ICPC 2023
Mon 15 - Tue 16 May 2023 Melbourne, Australia
co-located with ICSE 2023
The generalizability of Deep Learning (DL) models is a significant challenge, as poor generalizability indicates that the model has overfitted to the training data and is not able to generalize to new data. Despite numerous DL-based clone detectors emerging in recent years, their generalizability has not been thoroughly assessed. This study investigates the generalizability of three DL-based clone detectors (CCLearner, ASTNN, and CodeBERT) by comparing their detection accuracy on different training and testing datasets. The results show that all three clone detectors do not generalize well to new data and there is a strong relationship between clone types and generalizability for CCLearner and ASTNN.

Tue 16 May

Displayed time zone: Hobart change

09:00 - 10:30
Keynote / Code AnalysisDiscussion / Tool Demonstration / Research / Early Research Achievements (ERA) / ICPC Keynotes at Meeting Room 106
Chair(s): Christoph Treude University of Melbourne, Nicolás Cardozo Universidad de los Andes, Raula Gaikovina Kula Nara Institute of Science and Technology, Chaiyong Rakhitwetsagul Mahidol University, Thailand
09:00
45m
Keynote
Kobi Leins: Guidance on more than just standing upright to create safe models, software and use of data
ICPC Keynotes

09:45
9m
Full-paper
Implant Global and Local Hierarchy Information to Sequence based Code Representation Models
Research
Kechi Zhang Peking University, China, Zhuo Li , Zhi Jin Peking University, Ge Li Peking University
Pre-print
09:54
9m
Full-paper
Pathways to Leverage Transcompiler based Data Augmentation for Cross-Language Clone Detection
Research
Subroto Nag Pinku University of Saskatchewan, Debajyoti Mondal University of Saskatchewan, Chanchal K. Roy University of Saskatchewan
Pre-print
10:03
5m
Short-paper
Investigating the Generalizability of Deep Learning-based Clone Detectors
Early Research Achievements (ERA)
Eunjong Choi Kyoto Institute of Technology, Norihiro Fuke Osaka University, Yuji Fujiwara Osaka University, Norihiro Yoshida Ritsumeikan University, Katsuro Inoue Nanzan University
10:08
5m
Short-paper
UnityLint: A Bad Smell Detector for Unity
Tool Demonstration
Matteo Bosco University of Sannio, Italy, Pasquale Cavoto University of Sannio, Italy, Augusto Ungolo University of Sannio, Italy, Biruk Asmare Muse Polytechnique Montréal, Foutse Khomh Polytechnique Montréal, Vittoria Nardone , Massimiliano Di Penta University of Sannio, Italy
Pre-print
10:13
17m
Panel
Discussion 5
Discussion