Write a Blog >>
Sun 10 - Sat 16 October 2021
Fri 15 Oct 2021 00:20 - 00:40 at Room 1 - Model generation and Search-based engineering Chair(s): Matthias Tichy

The automatic generation of software models is an important element in many software and systems engineering scenarios such as software tool certification, validation of cyber-physical systems, or benchmarking graph databases. Several model generators are nowadays available, but the topic of whether they generate realistic models has been little studied. The state-of-the-art approach to check the realistic property in software models is to rely on simple comparisons using graph metrics and statistics. This generates a bottleneck due to the compression of all the information contained in the model into a small set of metrics. Furthermore, there is a lack of interpretation in these approaches since there are no hints of why the generated models are not realistic. Therefore, in this paper, we tackle the problem of assessing how realistic a generator is by mapping it to a classification problem in which a Graph Neural Network (GNN) will be trained to distinguish between the two sets of models (real and synthetic ones). Then, to assess how realistic a generator is we perform the Classifier Two-Sample Test (C2ST). Our approach allows for interpretation of the results by inspecting the attention layer of the GNN. We use our approach to assess four state-of-the-art model generators applied to three different domains. The results show that none of the generators can be considered realistic.

Fri 15 Oct

Displayed time zone: Osaka, Sapporo, Tokyo change

00:00 - 01:00
Model generation and Search-based engineeringTechnical Papers at Room 1
Chair(s): Matthias Tichy Ulm University, Germany
Automated Generation of Consistent, Diverse and Structurally Realistic Graph ModelsJ1ST
Technical Papers
Oszkár Semeráth Budapest University of Technology and Economics, Aren Babikian McGill University, Boqi Chen McGill University, Chuning Li , Kristóf Marussy Budapest University of Technology and Economics, Gabor Szarnyas , Daniel Varro McGill University / Budapest University of Technology and Economics
Towards the Characterization of Realistic Model Generators using Graph Neural NetworksFT
Technical Papers
Handling nonconforming individuals in Search-Based Model-Driven EngineeringJ1ST
Technical Papers
Jaime Font San Jorge University, Spain, Lorena Arcega San Jorge University, Øystein Haugen Østfold University College, Carlos Cetina San Jorge University, Spain