Tue 6 Nov 2018 14:37 - 15:00 at Horizons 6-9F - Deep Learning Chair(s): David Rosenblum

Artificial intelligence models are becoming an integral part of modern computing systems. Just like software inevitably has bugs, models have bugs too, leading to poor classification/prediction accuracy. Unlike software bugs, model bugs cannot be easily fixed by directly modifying models. Existing solutions work by providing additional training inputs. However, they have limited effectiveness due to the lack of understanding of model misbehaviors and hence the incapability of selecting proper inputs. Inspired by software debugging, we propose a novel model debugging technique that works by first conducting model state differential analysis to identify the internal features of the model that are responsible for model bugs and then performing training input selection that is similar to program input selection in regression testing. Our evaluation results on 29 different models for 6 different applications show that our technique can fix model bugs effectively and efficiently without introducing new bugs. For simple applications (e.g., digit recognition), MODE improves the test accuracy from 75% to 93% on average whereas the state-of-the-art can only improve to 85% with 11 times more training time. For complex applications and models (e.g., object recognition), MODE is able to improve the accuracy from 75% to over 91% in minutes to a few hours, whereas state-of-the-art fails to fix the bug or even degrades the test accuracy.

Tue 6 Nov
Times are displayed in time zone: (GMT-05:00) Guadalajara, Mexico City, Monterrey change

13:30 - 15:00: Research Papers - Deep Learning at Horizons 6-9F
Chair(s): David RosenblumNational University of Singapore
fse-2018-research-papers13:30 - 13:52
Vincent HellendoornUniversity of California at Davis, USA, Christian BirdMicrosoft Research, Earl T. Barr, Miltiadis AllamanisMicrosoft Research, Cambridge
fse-2018-research-papers13:52 - 14:15
Gang Zhao, Jeff HuangTexas A&M University
fse-2018-research-papers14:15 - 14:37
Jordan HenkelUniversity of Wisconsin–Madison, Shuvendu K. LahiriMicrosoft Research, Ben LiblitUniversity of Wisconsin–Madison, Thomas RepsUniversity of Wisconsin - Madison and GrammaTech, Inc.
fse-2018-research-papers14:37 - 15:00
Shiqing MaPurdue University, USA, Yingqi LiuPurdue University, USA, Wen-Chuan LeePurdue University, Xiangyu ZhangPurdue University, Ananth GramaPurdue University, USA