# Dividable Configuration Performance Learning

arXiv: https://arxiv.org/abs/2409.07629 · HTML: https://mlsanity.com/paper/2409.07629/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 133 references that are in the map.
- First posted on arXiv 11 Sep 2024.

## Builds on (most cited first, 30 of 36)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Finding Faster Configurations using FLASH](https://mlsanity.com/paper/1801.02175/) (2018)
- [Multi-Objectivizing Software Configuration Tuning (for a single performance concern)](https://mlsanity.com/paper/2106.01331/) (2021)
- [BestConfig: Tapping the Performance Potential of Systems via Automatic Configuration Tuning](https://mlsanity.com/paper/1710.03439/) (2017)
- [Plan-Structured Deep Neural Network Models for Query Performance Prediction](https://mlsanity.com/paper/1902.00132/) (2019)
- [Facilitating Database Tuning with Hyper-Parameter Optimization: A Comprehensive Experimental Evaluation](https://mlsanity.com/paper/2110.12654/) (2021)
- [Do Performance Aspirations Matter for Guiding Software Configuration Tuning?](https://mlsanity.com/paper/2301.03290/) (2023)
- [Transfer Learning for Performance Modeling of Configurable Systems: An Exploratory Analysis](https://mlsanity.com/paper/1709.02280/) (2017)
- [MMO: Meta Multi-Objectivization for Software Configuration Tuning](https://mlsanity.com/paper/2112.07303/) (2021)
- [Simultaneous Safe Screening of Features and Samples in Doubly Sparse Modeling](https://mlsanity.com/paper/1602.02485/) (2016)
- [An Uncertainty-Aware Approach to Optimal Configuration of Stream Processing Systems](https://mlsanity.com/paper/1606.06543/) (2016)
- [How to Evaluate Solutions in Pareto-based Search-Based Software Engineering? A Critical Review and Methodological Guidance](https://mlsanity.com/paper/2002.09040/) (2020)
- [The Weights can be Harmful: Pareto Search versus Weighted Search in Multi-Objective Search-Based Software Engineering](https://mlsanity.com/paper/2202.03728/) (2022)
- [DeepPerform: An Efficient Approach for Performance Testing of Resource-Constrained Neural Networks](https://mlsanity.com/paper/2210.05370/) (2022)
- [Predicting Configuration Performance in Multiple Environments with Sequential Meta-learning](https://mlsanity.com/paper/2402.03183/) (2024)
- [BiLO-CPDP: Bi-Level Programming for Automated Model Discovery in Cross-Project Defect Prediction](https://mlsanity.com/paper/2008.13489/) (2020)
- [Lifelong Dynamic Optimization for Self-Adaptive Systems: Fact or Fiction?](https://mlsanity.com/paper/2201.07096/) (2022)
- [Towards Dynamic and Safe Configuration Tuning for Cloud Databases](https://mlsanity.com/paper/2203.14473/) (2022)
- [Predicting Software Performance with Divide-and-Learn](https://mlsanity.com/paper/2306.06651/) (2023)
- [Robust Dialogue State Tracking with Weak Supervision and Sparse Data](https://mlsanity.com/paper/2202.03354/) (2022)
- [LlamaTune: Sample-Efficient DBMS Configuration Tuning](https://mlsanity.com/paper/2203.05128/) (2022)
- [Hyperparameter Optimization for Effort Estimation](https://mlsanity.com/paper/1805.00336/) (2018)
- [Adapting Multi-objectivized Software Configuration Tuning](https://mlsanity.com/paper/2404.04744/) (2024)
- [Planning Landscape Analysis for Self-Adaptive Systems](https://mlsanity.com/paper/2203.12472/) (2022)
- [White-Box Analysis over Machine Learning: Modeling Performance of Configurable Systems](https://mlsanity.com/paper/2101.05362/) (2021)
- [Does Configuration Encoding Matter in Learning Software Performance? An Empirical Study on Encoding Schemes](https://mlsanity.com/paper/2203.15988/) (2022)
- [Low-Level Augmented Bayesian Optimization for Finding the Best Cloud VM](https://mlsanity.com/paper/1712.10081/) (2017)
- [White-Box Performance-Influence Models: A Profiling and Learning Approach](https://mlsanity.com/paper/2102.06395/) (2021)
- [Deep Configuration Performance Learning: A Systematic Survey and Taxonomy](https://mlsanity.com/paper/2403.03322/) (2024)
- [Fast Linear Model Trees by PILOT](https://mlsanity.com/paper/2302.03931/) (2023)

## Built on by (most cited first, 4 of 4)

- [Faster Configuration Performance Bug Testing with Neural Dual-level Prioritization](https://mlsanity.com/paper/2501.15392/) (2025)
- [CoTune: Co-evolutionary Configuration Tuning](https://mlsanity.com/paper/2509.24694/) (2025)
- [CDS4RAG: Cyclic Dual-Sequential Hyperparameter Optimization for RAG](https://mlsanity.com/paper/2605.08333/) (2026)
- [LLMSYS-HPOBench: Hyperparameter Optimization Benchmark Suite for Real-World LLM Systems](https://mlsanity.com/paper/2605.08305/) (2026)

## Abstract (arXiv)

Machine/deep learning models have been widely adopted for predicting the configuration performance of software systems. However, a crucial yet unaddressed challenge is how to cater for the sparsity inherited from the configuration landscape: the influence of configuration options (features) and the distribution of data samples are highly sparse. In this paper, we propose a model-agnostic and sparsity-robust framework for predicting configuration performance, dubbed DaL, based on the new paradigm of dividable learning that builds a model via "divide-and-learn". To handle sample sparsity, the samples from the configuration landscape are divided into distant divisions, for each of which we build a sparse local model, e.g., regularized Hierarchical Interaction Neural Network, to deal with the feature sparsity. A newly given configuration would then be assigned to the right model of division for the final prediction. Further, DaL adaptively determines the optimal number of divisions required for a system and sample size without any extra training or profiling. Experiment results from 12 real-world systems and five sets of training data reveal that, compared with the state-of-the-art approaches, DaL performs no worse than the best counterpart on 44 out of 60 cases with up to 1.61x improvement on accuracy; requires fewer samples to reach the same/better accuracy; and producing acceptable training overhead. In particular, the mechanism that adapted the parameter d can reach the optimal value for 76.43% of the individual runs. The result also confirms that the paradigm of dividable learning is more suitable than other similar paradigms such as ensemble learning for predicting configuration performance. Practically, DaL considerably improves different global models when using them as the underlying local models, which further strengthens its flexibility.