Liu Microsoft Research, Haoxiang Lin Microsoft Research, Mao Yang Microsoft Research DOI Pre-print | ||