Testing Machine Learning Code using Polyhedral Region
To date, although machine learning has been successful in various practical applications, generic methods of testing machine learning code have not been established yet. Here we present a new approach to test machine learning code using the possible input region obtained as a \emph{polyhedron}. If an ML system generates different output for multiple input in the polyhedron, it is ensured that there exists a bug in the code. This property is known as one of theoretical fundamentals in statistical inference, for example, sparse regression models such as the lasso, and a wide range of machine learning algorithms satisfy this polyhedral condition, to which our testing procedure can be applied. We empirically show that the existence of bugs in lasso code can be effectively detected by our method in the \emph{mutation testing} framework.
Thu 12 NovDisplayed time zone: (UTC) Coordinated Universal Time change
08:00 - 08:30 | ML Testing 2Journal First / Paper Presentations / Research Papers / Tool Demos / Visions and Reflections at Virtual room 2 | ||
08:00 2mTalk | DeepSearch: A Simple and Effective Blackbox Attack for Deep Neural Networks Research Papers DOI | ||
08:03 1mTalk | Machine Learning Based Test Data Generation for Safety-critical Software Paper Presentations Ján Čegiň Faculty of Informatics and Information Technologies Slovak Technical University | ||
08:05 1mTalk | Machine Learning Testing: Survey, Landscapes and Horizons Journal First Jie M. Zhang University College London, UK, Mark Harman University College London, UK, Lei Ma Kyushu University, Yang Liu Nanyang Technological University, Singapore | ||
08:07 1mTalk | Machine Translation Testing via Pathological Invariance Research Papers Shashij Gupta IIT Bombay, India, Pinjia He ETH Zurich, Switzerland, Clara Meister ETH Zurich, Switzerland, Zhendong Su ETH Zurich DOI | ||
08:09 1mTalk | Model-Based Exploration of the Frontier of Behaviours for Deep Learning System Testing Research Papers DOI | ||
08:11 1mTalk | PRODeep: A Platform for Robustness Verification of Deep Neural Networks Tool Demos Renjue Li Institute of Software at Chinese Academy of Sciences, China, Jianlin Li Institute of Software at Chinese Academy of Sciences, China, Cheng-Chao Huang Institute of Intelligent Software, China, Pengfei Yang Institute of Software at Chinese Academy of Sciences, China, Xiaowei Huang University of Liverpool, Lijun Zhang Institute of Software, Chinese Academy of Sciences, Bai Xue Institute of Software at Chinese Academy of Sciences, China, Holger Hermanns Saarland University DOI | ||
08:13 1mTalk | Testing Machine Learning Code using Polyhedral Region Visions and Reflections Md Sohel Ahmed National Institute of Informatics, Japan, Fuyuki Ishikawa National Institute of Informatics, Mahito Sugiyama National Institute of Informatics, Japan DOI | ||
08:15 15mTalk | Conversations on ML Testing 2 Paper Presentations Fuyuan Zhang MPI-SWS, Germany, Ján Čegiň Faculty of Informatics and Information Technologies Slovak Technical University, Mark Harman University College London, UK, Renjue Li Institute of Software at Chinese Academy of Sciences, China, Shashij Gupta IIT Bombay, India, Vincenzo Riccio USI Lugano, Switzerland, M: Shin Yoo Korea Advanced Institute of Science and Technology | ||