kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
ITER: Iterative Neural Repair for Multi-Location Patches
Carnegie Mellon University United States.
KTH, School of Electrical Engineering and Computer Science (EECS), Computer Science, Theoretical Computer Science, TCS.ORCID iD: 0000-0003-3505-3383
2024 (English)In: ICSE 2024 - Proceedings of the 46th IEEE/ACM International Conference on Software Engineering, Association for Computing Machinery (ACM) , 2024Conference paper, Published paper (Refereed)
Abstract [en]

Automated program repair (APR) has achieved promising results, especially using neural networks. Yet, the overwhelming majority of patches produced by APR tools are confined to one single location. When looking at the patches produced with neural repair, most of them fail to compile, while a few uncompilable ones go in the right direction. In both cases, the fundamental problem is to ignore the potential of partial patches. In this paper, we propose an iterative program repair paradigm called ITER founded on the concept of improving partial patches until they become plausible and correct. First, ITER iteratively improves partial single-location patches by fixing compilation errors and further refining the previously generated code. Second, ITER iteratively improves partial patches to construct multi-location patches, with fault localization re-execution. ITER is implemented for Java based on battle-proven deep neural networks and code representation. ITER is evaluated on 476 bugs from 10 open-source projects in Defects4J 2.0. ITER succeeds in repairing 15.5% of them, including 9 uniquely repaired multi-location bugs.

Place, publisher, year, edition, pages
Association for Computing Machinery (ACM) , 2024.
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:kth:diva-344024DOI: 10.1145/3597503.3623337Scopus ID: 2-s2.0-85185535944OAI: oai:DiVA.org:kth-344024DiVA, id: diva2:1841394
Conference
46th IEEE/ACM International Conference on Software Engineering, ICSE 2024, Lisbon, Portugal, Apr 14 2024 - Apr 20 2024
Note

Part of proceedings ISBN 9798400702174

QC 20240305

Available from: 2024-02-28 Created: 2024-02-28 Last updated: 2024-03-05Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Monperrus, Martin

Search in DiVA

By author/editor
Monperrus, Martin
By organisation
Theoretical Computer Science, TCS
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 11 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf