Blogs (1) >>
ASE 2019
Sun 10 - Fri 15 November 2019 San Diego, California, United States
Thu 14 Nov 2019 11:40 - 12:00 at Cortez 2&3 - Deep Models Chair(s): Nazareno Aguirre

Deep Learning (DL) has recently achieved tremendous success in various application domains. A variety of DL frameworks and platforms play a key role to catalyze such progress. However, the differences in architecture designs and implementations of existing frameworks and platforms bring new challenges for DL software development and deployment. Till now, there is no study on how various mainstream frameworks and platforms influence both DL software development and deployment in practice.

To fill this gap, we take the first step towards understanding how the most widely-used DL frameworks and platforms support the DL software development and deployment. We conduct a systematic study on these frameworks and platforms by using two types of DNN architectures and three popular datasets. (1) For development process, we investigate the prediction accuracy under the same runtime training configuration or same model weights/biases. We also study the adversarial robustness of trained models by leveraging the existing adversarial attack techniques.The experimental results show that the {computing differences} across frameworks could result in an obvious prediction accuracy decline, which should draw the attention of DL developers. (2) For deployment process, we investigate the prediction accuracy and performance (refers to time cost and memory consumption) when the trained models are migrated/quantized from PC to real mobile devices and web browsers. The DL platform study unveils that the migration and quantization still suffer from compatibility and reliability issues. Meanwhile, we find several DL software bugs by using the results as a benchmark. We further validate the results through bug confirmation from stakeholders and industrial positive feedback to highlight the implications of our study. Through our study, we summarize practical guidelines, identify challenges and pinpoint new research directions, such as understanding the characteristics of DL frameworks and platforms, avoiding compatibility/reliability issues, detecting DL software bugs, and reducing time cost and memory consumption towards developing and deploying high quality DL systems effectively.

Thu 14 Nov

Displayed time zone: Tijuana, Baja California change

10:40 - 12:20
Deep ModelsResearch Papers / Demonstrations at Cortez 2&3
Chair(s): Nazareno Aguirre Dept. of Computer Science FCEFQyN, University of Rio Cuarto
10:40
20m
Talk
Wuji: Automatic Online Combat Game Testing Using Evolutionary Deep Reinforcement LearningACM SIGSOFT Distinguished Paper Award
Research Papers
Yan Zheng Tianjin University, Xiaofei Xie Nanyang Technological University, Ting Su ETH Zurich, Lei Ma Kyushu University, Jianye Hao Tianjin University, Zhaopeng Meng Tianjin University, Yang Liu Nanyang Technological University, Singapore, Ruimin Shen Fuxi AI Lab in Netease, Yinfeng Chen Fuxi AI Lab in Netease, Changjie Fan Fuxi AI Lab in Netease
Link to publication Pre-print
11:00
20m
Talk
A Study of Oracle Approximations in Testing Deep Learning Libraries
Research Papers
Mahdi Nejadgholi Concordia University, Jinqiu Yang Concordia University, Montreal, Canada
11:20
20m
Talk
Property Inference for Deep Neural Networks
Research Papers
Divya Gopinath Carnegie Mellon University, Hayes Converse The University of Texas at Austin, Corina S. Pasareanu Carnegie Mellon University Silicon Valley, NASA Ames Research Center, Ankur Taly Google
11:40
20m
Talk
An Empirical Study towards Characterizing Deep Learning Development and Deployment across Different Frameworks and Platforms
Research Papers
Qianyu Guo Tianjin University, Sen Chen Nanyang Technological University, Singapore, Xiaofei Xie Nanyang Technological University, Lei Ma Kyushu University, Qiang Hu Kyushu University, Japan, Hongtao Liu Tianjin University, Yang Liu Nanyang Technological University, Singapore, Jianjun Zhao Kyushu University, Li Xiaohong TianJin University
Pre-print
12:00
10m
Demonstration
DeepMutation++: a Mutation Testing Framework for Deep Learning Systems
Demonstrations
Qiang Hu Kyushu University, Japan, Lei Ma Kyushu University, Xiaofei Xie Nanyang Technological University, Bing Yu Kyushu University, Japan, Yang Liu Nanyang Technological University, Singapore, Jianjun Zhao Kyushu University
12:10
10m
Demonstration
DeepHunter: A Coverage-Guided Fuzzer for Deep Neural Networks
Demonstrations
Xiaofei Xie Nanyang Technological University, Hongxu Chen Nanyang Technological University, Yi Li Nanyang Technological University, Lei Ma Kyushu University, Yang Liu Nanyang Technological University, Singapore, Jianjun Zhao Kyushu University