• Home
  • Search
  • Improving Automated Program Repair with Domain Adaptation
  • Open Access IconOpen Access
  • Cite Icon14
  • https://doi.org/10.1145/3631972Copy DOI Icon

Improving Automated Program Repair with Domain Adaptation

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Automated Program Repair (APR) is defined as the process of fixing a bug/defect in the source code, by an automated tool. APR tools have recently experienced promising results by leveraging state-of-the-art Neural Language Processing (NLP) techniques. APR tools such as TFix and CodeXGLUE that combine text-to-text transformers with software-specific techniques are outperforming alternatives, these days. However, in most APR studies, the train and test sets are chosen from the same set of projects (i.e., when APR fixes a bug in the test set from project A, the model has already seen example fixed bugs from project A in the training set). In the real world, however, APR models are meant to be generalizable to new and different projects. Therefore, there is a potential threat that reported APR models with high effectiveness perform poorly when the characteristics of the new project or its bugs are different than the training set’s (“Domain Shift”). In this study, we first define the problem of domain shift in automated program repair. Next, we measure the potential damage of domain shift on two recent APR models (TFix and CodeXGLUE). Based on this observation, we then propose a domain adaptation framework that can adapt an APR model for a given target project. We conduct an empirical study with three domain adaptation methods FullFineTuning , TuningWithLightWeightAdapterLayers , and CurriculumLearning and two APR models on 2,672 bugs from 12 projects. The results show that our proposed framework on average can improve the effectiveness of TFix by 13.05% and CodeXGLUE by 48.78%, in terms of “Exact Match”. Through experiments, we also show that the framework provides high efficiency and reliability (in terms of “Exposure Bias”). Using synthetic data to domain adapt TFix and CodeXGLUE on the projects with no data (Zero-shot learning), also results in an average improvement of 5.76% and 17.62% for TFix and CodeXGLUE, respectively.

Similar Papers
  • Research Article
  • Citations12

Evaluating the usage of fault localization in automated program repair: an empirical study

  • Sep 29, 2020
  • Frontiers of Computer Science
  • Deheng Yang +3
  • Research Article
  • Citations54

Fault localization for automated program repair: effectiveness, performance, repair correctness

  • Mar 26, 2016
  • Software Quality Journal
  • Fatmah Yousef Assiri +1
  • Research Article
  • Citations12

Restore: Retrospective Fault Localization Enhancing Automated Program Repair

  • Apr 02, 2020
  • IEEE Transactions on Software Engineering
  • Tongtong Xu +5
  • Conference Article

The Inversive Relationship Between Bugs and Patches: An Empirical Study

  • Apr 01, 2023
  • Jinhan Kim +2
  • Research Article
  • Citations3

An analysis of the suitability of test-based patch acceptance criteria

  • May 20, 2017
  • Luciano Zemín +7
  • Conference Article
  • Citations8

Understanding the Non-Repairability Factors of Automated Program Repair Techniques

  • Dec 01, 2020
  • Bo Lin +6
  • Research Article

Prediction model and scoring system for in-hospital mortality risk in infants with heart failure aged 1-36 months: A retrospective case-control study.

  • Feb 01, 2025
  • Heliyon
  • Meng Wei +5
  • Research Article
  • Citations324

Does Rational Selection of Training and Test Sets Improve the Outcome of QSAR Modeling?

  • Oct 03, 2012
  • Journal of Chemical Information and Modeling
  • Todd M Martin +6
  • Conference Article
  • Citations8

Blurred image recognition using domain adaptation

  • Sep 01, 2015
  • Xiaokang Xie +4
  • Research Article
  • Citations25

Random forest estimation of genomic breeding values for disease susceptibility over different disease incidences and genomic architectures in simulated cow calibration groups

  • Jun 22, 2016
  • Journal of Dairy Science
  • S Naderi +2
  • Research Article

Early warning method for invasive mechanical ventilation in septic patients based on machine learning model

  • Jul 01, 2025
  • Zhonghua wei zhong bing ji jiu yi xue
  • Wanjun Liu +7
  • Research Article
  • Citations26

The prognostic value of the lymphocyte-to-monocyte ratio for high-risk papillary thyroid carcinoma.

  • Sep 01, 2019
  • Cancer Management and Research
  • Linlin Song +5
  • Dissertation
  • Citations1

Domain adaptation and generalization for visual recognition

  • Jan 01, 2017
  • Li Niu
  • PDF
  • Research Article
  • Citations38

Radiomics features of hippocampal regions in magnetic resonance imaging can differentiate medial temporal lobe epilepsy patients from healthy controls

  • Nov 11, 2020
  • Scientific Reports
  • Yae Won Park +10
  • Research Article
  • Citations37

Validation of a methylated DNA marker panel for the nonendoscopic detection of Barrett’s esophagus in a multisite case-control study

  • Apr 20, 2021
  • Gastrointestinal Endoscopy
  • Prasad G Iyer +13
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.