Flow2Vec: Value-flow-based precise code embedding

Sui, Y; Cheng, X; Zhang, G; Wang, H

Flow2Vec: Value-flow-based precise code embedding

Sui, Y

Cheng, X Zhang, G Wang, H

Permalink

Publisher:: Association for Computing Machinery (ACM)
Publication Type:: Journal Article
Citation:: Proceedings of the ACM on Programming Languages, 2020, 4, (OOPSLA), pp. 1-27
Issue Date:: 2020-11-13

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Published versionAdobe PDF (2.64 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Sui, Y https://orcid.org/0000-0002-9510-6574
dc.contributor.author	Cheng, X
dc.contributor.author	Zhang, G
dc.contributor.author	Wang, H
dc.date.accessioned	2021-01-27T23:30:36Z
dc.date.available	2021-01-27T23:30:36Z
dc.date.issued	2020-11-13
dc.identifier.citation	Proceedings of the ACM on Programming Languages, 2020, 4, (OOPSLA), pp. 1-27
dc.identifier.issn	2475-1421
dc.identifier.issn	2475-1421
dc.identifier.uri	http://hdl.handle.net/10453/145609
dc.description.abstract	© 2020 Owner/Author. Code embedding, as an emerging paradigm for source code analysis, has attracted much attention over the past few years. It aims to represent code semantics through distributed vector representations, which can be used to support a variety of program analysis tasks (e.g., code summarization and semantic labeling). However, existing code embedding approaches are intraprocedural, alias-unaware and ignoring the asymmetric transitivity of directed graphs abstracted from source code, thus they are still ineffective in preserving the structural information of code. This paper presents Flow2Vec, a new code embedding approach that precisely preserves interprocedural program dependence (a.k.a value-flows). By approximating the high-order proximity, i.e., the asymmetric transitivity of value-flows, Flow2Vec embeds control-flows and alias-aware data-flows of a program in a low-dimensional vector space. Our value-flow embedding is formulated as matrix multiplication to preserve context-sensitive transitivity through CFL reachability by filtering out infeasible value-flow paths. We have evaluated Flow2Vec using 32 popular open-source projects. Results from our experiments show that Flow2Vec successfully boosts the performance of two recent code embedding approaches codevec and codeseq for two client applications, i.e., code classification and code summarization. For code classification, Flow2Vec improves codevec with an average increase of 21.2%, 20.1% and 20.7% in precision, recall and F1, respectively. For code summarization, Flow2Vec outperforms codeseq by an average of 13.2%, 18.8% and 16.0% in precision, recall and F1, respectively.
dc.language	en
dc.publisher	Association for Computing Machinery (ACM)
dc.relation	http://purl.org/au-research/grants/arc/DP200101328
dc.relation.ispartof	Proceedings of the ACM on Programming Languages
dc.relation.isbasedon	10.1145/3428301
dc.rights	info:eu-repo/semantics/openAccess
dc.title	Flow2Vec: Value-flow-based precise code embedding
dc.type	Journal Article
utslib.citation.volume	4
utslib.for	0803 Computer Software
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - AAII - Australian Artificial Intelligence Institute
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
pubs.organisational-group	/University of Technology Sydney
utslib.copyright.status	open_access	*
dc.date.updated	2021-01-27T23:29:36Z
pubs.issue	OOPSLA
pubs.publication-status	Published
pubs.volume	4
utslib.citation.issue	OOPSLA

Abstract:

© 2020 Owner/Author. Code embedding, as an emerging paradigm for source code analysis, has attracted much attention over the past few years. It aims to represent code semantics through distributed vector representations, which can be used to support a variety of program analysis tasks (e.g., code summarization and semantic labeling). However, existing code embedding approaches are intraprocedural, alias-unaware and ignoring the asymmetric transitivity of directed graphs abstracted from source code, thus they are still ineffective in preserving the structural information of code. This paper presents Flow2Vec, a new code embedding approach that precisely preserves interprocedural program dependence (a.k.a value-flows). By approximating the high-order proximity, i.e., the asymmetric transitivity of value-flows, Flow2Vec embeds control-flows and alias-aware data-flows of a program in a low-dimensional vector space. Our value-flow embedding is formulated as matrix multiplication to preserve context-sensitive transitivity through CFL reachability by filtering out infeasible value-flow paths. We have evaluated Flow2Vec using 32 popular open-source projects. Results from our experiments show that Flow2Vec successfully boosts the performance of two recent code embedding approaches codevec and codeseq for two client applications, i.e., code classification and code summarization. For code classification, Flow2Vec improves codevec with an average increase of 21.2%, 20.1% and 20.7% in precision, recall and F1, respectively. For code summarization, Flow2Vec outperforms codeseq by an average of 13.2%, 18.8% and 16.0% in precision, recall and F1, respectively.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/145609