Quality-Driven Selective Mutation for Deep Learning

• URL: http://arxiv.org/abs/2604.22640v1
• Date: Fri, 24 Apr 2026 15:15:10 GMT
• Title: Quality-Driven Selective Mutation for Deep Learning
• Abstract summary: selective mutation for deep learning aims to reduce the cost of mutant generation and execution by choosing operator configurations that yield resistant and realistic mutants.<n>This study presents a probabilistic framework to quantify mutant quality along two complementary axes: resistance and realism.<n>We show that quality-driven selection reduces the number of generated mutants by up to 55.6% while preserving typical levels of resistance and realism.
• Score: 0.31498833540989407
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Mutants support testing and debugging in two roles: (i) as test goals and (ii) as substitutes for real faults. Hard-to-kill mutants provide better guidance for test improvement, while realism is essential when mutants are used to simulate real bugs. Building on these roles, selective mutation for deep learning (DL) aims to reduce the cost of mutant generation and execution by choosing operator configurations that yield resistant and realistic mutants. However, the DL literature lacks a unified measure that captures both aspects. This study presents a probabilistic framework to quantify mutant quality along two complementary axes: resistance and realism. Resistance adapts the classical notion of hard-to-kill mutants to the DL setting using statistical killing probabilities, while realism is measured via the generalized Jaccard similarity between mutant and real-fault detectability patterns. The framework enables ranking and filtering of low-quality mutation-operator configurations without assuming a specific use case. We empirically evaluate the approach on four datasets of real DL faults. Three datasets (CleanML, DeepFD, and DeepLocalize) are used to estimate and select high-quality operator configurations, and the held-out defect4ML dataset is used for validation. Results show that quality-driven selection reduces the number of generated mutants by up to 55.6% while preserving typical levels of resistance and realism under baseline-aligned selection thresholds. These findings confirm that dual-objective selection can lower cost without compromising the usefulness of mutants for either role.

Related papers

• FACTOR: Counterfactual Training-Free Test-Time Adaptation for Open-Vocabulary Object Detection [63.91351553178842]
  FACTOR is a training-free Test-time adaptation for Open-vocabulary object detection.<n>It quantifies attribute sensitivity, semantic relevance, and prediction variation to selectively suppress attribute-dependent predictions.<n>Experiments on PASCAL-C, COCO-C, and FoggyCityscapes show that FACTOR consistently outperforms prior TTA methods.
  arXiv  Detail & Related papers  (2026-05-05T02:31:18Z)
• Improving RCT-Based Treatment Effect Estimation Under Covariate Mismatch via Calibrated Alignment [0.0]
  We propose CALM, which bypasses imputation by learning embeddings that map each source's features into a common representation space.<n> OS outcome models are transferred to the RCT embedding space and calibrated using trial data, preserving causal identification from randomization.
  arXiv  Detail & Related papers  (2026-03-19T17:43:12Z)
• Attribution-Guided Model Rectification of Unreliable Neural Network Behaviors [60.06461883533697]
  We leverage rank-one model editing to establish an attribution-guided model rectification framework.<n>We first distinguish our rectification setting from existing model editing, yielding a formulation that corrects unreliable behavior.<n>To target the primary source of misbehavior, we introduce an attribution-guided layer localization method.
  arXiv  Detail & Related papers  (2026-03-08T01:06:07Z)
• An Empirical Study of the Realism of Mutants in Deep Learning [0.34410212782758043]
  This study presents the first empirical comparison of pre-training and post-training mutation approaches in deep learning.<n>Results show that pre-training mutants exhibit consistently stronger coupling and higher behavioral similarity to real faults than post-training mutants.
  arXiv  Detail & Related papers  (2025-12-18T16:37:50Z)
• An Empirical Evaluation of Manually Created Equivalent Mutants [54.02049952279685]
  Less than 10 % of manually created mutants are equivalent. Surprisingly, our findings indicate that a significant portion of developers struggle to accurately identify equivalent mutants.
  arXiv  Detail & Related papers  (2024-04-14T13:04:10Z)
• Predicting loss-of-function impact of genetic mutations: a machine learning approach [0.0]
  This paper aims to train machine learning models on the attributes of a genetic mutation to predict LoFtool scores. These attributes included, but were not limited to, the position of a mutation on a chromosome, changes in amino acids, and changes in codons caused by the mutation. Models were evaluated using five-fold cross-validated averages of r-squared, mean squared error, root mean squared error, mean absolute error, and explained variance.
  arXiv  Detail & Related papers  (2024-01-26T19:27:38Z)
• Variational Classification [51.2541371924591]
  We derive a variational objective to train the model, analogous to the evidence lower bound (ELBO) used to train variational auto-encoders. Treating inputs to the softmax layer as samples of a latent variable, our abstracted perspective reveals a potential inconsistency. We induce a chosen latent distribution, instead of the implicit assumption found in a standard softmax layer.
  arXiv  Detail & Related papers  (2023-05-17T17:47:19Z)
• Score-based Causal Representation Learning with Interventions [54.735484409244386]
  This paper studies the causal representation learning problem when latent causal variables are observed indirectly. The objectives are: (i) recovering the unknown linear transformation (up to scaling) and (ii) determining the directed acyclic graph (DAG) underlying the latent variables.
  arXiv  Detail & Related papers  (2023-01-19T18:39:48Z)
• Mutation Testing of Deep Reinforcement Learning Based on Real Faults [11.584571002297217]
  This paper builds on the existing approach of Mutation Testing (MT) to extend it to Reinforcement Learning (RL) systems. We show that the design choice of the mutation killing definition can affect whether or not a mutation is killed as well as the generated test cases.
  arXiv  Detail & Related papers  (2023-01-13T16:45:56Z)
• Calibration of Neural Networks using Splines [51.42640515410253]
  Measuring calibration error amounts to comparing two empirical distributions. We introduce a binning-free calibration measure inspired by the classical Kolmogorov-Smirnov (KS) statistical test. Our method consistently outperforms existing methods on KS error as well as other commonly used calibration measures.
  arXiv  Detail & Related papers  (2020-06-23T07:18:05Z)
• DeepMutation: A Neural Mutation Tool [26.482720255691646]
  DeepMutation is a tool wrapping our deep learning model into a fully automated tool chain. It can generate, inject, and test mutants learned from real faults.
  arXiv  Detail & Related papers  (2020-02-12T01:57:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.