Active learning for software engineering

Cambronero, José; Dang, Thurston H. Y.; Vasilakis, Nikos; Shen, Jiasi; Wu, Jerry J.; Rinard, Martin

doi:10.1145/3359591.3359732

Cited by 6 publications

(1 citation statement)

References 67 publications

(58 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yu et al [30] show that active learning can help with conducting literature reviews. Recently, Cambronero et al [31] proposed the use of active learning to automatically infer programs, which can significantly alleviate the difficulty of manual annotations. Based on the Mozilla Firefox vulnerability data, Yu et al [32] prove that active learning is useful in building a prediction model which learns from the historical source code data and predicts the candidates to inspect.…”

Section: Active Learning For Sementioning

confidence: 99%

DRE: density-based data selection with entropy for adversarial-robust deep learning models

Guo

Cordy

et al. 2022

Neural Comput & Applic

View full text Add to dashboard Cite

Active learning helps software developers reduce the labeling cost when building high-quality machine learning models. A core component of active learning is the acquisition function that determines which data should be selected to annotate.State-of-the-art (SOTA) acquisition functions focus on clean performance (e.g. accuracy) but disregard robustness (an important quality property), leading to fragile models with negligible robustness (less than 0.20%). In this paper, we first propose to integrate adversarial training into active learning (adversarial-robust active learning, ARAL) to produce robust models. Our empirical study on 11 acquisition functions and 15105 trained deep neural networks (DNNs) shows that ARAL can produce models with robustness ranging from 2.35% to 63.85%. Our study also reveals, however, that the acquisition functions that perform well on accuracy are worse than random sampling when it comes to robustness. Via examining the reasons behind this, we devise the density-based robust sampling with entropy (DRE) to target both clean performance and robustness. The core idea of DRE is to maintain a balance between selected data and the entire set based on the entropy density distribution. DRE outperforms SOTA functions in terms of robustness by up to 24.40%, while remaining competitive on accuracy. Additionally, the in-depth evaluation shows that DRE is applicable as a test selection metric for model retraining and stands out from all compared functions by up to 8.21% robustness.

show abstract

Section: Active Learning For Sementioning

confidence: 99%

DRE: density-based data selection with entropy for adversarial-robust deep learning models

Guo

Cordy

et al. 2022

Neural Comput & Applic

View full text Add to dashboard Cite

show abstract

Reading to Write Code: An Experience Report of a Reverse Engineering and Modeling Course

Ryan

Soria

Dreef

et al. 2022

2022 IEEE/ACM 44th International Conference on Software Engineering: Software Engineering Education and Training (ICSE-SEET)

View full text Add to dashboard Cite

A substantial portion of any software engineer's job is reading code. Despite the criticality of this skill in a budding software engineer, reading code-and more specifically, techniques on how to read code when integrating oneself into a large existing software project-is often neglected in the typical software engineering education. As part of a new professional Master of Software Engineering at the University of California, Irvine, we designed and delivered a "reading to write code" course from the ground up. Titled Reverse Engineering and Modeling, the course introduces students to techniques they can use to become familiar with a large code base, so they are able to make meaningful contributions. In this paper, we briefly introduce the Master program and its underlying philosophy, articulate the course's learning outcomes, present the design of the course, and provide a detailed reflection on our experiences in terms of what went well, what did not go well, what we do not know yet, and what our next steps are in preparing for the forthcoming incarnation of the course in Spring 2022. In so doing, we hope to provide a baseline together with lessons learned for others who may be interested in instituting a similar course at their institution.

show abstract

Active Learning for Inference and Regeneration of Applications that Access Databases

Shen

Rinard

2020

ACM Trans. Program. Lang. Syst.

View full text Add to dashboard Cite

We present K onure , a new system that uses active learning to infer models of applications that retrieve data from relational databases. K onure comprises a domain-specific language (each model is a program in this language) and associated inference algorithm that infers models of applications whose behavior can be expressed in this language. The inference algorithm generates inputs and database contents, runs the application, then observes the resulting database traffic and outputs to progressively refine its current model hypothesis. Because the technique works with only externally observable inputs, outputs, and database contents, it can infer the behavior of applications written in arbitrary languages using arbitrary coding styles (as long as the behavior of the application is expressible in the domain-specific language). K onure also implements a regenerator that produces a translated Python implementation of the application that systematically includes relevant security and error checks.

show abstract

Active learning for software engineering

Cited by 6 publications

References 67 publications

DRE: density-based data selection with entropy for adversarial-robust deep learning models

DRE: density-based data selection with entropy for adversarial-robust deep learning models

Reading to Write Code: An Experience Report of a Reverse Engineering and Modeling Course

Active Learning for Inference and Regeneration of Applications that Access Databases

Contact Info

Product

Resources

About