TEP-GNN: Accurate Execution Time Prediction of Functional Tests Using Graph Neural Networks

Samoaa, Hazem; Longa, Antonio; Mohamad, Mazen; Chehreghani, Morteza Haghir; Leitner, Philipp

doi:10.1007/978-3-031-21388-5_32

Cited by 3 publications

(1 citation statement)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Inspired by this work, other works also tried to employ active learning in other software domains, e.g., Nir et al used active learning to identify new unknown malware in Android systems [57] and Windows OS [58]. Recently, Berezov et al [59] combined active learning and code generation techniques to help build code benchmarks. In their work, the Greedy Sampling [60] acquisition function was used to select the most valuable code for the active learning component.…”

Section: Active Learning For Codementioning

confidence: 99%

Active Code Learning: Benchmarking Sample-Efficient Training of Code Models

Hu,

Guo,

Xie

et al. 2024

IIEEE Trans. Software Eng.

View full text Add to dashboard Cite

The costly human effort required to prepare the training data of machine learning (ML) models hinders their practical development and usage in software engineering (ML4Code), especially for those with limited budgets. Therefore, efficiently training models of code with less human effort has become an emergent problem. Active learning is such a technique to address this issue that allows developers to train a model with reduced data while producing models with desired performance, which has been well studied in computer vision and natural language processing domains. Unfortunately, there is no such work that explores the effectiveness of active learning for code models. In this paper, we bridge this gap by building the first benchmark to study this critical problem -active code learning. Specifically, we collect 11 acquisition functions (which are used for data selection in active learning) from existing works and adapt them for code-related tasks. Then, we conduct an empirical study to check whether these acquisition functions maintain performance for code data. The results demonstrate that feature selection highly affects active learning and using output vectors to select data is the best choice. For the code summarization task, active code learning is ineffective which produces models with over a 29.64% gap compared to the expected performance. Furthermore, we explore future directions of active code learning with an exploratory study. We propose to replace distance calculation methods with evaluation metrics and find a correlation between these evaluation-based distance methods and the performance of code models.

show abstract

Section: Active Learning For Codementioning

confidence: 99%

Active Code Learning: Benchmarking Sample-Efficient Training of Code Models

Hu,

Guo,

Xie

et al. 2024

IIEEE Trans. Software Eng.

View full text Add to dashboard Cite

show abstract

Batch Mode Deep Active Learning for Regression on Graph Data

Samoaa,

Aronsson,

Leitner

et al. 2023

2023 IEEE International Conference on Big Data (BigData)

View full text Add to dashboard Cite

PACE: A Program Analysis Framework for Continuous Performance Prediction

Biringa,

Kul

2024

ACM Trans. Softw. Eng. Methodol.

View full text Add to dashboard Cite

Software development teams establish elaborate continuous integration pipelines containing automated test cases to accelerate the development process of software. Automated tests help to verify the correctness of code modifications decreasing the response time to changing requirements. However, when the software teams do not track the performance impact of pending modifications, they may need to spend considerable time refactoring existing code. This paper presents PACE , a program analysis framework that provides continuous feedback on the performance impact of pending code updates. We design performance microbenchmarks by mapping the execution time of functional test cases given a code update. We map microbenchmarks to code stylometry features and feed them to predictors for performance predictions. Our experiments achieved significant performance in predicting code performance, outperforming current state-of-the-art by 75% on neural-represented code stylometry features.

show abstract

TEP-GNN: Accurate Execution Time Prediction of Functional Tests Using Graph Neural Networks

Cited by 3 publications

References 24 publications

Active Code Learning: Benchmarking Sample-Efficient Training of Code Models

Active Code Learning: Benchmarking Sample-Efficient Training of Code Models

Batch Mode Deep Active Learning for Regression on Graph Data

PACE: A Program Analysis Framework for Continuous Performance Prediction

Contact Info

Product

Resources

About