Improving fault localization and program repair with deep semantic features and transferred knowledge

Meng, Xiangxin; Wang, Xu; Zhang, Hongyu; Sun, Hailong; Li, Xudong

doi:10.1145/3510003.3510147

Cited by 32 publications

(7 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, it is flexible to integrate DL techniques into traditional APR techniques instead of developing a brand-new end-to-end patch generator. For example, Meng et al [107] design a multi-classifier to rank the fix templates for TBar. In the future, researchers can boost existing template-based APR techniques (e.g., TBar) via mask prediction.…”

Section: Implication and Discussionmentioning

confidence: 99%

“…In the literature, recurrent [24,48,146,147]. Besides, researchers use long short-term memory (LSTM) architecture to capture the long-distance dependencies among code sequences [20,107]. Recently, as a variant of the Seq2Seq model, Transformer [150] has been considered the state-of-the-art NMT repair architecture due to the self-attention mechanism [25,26,40].…”

Section: Neural Machine Translationmentioning

confidence: 99%

“…Recently, Meng et al . [107] build a novel fault localization technique based on deep semantic features and transferred knowledge, which is further fed to a fix template prioritization model and a template-based APR technique TBar.…”

Section: Localizationmentioning

confidence: 99%

“…Wang et al [107] propose TRANSFER, a fault localization and program repair approach with deep semantic features and transferred knowledge which is obtained by a combination of spectrum-based and mutation-based localization techniques. They build a fault localization and program repair dataset respectively and employ existing fix templates designed by TBar.…”

Section: For Traditional Aprmentioning

confidence: 99%

See 3 more Smart Citations

A Survey of Learning-based Automated Program Repair

Zhang¹,

Fang²,

Ma³

et al. 2023

Preprint

View full text Add to dashboard Cite

Automated program repair (APR) aims to fix software bugs automatically and plays a crucial role in software development and maintenance. With the recent advances in deep learning (DL), an increasing number of APR techniques have been proposed to leverage neural networks to learn bug-fixing patterns from massive opensource code repositories. Such learning-based techniques usually treat APR as a neural machine translation (NMT) task, where buggy code snippets (i.e., source language) are translated into fixed code snippets (i.e., target language) automatically. Benefiting from the powerful capability of DL to learn hidden relationships from previous bug-fixing datasets, learning-based APR techniques have achieved remarkable performance.In this paper, we provide a systematic survey to summarize the current state-of-the-art research in the learning-based APR community. We illustrate the general workflow of learning-based APR techniques and detail the crucial components, including fault localization, patch generation, patch ranking, patch validation, and patch correctness phases. We then discuss the widely-adopted datasets and evaluation metrics and outline existing empirical studies. We discuss several critical aspects of learning-based APR techniques, such as repair domains, industrial deployment, and the open science issue. We highlight several practical guidelines on applying DL techniques for future APR studies, such as exploring explainable patch generation and utilizing code features. Overall, our paper can help researchers gain a comprehensive understanding about the achievements of the existing learning-based APR techniques and promote the practical application of these techniques. Our artifacts are publicly available at https://github.com/QuanjunZhang/AwesomeLearningAPR. CCS Concepts: • Software and its engineering → Software testing and debugging; Software testing and debugging.

show abstract

Section: Implication and Discussionmentioning

confidence: 99%

Section: Neural Machine Translationmentioning

confidence: 99%

Section: Localizationmentioning

confidence: 99%

Section: For Traditional Aprmentioning

confidence: 99%

See 2 more Smart Citations

A Survey of Learning-based Automated Program Repair

Zhang¹,

Fang²,

Ma³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…A common LSTM gate unit is composed of a cell, an input gate, an output gate and a forget gate. Thanks to the gated mechanism, LSTM is well-suited to extract the contextual semantic features containing token sequential dependencies and has been widely used in various kinds of tasks, such as vulnerability detection [33], fault localization [34], and automated program repair [35].…”

Section: Lstm Stackmentioning

confidence: 99%

Boosting Automated Patch Correctness Prediction via Pre-trained Language Model

Zhang¹,

Fang²,

Sun³

et al. 2023

Preprint

View full text Add to dashboard Cite

Automated program repair (APR) aims to fix software bugs automatically without human debugging efforts and plays a crucial role in software development and maintenance. Despite the recent significant progress in the number of fixed bugs, APR is still challenged by a long-standing overfitting problem (i.e., the generated patch is plausible but overfitting). Various techniques have thus been proposed to address the overfitting problem. Among them, leveraging deep learning approaches to predict patch correctness automatically is emerging along with the available large-scale patch benchmarks recently. However, existing learning-based techniques mainly rely on manually-designed code features, which can be extremely costly and challenging to construct in practice. In this paper, we propose APPT, a pre-trained model-based automated patch correctness assessment technique, which treats the source code as a sequence of tokens without extra overhead to design a mass of features from different perspectives. In particular, APPT adopts a pre-trained model as the encoder stack, followed by an LSTM stack and a deep learning classifier. Although our idea is general and can be built on various existing pre-trained models, we have implemented APPT based on the BERT model. We conduct an extensive experiment on 1,183 Defects4J patches and the experimental results show that APPT achieves prediction accuracy of 79.0% and recall of 81.3%, outperforming the state-of-the-art technique CACHE by 3.6% and 4.8%. Our additional investigation on 49,694 real-world patches shows that APPT achieves the optimum performance (exceeding 99% in five common metrics for assessing patch classification techniques) compared with existing representation learning techniques. We also prove that adopting advanced pre-trained models can further provide substantial advancement (e.g., GraphCodeBERT-based APPT improves BERT-based APPT by 3.0% and 2.6% in precision and recall, respectively), highlighting the generalizability of APPT.

show abstract

A Systematic Exploration of Mutation‐Based Fault Localization Formulae

Wang,

Wei,

Chen

et al. 2024

Software Testing Verif & Rel

View full text Add to dashboard Cite

Fault localization (FL) aims to automatically find the location of bugs in a software program. In the family of FL approaches, spectrum‐based fault localization (SBFL) is the most widely used and has been extensively studied, which computes the suspicious scores of a code element to be buggy via test coverage information. Mutation‐based fault localization (MBFL) further analyses the relationship between mutants and test results. Although MBFL involves more information, it also faces the following limitations. (1) To precisely evaluate suspicious sources, SBFL approaches proposed dozens of formulae based on coverage, while only a few of them have been adopted by MBFL. (2) The current MBFL approaches are based on the assumption that the capability in localizing bugs of each mutant is the same, so they assign the same weight to the mutants that change the test outputs and consider the mutant from the same code element equivalent. In this paper, we intend to enrich the MBFL family by the following two approaches. First, we collect 25 typical SBFL formulae and transform them into MBFL versions. Second, we propose new assumptions that the mutants should have different weights in computing suspicious sources and propose BLMu, a novel MBFL approach that treats mutants differently. We also propose novel metrics for MBFL by considering the high cost of mutation analysis. We perform large‐scale experiments by evaluating all the MBFL approaches against 395 real‐world Java bugs of the Defects4J benchmark. Our evaluation results reveal that BLMu demonstrates a substantial improvement over both MUSE and Metallaxis, the most popular MBFL approaches, at both the statement level and the method level. Specifically, in terms of Top‐1, BLMu improves by 106% at the statement level and 69% at the method level. When compared with other types of FL approaches, MBFL outperforms typical SBFL approaches while still far behind the state‐of‐the‐art learning‐based FL approaches.

show abstract

Improving fault localization and program repair with deep semantic features and transferred knowledge

Cited by 32 publications

References 55 publications

A Survey of Learning-based Automated Program Repair

A Survey of Learning-based Automated Program Repair

Boosting Automated Patch Correctness Prediction via Pre-trained Language Model

A Systematic Exploration of Mutation‐Based Fault Localization Formulae

Contact Info

Product

Resources

About