Generating attributed variability models for transfer learning

Dorn, Johannes; Apel, Sven; Siegmund, Norbert

doi:10.1145/3377024.3377040

Cited by 6 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While there is a growing interest to employ ML techniques for VIS engineering Pereira et al (2020);Ferreira et al (2021), to the best of our knowledge, classification of variants from behavioural traces using ML techniques has not been studied yet. ML approaches have been used to support performance prediction (e.g., Shu et al (2020); Ha and Zhang (2019);Valov et al (2015); Zhang et al (2015); Kaltenecker et al (2020); Alves Pereira et al (2020); Bacciu et al (2015)), performance optimisation (e.g., Martin et al (2021); Dorn and Apel (2020); Weckesser et al (2018); Weber et al (2021); Velez et al (2021)), to improve the search for good and acceptable configurations (e.g., ; Nair et al (2017); Temple et al (2016)) or to predict unwanted feature interactions Khoshmanesh and Lutz (2020); Li et al (2020). If some of these works also target classification tasks, they consider configurations as the main entry point of their approaches and do not take into account the behaviour of the studied systems.…”

Section: Machine Learning For Variability-intensive Systemsmentioning

confidence: 99%

VaryMinions: leveraging RNNs to identify variants in variability-intensive systems’ logs

Fortz,

Temple,

Devroey

et al. 2024

Empir Software Eng

View full text Add to dashboard Cite

From business processes to course management, variability-intensive software systems (VIS) are now ubiquitous. One can configure these systems’ behaviour by activating options, e.g., to derive variants handling building permits across municipalities or implementing different functionalities (quizzes, forums) for a given course. These customisation facilities allow VIS to support distinct relevant customer requirements while taking advantage of reuse for common parts. Customisation thus allows realising both scope and scale economies. Behavioural differences amongst variants manifest themselves in event logs. To re-engineer this kind of system, one must know which variant(s) have produced which behaviour. Since variant information is barely present in logs, this paper supports this task by employing machine learning techniques to classify behaviours (event sequences) among variants. Specifically, we train Long Short Term Memory (LSTMs) and Gated Recurrent Units (GRUs) recurrent neural networks to relate event sequences with the variants they belong to on six different datasets issued from the configurable process and VIS domains. After having evaluated 20 different architectures of LSTM/GRU, our results demonstrate that it is possible to effectively learn the trace-to-variant mapping with high accuracy (at least $$80\%$$ 80 % and up to $$99\%$$ 99 % ) and at scale, i.e., identifying 50 variants using 5000+ traces for each variant.

show abstract

Section: Machine Learning For Variability-intensive Systemsmentioning

confidence: 99%

VaryMinions: leveraging RNNs to identify variants in variability-intensive systems’ logs

Fortz,

Temple,

Devroey

et al. 2024

Empir Software Eng

View full text Add to dashboard Cite

show abstract

“…But configuration options influence software performance, e.g., the energy consumption [13]. An option is called influential for a performance when its values have a strong effect on this performance [42,18]. For example, developers might wonder whether the option they add to a configurable system has an influence on its performance.…”

Section: Research Questionsmentioning

confidence: 99%

“…Understanding the effects of options and their interactions is hard for developers and users yet crucial for maintaining, debugging or configuring a software system. Some works (e.g., [102]) have proposed to build performance models 18 See https://github.com/llesoil/input_sensitivity/tree/ master/results/RQS/RQ5/RQ5-other_ref.ipynb that are interpretable and capable of communicating the influence of individual options on performance. Key insights.…”

Section: Implications Insights Open Challengesmentioning

confidence: 99%

Input sensitivity on the performance of configurable systems an empirical study

Lesoil

Acher

Blouin

et al. 2023

Journal of Systems and Software

View full text Add to dashboard Cite

“…Several research papers have shown that it is possible to transfer software performances from a source environment to a target environment, using either the similarities between environments [9,16,39], or selecting the best source environment [23]. Including causalities in the performance model to improve the transfer [17,18] is another promising research direction to explore.…”

Section: Generalize the Configuration Knowledgementioning

confidence: 99%

Deep Software Variability: Towards Handling Cross-Layer Configuration

Lesoil

Acher

Blouin

et al. 2021

Proceedings of the 15th International Working Conference on Variability Modelling of Software-Intensive Systems

View full text Add to dashboard Cite

Configuring software is a powerful means to reach functional and performance goals of a system. However, many layers (hardware, operating system, input data, etc.), themselves subject to variability, can alter performances of software configurations. For instance, configurations' options of the x264 video encoder may have very different effects on x264's encoding time when used with different input videos, depending on the hardware on which it is executed. In this vision paper, we coin the term deep software variability to refer to the interaction of all external layers modifying the behavior or non-functional properties of a software. Deep software variability challenges practitioners and researchers: the combinatorial explosion of possible executing environments complicates the understanding, the configuration, the maintenance, the debug, and the test of configurable systems. There are also opportunities: harnessing all variability layers (and not only the software layer) can lead to more efficient systems and configuration knowledge that truly generalizes to any usage and context.

show abstract

Generating attributed variability models for transfer learning

Cited by 6 publications

References 21 publications

VaryMinions: leveraging RNNs to identify variants in variability-intensive systems’ logs

VaryMinions: leveraging RNNs to identify variants in variability-intensive systems’ logs

Input sensitivity on the performance of configurable systems an empirical study

Deep Software Variability: Towards Handling Cross-Layer Configuration

Contact Info

Product

Resources

About