mlsanityData to 7 Oct 2026

Deep Configuration Performance Learning: A Systematic Survey and Taxonomy

arXiv 2403.03322 ↗First posted 5 Mar 2024cs.SE cs.AI cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

Performance is arguably the most crucial attribute that reflects the quality of a configurable software system. However, given the increasing scale and complexity of modern software, modeling and predicting how various configurations can impact performance becomes one of the major challenges in software maintenance. As such, performance is often modeled without having a thorough knowledge of the software system, but relying mainly on data, which fits precisely with the purpose of deep learning. In this paper, we conduct a comprehensive review exclusively on the topic of deep learning for performance learning of configurable software, covering 1,206 searched papers spanning six indexing services, based on which 99 primary papers were extracted and analyzed. Our results outline key statistics, taxonomy, strengths, weaknesses, and optimal usage scenarios for techniques related to the preparation of configuration data, the construction of deep learning performance models, the evaluation of these models, and their utilization in various software configuration-related tasks.We also identify the good practices and potentially problematic phenomena from the studies surveyed, together with a comprehensive summary of actionable suggestions and insights into future opportunities within the field. To promote open science, all the raw results of this survey can be accessed at our repository: https://github.com/ideas-labo/DCPL-SLR.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 49 of its 173 references that are in the map. First posted on arXiv 5 Mar 2024.

Builds on

49 of 173 references.

References · 49

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 462
  4. 2019Which Tasks Should Be Learned Together in Multi-task Learning?cited by 367
  5. 2016Model-Agnostic Interpretability of Machine Learningcited by 219
  6. 2016Deep Multi-task Representation Learning: A Tensor Factorisation Approachcited by 69
  7. 2019Hierarchically Structured Meta-learningcited by 67
  8. 2018FINN-R: An End-to-End Deep-Learning Framework for Fast Exploration of Quantized Neural Networkscited by 54
  9. 2020How to Retrain Recommender System? A Sequential Meta-Learning Methodcited by 42
  10. 2020A Survey on Deep Learning for Software Engineeringcited by 37
  11. 2020A Systematic Literature Review on the Use of Deep Learning in Software Engineering Researchcited by 35
  12. 2018Finding Faster Configurations using FLASHcited by 32
37 more
  1. 2021Multi-Objectivizing Software Configuration Tuning (for a single performance concern)cited by 27
  2. 2019Plan-Structured Deep Neural Network Models for Query Performance Predictioncited by 24
  3. 2023Do Performance Aspirations Matter for Guiding Software Configuration Tuning?cited by 21
  4. 2017Transfer Learning for Performance Modeling of Configurable Systems: An Exploratory Analysiscited by 20
  5. 2021MMO: Meta Multi-Objectivization for Software Configuration Tuningcited by 19
  6. 2016A Survey and Taxonomy of Self-Aware and Self-Adaptive Cloud Autoscaling Systemscited by 18
  7. 2016Self-Adaptive Trade-off Decision Making for Autoscaling Cloud-Based Servicescited by 17
  8. 2020How to Evaluate Solutions in Pareto-based Search-Based Software Engineering? A Critical Review and Methodological Guidancecited by 17
  9. 2022VUDENC: Vulnerability Detection with Deep Learning on a Natural Codebase for Pythoncited by 17
  10. 2022The Weights can be Harmful: Pareto Search versus Weighted Search in Multi-Objective Search-Based Software Engineeringcited by 17
  11. 2024Predicting Configuration Performance in Multiple Environments with Sequential Meta-learningcited by 17
  12. 2020On the Replicability and Reproducibility of Deep Learning in Software Engineeringcited by 16
  13. 2022Lifelong Dynamic Optimization for Self-Adaptive Systems: Fact or Fiction?cited by 16
  14. 2022DeepPerform: An Efficient Approach for Performance Testing of Resource-Constrained Neural Networkscited by 16
  15. 2023Predicting Software Performance with Divide-and-Learncited by 16
  16. 2020BiLO-CPDP: Bi-Level Programming for Automated Model Discovery in Cross-Project Defect Predictioncited by 15
  17. 2019Learning Software Configuration Spaces: A Systematic Literature Reviewcited by 14
  18. 2017Transfer Learning for Improving Model Predictions in Highly Configurable Softwarecited by 12
  19. 2022Planning Landscape Analysis for Self-Adaptive Systemscited by 12
  20. 2021White-Box Analysis over Machine Learning: Modeling Performance of Configurable Systemscited by 10
  21. 2022Does Configuration Encoding Matter in Learning Software Performance? An Empirical Study on Encoding Schemescited by 10
  22. 2017Low-Level Augmented Bayesian Optimization for Finding the Best Cloud VMcited by 9
  23. 2020Synergizing Domain Expertise with Self-Awareness in Software Systems: A Patternized Architecture Guidelinecited by 9
  24. 2020DATESSO: Self-Adapting Service Composition with Debt-Aware Two Levels Constraint Reasoningcited by 9
  25. 2015Machine Learning Based Auto-tuning for Enhanced OpenCL Performance Portabilitycited by 7
  26. 2022Cross-Domain Deep Code Search with Meta Learningcited by 6
  27. 2022HINNPerf: Hierarchical Interaction Neural Network for Performance Prediction of Configurable Systemscited by 5
  28. 2014Patterns in the Chaos - a Study of Performance Variation and Predictability in Public IaaS Cloudscited by 4
  29. 2017Binarsity: a penalization for one-hot encoded features in linear supervised learningcited by 4
  30. 2018ConPredictor: Concurrency Defect Prediction in Real-World Applicationscited by 4
  31. 2021High-Dimensional Bayesian Optimization with Multi-Task Learning for RocksDBcited by 4
  32. 2023PerfSAGE: Generalized Inference Performance Predictor for Arbitrary Deep Learning Models on Edge Devicescited by 4
  33. 2023A Unified Active Learning Framework for Annotating Graph Data with Application to Software Source Code Performance Predictioncited by 4
  34. 2015Performance-oriented DevOps: A Research Agendacited by 3
  35. 2019Towards Quality Assurance of Software Product Lines with Adversarial Configurationscited by 3
  36. 2023Predicting the Performance of a Computing System with Deep Networkscited by 3
  37. 2020Understanding the Automated Parameter Optimization on Transfer Learning for CPDP: An Empirical Studycited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 6; 2026: 1.

8 papers.

  1. 2025Distilled Lifelong Self-Adaptation for Configurable Systemscited by 11
  2. 2025Faster Configuration Performance Bug Testing with Neural Dual-level Prioritizationcited by 9
  3. 2025Dually Hierarchical Drift Adaptation for Online Configuration Performance Learningcited by 7
  4. 2024Dividable Configuration Performance Learningcited by 4
  5. 2026Revealing Domain-Spatiality Patterns for Configuration Tuning: Domain Knowledge Meets Fitness Landscapescited by 4
  6. 2025Learning Software Bug Reports: A Systematic Literature Reviewcited by 3
  7. 2025Evaluating Useful Surrogate Models for Configuration Tuning Beyond Accuracy: A Fitness Landscape Analysis Perspectivecited by 0
  8. 2025ScaleDL: Towards Scalable and Efficient Runtime Prediction for Distributed Deep Learning Workloadscited by 0