Tree-based Convolutional Neural Network Research Articles

Quartet: A Query Aware Database Adaptive Compilation Decision System

The executor is an important component of a database. Typical executors that are applied in modern database systems follow either the VOLCANO model or Compiled model, each of which fits some scenarios but not all. Even the widely employed PostgreSQL (PGSQL) and CockroachDB (CRDB) have to rely on human experts to achieve the optimal execution mode. Nevertheless, the accuracy of these decisions is only 32.8% on average, even with an expert involved. Moreover, due to the exclusive use of rule-based strategies, it is not feasible to reasonably switch between two working modes when confronted with different queries. To solve this problem, we propose a QUery awARe daTabase adaptivE compilaTion decision system (Quartet), which can determine the most suitable execution mode with respect to the current workload at runtime. Quartet generates operator-cost and tree-based vectors by analysing the query execution plan (QEP) and then uses the fully connected neural network (FCNN) and tree-based convolutional neural network (TBCNN) to learn the relationship between the QEP and the optimal execution. Our evaluations show that Quartet can improve execution decision accuracy by 60% on average under TPC-H (under 3 GB) workloads.

Automatic Classification of Equivalent Mutants in Mutation Testing of Android Applications

Software and symmetric testing methodologies are primarily used in detecting software defects, but these testing methodologies need to be optimized to mitigate the wasting of resources. As mobile applications are becoming more prevalent in recent times, the need to have mobile applications that satisfy software quality through testing cannot be overemphasized. Testing suites and software quality assurance techniques have also become prevalent, which underscores the need to evaluate the efficacy of these tools in the testing of the applications. Mutation testing is one such technique, which is the process of injecting small changes into the software under test (SUT), thereby creating mutants. These mutants are then tested using mutation testing techniques alongside the SUT to determine the effectiveness of test suites through mutation scoring. Although mutation testing is effective, the cost of implementing it, due to the problem of equivalent mutants, is very high. Many research works gave varying solutions to this problem, but none used a standardized dataset. In this research work, we employed a standard mutant dataset tool called MutantBench to generate our data. Subsequently, an Abstract Syntax Tree (AST) was used in conjunction with a tree-based convolutional neural network (TBCNN) as our deep learning model to automate the classification of the equivalent mutants to reduce the cost of mutation testing in software testing of android applications. The result shows that the proposed model produces a good accuracy rate of 94%, as well as other performance metrics such as recall (96%), precision (89%), F1-score (92%), and Matthew’s correlation coefficients (88%) with fewer False Negatives and False Positives during testing, which is significant as it implies that there is a decrease in the risk of misclassification.

TreeCaps: Tree-Based Capsule Networks for Source Code Processing

Recently program learning techniques have been proposed to process source code based on syntactical structures (e.g., abstract syntax trees) and/or semantic information (e.g., dependency graphs). While graphs may be better than trees at capturing code semantics, constructing the graphs from code inputs through the semantic analysis of multiple viewpoints can lead to inaccurate noises for a specific software engineering task. Compared to graphs, syntax trees are more precisely defined on the grammar and easier to parse; unfortunately, previous tree-based learning techniques have not been able to learn semantic information from trees to achieve better accuracy than graph-based techniques. We have proposed a new learning technique, named TreeCaps, by fusing together capsule networks with tree-based convolutional neural networks to achieve a learning accuracy higher than some existing graph-based techniques while it is based only on trees. TreeCaps introduces novel variable-to-static routing algorithms into the capsule networks to compensate for the loss of previous routing algorithms. Aside from accuracy, we also find that TreeCaps is the most robust to withstand those semantic-preserving program transformations that change code syntax without modifying the semantics. Evaluated on a large number of Java and C/C++ programs, TreeCaps models outperform prior deep learning models of program source code, in terms of both accuracy and robustness for program comprehension tasks such as code functionality classification and function name prediction. Our implementation is publicly available at: https://github.com/bdqnghi/treecaps.

Tree-based convolutional neural networks for object classification in segmented satellite images

Satellite images have a very high resolution, which make their automatic processing computationally costly, and they suffer from artifacts making their processing difficult. This paper describes a method for the effective semantic segmentation of satellite images, and compares different object classifiers in terms of accuracy and execution time. In the paper, the image spectrum is used to reduce the computational cost during the segmentation and classification steps. Firstly, artifacts are corrected from the satellite images for facilitating the feature extraction process. After this, semantic representation is used to gather the semantic regions of downscaled images. As the images are very large, this scaling down significantly reduces the computing time with little degradation in the coarse object detection results. A deep neural forest classifier finds potential regions before executing the pixel-based segmentation. Finally, in our experiments, boundary detection and several classifiers are evaluated to find the objects associated with these regions. The paper details the set-up for our tree-based convolutional neural network. The results indicate that this tree-based convolutional neural network outperforms the other surveyed techniques in the literature.

Analyzing bug fix for automatic bug cause classification

During the bug fixing process, developers usually need to analyze the source code to induce the bug cause, which is useful for bug understanding and localization. The bug fixes of historical bugs usually reflects the bug causes when fixing them. This paper aims at exploiting the corresponding relationship between bug causes and bug fixes to automatically classify bugs into their cause categories. First, we define the code-related bug classification criterion from the perspective of the cause of bugs. Then, we propose a new model to exploit the knowledge in the bug fix by constructing fix trees from the diff source code at Abstract Syntax Tree (AST) level, and representing each fix tree based on the encoding method of Tree-based Convolutional Neural Network (TBCNN). Finally, the corresponding relationship between bug causes and bug fixes is analyzed by automatically classifying bugs into their cause categories. We collected 2000 real-world bugs from two open source projects Mozilla and Radare2 to evaluate our approach. The experimental results show the existence of observational correlation between the bug fix and the cause of the historical bugs, and the proposed fix tree can effectively express the characteristics of the historical bugs for bug cause classification.

Improvement of BigCloneBench Using Tree-Based Convolutional Neural Network

Improvement of BigCloneBench Using Tree-Based Convolutional Neural Network

Deep Learning With Customized Abstract Syntax Tree for Bug Localization

Given a bug report, bug localization technique can help developers automatically locate potential buggy files. Information retrieval and deep learning approaches have been applied in bug localization by extracting lexical features in bug reports and syntactic features in source code files, though they fail to utilize the structural and semantic information of source code files. In this paper, we present a bug localization system CAST, which exploits deep learning and customized abstract syntax trees of programs to locate potential buggy source files automatically and effectively. Specifically, CAST extracts both lexical semantics in bug reports (e.g., words) and source files (e.g., method names) and program semantics in source files (e.g., abstract syntax tree, AST). Moreover, CAST enhances the tree-based convolutional neural network (TBCNN) model with customized ASTs, which distinguish between user-defined methods and system-provided ones to reflect their contributions leading to defects. Furthermore, customized ASTs group the syntactic entities with similar semantics and prune the ones with little or redundant semantics in order to facilitate the learning performance. Experimental results on four widely-used software projects show that CAST significantly outperforms the state-of-the-art methods in locating the buggy source files.

Automatically classifying source code using tree-based approaches

Analyzing source code to solve software engineering problems such as fault prediction, cost, and effort estimation always receives attention of researchers as well as companies. The traditional approaches are based on machine learning, and software metrics obtained by computing standard measures of software projects. However, these methods have faced many challenges due to limitations of using software metrics which were not enough to capture the complexity of programs.To overcome the limitations, this paper aims to solve software engineering problems by exploring information of programs' abstract syntax trees (ASTs) instead of software metrics. We propose two combination models between a tree-based convolutional neural network (TBCNN) and k-Nearest Neighbors (kNN), support vector machines (SVMs) to exploit both structural and semantic ASTs' information. In addition, to deal with high-dimensional data of ASTs, we present several pruning tree techniques which not only reduce the complexity of data but also enhance the performance of classifiers in terms of computational time and accuracy.We survey many machine learning algorithms on different types of program representations including software metrics, sequences, and tree structures. The approaches are evaluated based on classifying 52000 programs written in C language into 104 target labels. The experiments show that the tree-based classifiers dramatically achieve high performance in comparison with those of metrics-based or sequences-based; and two proposed models TBCNN + SVM and TBCNN + kNN rank as the top and the second classifiers. Pruning redundant AST branches leads to not only a substantial reduction in execution time but also an increase in accuracy.

Convolutional Neural Networks over Tree Structures for Programming Language Processing

Programming language processing (similar to natural language processing) is a hot research topic in the field of software engineering; it has also aroused growing interest in the artificial intelligence community. However, different from a natural language sentence, a program contains rich, explicit, and complicated structural information. Hence, traditional NLP models may be inappropriate for programs. In this paper, we propose a novel tree-based convolutional neural network (TBCNN) for programming language processing, in which a convolution kernel is designed over programs' abstract syntax trees to capture structural information. TBCNN is a generic architecture for programming language processing; our experiments show its effectiveness in two different program analysis tasks: classifying programs according to functionality, and detecting code snippets of certain patterns. TBCNN outperforms baseline methods, including several neural models for NLP.