Applying Product Line Engineering Concepts to Deep Neural Networks

Javad Ghofrani, Ehsan Kozegar, Anna Lena Fehlhaber, Mohammad Divband Soorati


Deep Neural Networks (DNNs) are increasingly being used as a machine learning solution thanks to the complexity of their architecture and hyperparameters-weights. A drawback is the excessive demand for massive computational power during the training process. Not only as a whole but parts of neural networks can also be in charge of certain functionalities. We present a novel challenge in an intersection between machine learning and variability management communities to reuse modules of DNNs without further training. Let us assume that we are given a DNN for image processing that recognizes cats and dogs. By extracting a part of the network, without additional training a new DNN should be divisible with the functionality of recognizing only cats. Existing research in variability management can offer a foundation for a product line of DNNs composing the reusable functionalities. An ideal solution can be evaluated based on its speed, granularity of determined functionalities, and the support for adding variability to the network. The challenge is decomposed in three subchallenges: feature extraction, feature abstraction, and the implementation of a product line of DNNs.

Original languageEnglish
Title of host publicationSPLC '19: Proceedings of the 23rd International Systems and Software Product Line Conference
Editorshorsten Berger, Philippe Collet, Laurence Duchien, Thomas Fogdal, Patrick Heymans, Timo Kehrer, Jabier Martinez, Raúl Mazo, Leticia Montalvillo, Camille Salinesi, Xhevahire Tërnava, Thomas Thüm, Tewfik Ziadi
Number of pages6
Publication date09.09.2019
ISBN (Print)978-145037138-4
Publication statusPublished - 09.09.2019
Event23rd International Systems and Software Product Line Conference - Paris, France
Duration: 09.09.201913.09.2019
Conference number: 154713


Dive into the research topics of 'Applying Product Line Engineering Concepts to Deep Neural Networks'. Together they form a unique fingerprint.

Cite this