Software Defect Prediction via Attention-Based Recurrent Neural Network

Fan, Guisheng; Diao, Xuyang; Yu, Huiqun; Yang, Kang; Chen, Liqiong

doi:10.1155/2019/6230953

Cited by 86 publications

(67 citation statements)

References 40 publications

(43 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…[ 2 ] assembled a software defect prediction algorithm based on AST based on the deep tree. Fan et al [ 10 ] the attention-based recurrent neural network is applied to the vector encoding structure of the code as a deep learning model. They built the AST code and converted it into a digital vector.…”

Section: Background and Related Workmentioning

confidence: 99%

“…Functions that include these types of structural information and the semantics of defect prediction should improve performance. The rich functions of code semantics and syntactic structure have specific statistical functions, and ASTs [ 10 ] hides these specific statistical functions, which can help locate and analyze faults more accurately.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Attention based GRU-LSTM for software defect prediction

et al. 2021

View full text Add to dashboard Cite

Software defect prediction (SDP) can be used to produce reliable, high-quality software. The current SDP is practiced on program granular components (such as file level, class level, or function level), which cannot accurately predict failures. To solve this problem, we propose a new framework called DP-AGL, which uses attention-based GRU-LSTM for statement-level defect prediction. By using clang to build an abstract syntax tree (AST), we define a set of 32 statement-level metrics. We label each statement, then make a three-dimensional vector and apply it as an automatic learning model, and then use a gated recurrent unit (GRU) with a long short-term memory (LSTM). In addition, the Attention mechanism is used to generate important features and improve accuracy. To verify our experiments, we selected 119,989 C/C++ programs in Code4Bench. The benchmark tests cover various programs and variant sets written by thousands of programmers. As an evaluation standard, compared with the state evaluation method, the recall, precision, accuracy and F1 measurement of our well-trained DP-AGL under normal conditions have increased by 1%, 4%, 5%, and 2% respectively.

show abstract

Section: Background and Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Attention based GRU-LSTM for software defect prediction

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The LSTM network produces a plausible outcome for source code bug detection. Fan et al [30] presented an attention-based RNN for source code defect prediction. F-measure score and the area under the curve (AUC) were used as model evaluation metrics.…”

Section: Background and Literature Reviewmentioning

confidence: 99%

Source Code Assessment and Classification Based on Estimated Error Probability Using Attentive LSTM Language Model and Its Application in Programming Education

2020

View full text Add to dashboard Cite

The rate of software development has increased dramatically. Conventional compilers cannot assess and detect all source code errors. Software may thus contain errors, negatively affecting end-users. It is also difficult to assess and detect source code logic errors using traditional compilers, resulting in software that contains errors. A method that utilizes artificial intelligence for assessing and detecting errors and classifying source code as correct (error-free) or incorrect is thus required. Here, we propose a sequential language model that uses an attention-mechanism-based long short-term memory (LSTM) neural network to assess and classify source code based on the estimated error probability. The attentive mechanism enhances the accuracy of the proposed language model for error assessment and classification. We trained the proposed model using correct source code and then evaluated its performance. The experimental results show that the proposed model has logic and syntax error detection accuracies of 92.2% and 94.8%, respectively, outperforming state-of-the-art models. We also applied the proposed model to the classification of source code with logic and syntax errors. The average precision, recall, and F-measure values for such classification are much better than those of benchmark models. To strengthen the proposed model, we combined the attention mechanism with LSTM to enhance the results of error assessment and detection as well as source code classification. Finally, our proposed model can be effective in programming education and software engineering by improving code writing, debugging, error-correction, and reasoning.

show abstract

“…They also replaced rare tokens with a special token to compact the corpus. Fan et al [29] considered that the hidden features extracted from the AST contain key syntax and semantics, so they employed bidirectional long short-term memory (Bi-LSTM) with attention mechanism to discriminate key syntax and semantics features. They record plain texts for method invocation nodes and extracted the node names as tokens for all the nodes of declarations.…”

Section: B Abstract Syntax Tree In Defect Predictionmentioning

confidence: 99%

A Suitable AST Node Granularity and Multi-Kernel Transfer Convolutional Neural Network for Cross-Project Defect Prediction

Deng

Qiu

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Cross-project defect prediction (CPDP) is a feasible way to perform software defect prediction (SDP) when lacking historical data. Recent CPDP approaches have employed deep learning techniques to better exploit the information from the program's abstract syntax trees (ASTs). However, the granularity of the AST nodes and the data distribution difference between projects may have negative impacts on the prediction performance, which many CPDP studies didn't take into consideration. To handle these issues, this paper explores a better AST node granularity and proposes a CPDP framework based on multi-kernel transfer convolutional neural networks. Specifically, for AST node granularity, we explore the difference of three AST node granularities and then compare the prediction performance of each granularity on several prediction models. For the CPDP framework, we first parse the program source code into ASTs and then encode the AST nodes into numerical vectors using the embedding technique. Secondly, to mine transferable semantic features, the encoded ASTs are fed into a convolutional neural network, in which a multi-kernel matching layer is added to minimize the data distribution divergence between the source and target project. Finally, to make use of the information from the handcrafted features, the semantic features mined from the AST are joint with handcrafted features to form the joint features for CPDP. We evaluate our approach on 110 CPDP tasks formed by 11 open-source projects and results show that the proposed CPDP method outperforms most deep learning-based approaches. INDEX TERMS Abstract syntax tree, cross-project defect prediction, maximum mean discrepancy, multikernel, transfer learning.

show abstract

Software Defect Prediction via Attention-Based Recurrent Neural Network

Cited by 86 publications

References 40 publications

Attention based GRU-LSTM for software defect prediction

Attention based GRU-LSTM for software defect prediction

Source Code Assessment and Classification Based on Estimated Error Probability Using Attentive LSTM Language Model and Its Application in Programming Education

A Suitable AST Node Granularity and Multi-Kernel Transfer Convolutional Neural Network for Cross-Project Defect Prediction

Contact Info

Product

Resources

About