A Pragmatic Approach for Hyper-Parameter Tuning in Search-based Test Case Generation

TL;DR

This paper introduces a static feature-based method to prioritize classes for hyper-parameter tuning in search-based test case generation, significantly improving efficiency and coverage with limited tuning budgets.

Contribution

It proposes a novel metric 'Tuning Gain' and a class prioritization approach using static code features, enhancing tuning effectiveness in search-based test generation.

Findings

Prioritizing classes improves branch coverage tenfold over global tuning.

The approach is effective with low tuning budgets.

Different features and tuning parameters impact results significantly.

Abstract

Search-based test case generation, which is the application of meta-heuristic search for generating test cases, has been studied a lot in the literature, lately. Since, in theory, the performance of meta-heuristic search methods is highly dependent on their hyper-parameters, there is a need to study hyper-parameter tuning in this domain. In this paper, we propose a new metric ("Tuning Gain"), which estimates how cost-effective tuning a particular class is. We then predict "Tuning Gain" using static features of source code classes. Finally, we prioritize classes for tuning, based on the estimated "Tuning Gains" and spend the tuning budget only on the highly-ranked classes. To evaluate our approach, we exhaustively analyze 1,200 hyper-parameter configurations of a well-known search-based test generation tool (EvoSuite) for 250 classes of 19 projects from benchmarks such as SF110 and SBST2018 tool competition. We used a tuning approach called Meta-GA and compared the tuning results with and without the proposed class prioritization. The results show that for a low tuning budget, prioritizing classes outperforms the alternatives in terms of extra covered branches (10 times more than a traditional global tuning). In addition, we report the impact of different features of our approach such as search space size, tuning budgets, tuning algorithms, and the number of classes to tune, on the final results.