Modeling Functional Similarity in Source Code With Graph-Based Siamese Networks

Mehrotra, Nikita; Agarwal, Navdha; Gupta, Piyush; Anand, Sandeep; Lo, David; Purandare, Rahul

doi:10.1109/tse.2021.3105556

Cited by 26 publications

(7 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mehrotra et al. [6] use the Soot optimization framework [77] to build program dependence graphs for Java code, followed by the Cytron's method [78] to compute control dependence. Reaching definition [79] and upward exposed analysis [80] are both used for computing data dependence graphs.…”

Section: Main Attributes Analysismentioning

confidence: 99%

“…For example, Ben-Nun et al [48] convert Java code to statements in an Intermediate Representation (IR) using the LLVM Compiler Infrastructure [76], which is then processed to contextual flow graphs. Mehrotra et al [6] use the Soot optimization framework [77] to build program dependence graphs for Java code, followed by the Cytron's method [78] to compute control dependence. Reaching definition [79] and upward exposed analysis [80] are both used for computing data dependence graphs.…”

Section: Code Representation For Different Programming Languagesmentioning

confidence: 99%

“…Machine learning (ML), and nowadays deep learning (DL), is increasingly used by software engineering (SE) researchers and practitioners for a wide range of tasks. Examples include source code classification [1][2][3], code clone detection [4][5][6], bug detection [7][8][9], or code summarisation [10][11][12]. The current interest in DL is enabled by the wide availability of large-scale data (e.g., through open-source systems hosted on platforms, such as GitHub).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A systematic mapping study of source code representation for deep learning in software engineering

et al. 2022

View full text Add to dashboard Cite

The usage of deep learning (DL) approaches for software engineering has attracted much attention, particularly in source code modelling and analysis. However, in order to use DL, source code needs to be formatted to fit the expected input form of DL models. This problem is known as source code representation. Source code can be represented via different approaches, most importantly, the tree-based, token-based, and graph-based approaches. We use a systematic mapping study to investigate i detail the representation approaches adopted in 103 studies that use DL in the context of software engineering. Thus, studies are collected from 2014 to 2021 from 14 different journals and 27 conferences. We show that each way of representing source code can provide a different, yet orthogonal view of the same source code. Thus, different software engineering tasks might require different (combinations of) code representation approaches, depending on the nature and complexity of the task. Particularly, we show that it is crucial to define whether the DL approach requires lexical, syntactical, or semantic code information. Our analysis shows that a wide range of different representations and combinations of representations (hybrid representations) are used to solve a wide range of common software engineering problems. However, we also observe that current research does not generally attempt to transfer existing representations or models to other studies even though there are other contexts in which these representations and models may also be useful. We believe that there is potential for more reuse and the application of transfer learning when applying DL to software engineering tasks.

show abstract

Section: Main Attributes Analysismentioning

confidence: 99%

Section: Code Representation For Different Programming Languagesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A systematic mapping study of source code representation for deep learning in software engineering

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Machine Learning for Program Analysis. Machine learning has been shown to be extremely promising in analyzing both source code and executables [3,24,62,74] in tasks like type inference [36,38,56,61,64,70,94], code completion [10,17,44], program synthesis and generation [79,89], program repair and fix [2,26,42,80,90,99], code summarization [14,21,75,84], general code representation [13,40,50,52,91], bug/vulnerability detection [23,47,63,73,87], code clone detection and search [14,32,33,43,54,66], code translation [72], comment suggestion [41,51], and reverse engineering tasks [7,9,…”

Section: Related Workmentioning

confidence: 99%

NeuDep: Neural Binary Memory Dependence Analysis

Pei,

She,

Wang

et al. 2022

Preprint

View full text Add to dashboard Cite

Determining whether multiple instructions can access the same memory location is a critical task in binary analysis. It is challenging as statically computing precise alias information is undecidable in theory. The problem aggravates at the binary level due to the presence of compiler optimizations and the absence of symbols and types. Existing approaches either produce significant spurious dependencies due to conservative analysis or scale poorly to complex binaries.We present a new machine-learning-based approach to predict memory dependencies by exploiting the model's learned knowledge about how binary programs execute. Our approach features (i) a self-supervised procedure that pretrains a neural net to reason over binary code and its dynamic value flows through memory addresses, followed by (ii) supervised finetuning to infer the memory dependencies statically. To facilitate efficient learning, we develop dedicated neural architectures to encode the heterogeneous inputs (i.e., code, data values, and memory addresses from traces) with specific modules and fuse them with a composition learning strategy.We implement our approach in NEUDEP and evaluate it on 41 popular software projects compiled by 2 compilers, 4 optimizations, and 4 obfuscation passes. We demonstrate that NEUDEP is more precise (1.5×) and faster (3.5×) than the current state-of-the-art. Extensive probing studies on security-critical reverse engineering tasks suggest that NEUDEP understands memory access patterns, learns function signatures, and is able to match indirect calls. All these tasks either assist or benefit from inferring memory dependencies. Notably, NEUDEP also outperforms the current state-of-the-art on these tasks.

show abstract

“…ASTs are typically characterised by multi-node, multi-level and multi-nested structures. Previous source code representations [31,32] have demonstrated that GNNs can better encode the local structure of ASTs [33]. However, it is difficult for GNNs to effectively model the long-range dependencies (i.e., global relationships) between nodes of a deep AST.…”

Section: Introductionmentioning

confidence: 99%

HELoC: Hierarchical Contrastive Learning of Source Code Representation

Wang¹,

Wu²,

Zhang³

et al. 2022

Preprint

View full text Add to dashboard Cite

syntax trees (ASTs) play a crucial role in source code representation. However, due to the large number of nodes in an AST and the typically deep AST hierarchy, it is challenging to learn the hierarchical structure of an AST effectively. In this paper, we propose HELoC, a hierarchical contrastive learning model for source code representation. To effectively learn the AST hierarchy, we use contrastive learning to allow the network to predict the AST node level and learn the hierarchical relationships between nodes in a self-supervised manner, which makes the representation vectors of nodes with greater differences in AST levels farther apart in the embedding space. By using such vectors, the structural similarities between code snippets can be measured more precisely. In the learning process, a novel GNN (called Residual Self-attention Graph Neural Network, RSGNN) is designed, which enables HELoC to focus on embedding the local structure of an AST while capturing its overall structure. HELoC is self-supervised and can be applied to many source code related downstream tasks such as code classification, code clone detection, and code clustering after pre-training. Our extensive experiments demonstrate that HELoC outperforms the state-of-the-art source code representation models. CCS CONCEPTS• Software and its engineering → Software maintenance tools.

show abstract

Modeling Functional Similarity in Source Code With Graph-Based Siamese Networks

Cited by 26 publications

References 68 publications

A systematic mapping study of source code representation for deep learning in software engineering

A systematic mapping study of source code representation for deep learning in software engineering

NeuDep: Neural Binary Memory Dependence Analysis

HELoC: Hierarchical Contrastive Learning of Source Code Representation

Contact Info

Product

Resources

About