Program similarity is a fundamental concept, central to the solution of software engineering tasks such as software plagiarism, clone identification, code refactoring and code search.
This film presents a short summary of research results obtained at KTH Royal Insitute of Technology, Stockholm within the ITEA3 Testomat project in using graph neural networks to identify program similarity. The similarity concept used is graph edit distance (GED).
Details of this approach can be found in the paper: A. Nair, A. Roy, K. Meinke. 2020. “funcGNN: A Graph Neural Network Approach to Program Similarity“. In ESEM ’20: ACM / IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM) (ESEM ’20), October 8–9, 2020. ACM, New York, NY, USA, 11 pages. https://arxiv.org/abs/2007.13239