Publications

2024

Journal articles

• Tackling the XAI Disagreement Problem with Regional Explanations

Gabriel Laberge, Yann Pequignot, Mario Marchand, Foutse Khomh

International Conference on Artificial Intelligence and Statistics (AISTATS), May 2024, Valencia, Spain. 

 

• Oblivious Turing Machine

Sofiane Azogagh, Victor Delfour, Marc-Olivier Killijian

19th European Dependable Computing Conference, Apr 2024, Leuven, France

 

Preprints, Working Papers, …

• Layerwise Early Stopping for Test Time Adaptation

Sabyasachi Sahoo, Mostafa Elaraby, Jonas Ngnawe, Yann Pequignot, Frédéric Precioso, Christian Gagné,2024

 

2023

Journal articles

• Silent bugs in deep learning frameworks: an empirical study of Keras and TensorFlow

Florian Tambon, Amin Nikanjam, Le An, Foutse Khomh, Giuliano Antoniol

Empirical Software Engineering, 2023, 29 (1), pp.10. ⟨10.1007/s10664-023-10389-6⟩

 

• Physics-Guided Adversarial Machine Learning for Aircraft Systems Simulation

Houssem Ben Braiek, Thomas Reid, Foutse Khomh,IEEE Transactions on Reliability, 2023, 72 (3), pp.1161-1175. ⟨10.1109/TR.2022.3196272⟩

 

• Bugs in machine learning-based systems: a faultload benchmark

Mohammad Mehdi Morovati, Amin Nikanjam, Foutse Khomh, Zhen Ming Jiang

Empirical Software Engineering, 2023, 28 (3), pp.62. ⟨10.1007/s10664-023-10291-1⟩

 

• Behavioural equivalences for continuous-time Markov processes

Linan Chen, Florence Clerc, Prakash Panangaden

Mathematical Structures in Computer Science, 2023, 33 (4-5), pp.222-258. ⟨10.1017/S0960129523000099⟩

 

• A probabilistic framework for mutation testing in deep neural networks

Florian Tambon, Foutse Khomh, Giuliano Antoniol

Information and Software Technology, 2023, 155 (2), pp.107129. ⟨10.1016/j.infsof.2022.107129⟩

 

• Bug Characterization in Machine Learning-based Systems

Mohammad Mehdi Morovati, Amin Nikanjam, Florian Tambon, Foutse Khomh, Zhen Ming Empirical Software Engineering, 2023, ⟨10.48550/arXiv.2307.14512⟩

 

• Explainable prediction of Qcodes for NOTAMs using column generation

Krunal Kishor Patel, Guy Desaulniers, Andrea Lodi, Freddy Lecue

Journal of the Operational Research Society, 2023, pp.1-11. ⟨10.1080/01605682.2023.2181715⟩

Conference papers

• Statistical Guarantees for Variational Autoencoders using PAC-Bayesian Theory

Sokhna Diarra Mbacke, Florence Clerc, Pascal Germain

37th Conference on Neural Information Processing Systems (NeurIPS 2023)., Dec 2023, New-Orleans, United States

 

• PAC-Bayesian Generalization Bounds for Adversarial Generative Models

Sokhna Diarra Mbacke, Florence Clerc, Pascal Germain

International Conference on Machine Learning, Jul 2023, Honololu, Hawaii, United States

 

• Fool SHAP with Stealthily Biased Sampling

Gabriel Laberge, Ulrich Aïvodji, Satoshi Hara, Mario Marchand, Foutse Khomh

International Conference on Learning Representations (ICLR), May 2023, Kigali, Rwanda

 

• Estimating Regression Predictive Distributions with Sample Networks

Ali Harakeh, Jordan Sir Kwang Hu, Naiqing Guan, Steven Waslander, Liam Paull

Proceedings of the AAAI Conference on Artificial Intelligence, Feb 2023, Washington DC, United States. pp.7830-7838, ⟨10.1609/aaai.v37i6.25948⟩

 

Proceedings

• Sample Boosting Algorithm (SamBA) -An Interpretable Greedy Ensemble Classifier Based On Local Expertise For Fat Data

Baptiste Bauvin, Cécile Capponi, Florence Clerc, Pascal Germain, Sokol Koço, Jacques Corbeil

Proceedings of Machine Learning Research, 216, pp.130-140, 2023, Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence

 

• Mutation Testing of Deep Reinforcement Learning Based on Real Faults

Florian Tambon, Vahid Majdinasab, Amin Nikanjam, Foutse Khomh, Giuliano Antoniol

IEEE, pp.188-198, 2023, ⟨10.1109/ICST57152.2023.00026⟩

 

Preprints, Working Papers, …

• Deploying Deep Reinforcement Learning Systems: A Taxonomy of Challenges

Ahmed Haj Yahmed, Altaf Allah Abbassi, Amin Nikanjam, Heng Li, Foutse Khomh 2023

 

• An Intentional Forgetting-Driven Self-Healing Method For Deep Reinforcement Learning Systems

Ahmed Haj Yahmed, Rached Bouchoucha, Houssem Ben Braiek, Foutse Khomh, 2023

 

• Oblivious Turing Machine

Sofiane Azogagh, Victor Delfour, Marc-Olivier Killijian 2023

 

• HOMRS: High Order Metamorphic Relations Selector for Deep Neural Networks

Florian Tambon, Giulio Antoniol, Foutse Khomh 2023

 

• RKHS Weightings of Functions

Gabriel Dubé, Mario Marchand 2023

 

• Understanding Interventional TreeSHAP : How and Why it Works

Gabriel Laberge, Yann Batiste Pequignot 2023

 

• Partial Order in Chaos: Consensus on Feature Attributions in the Rashomon Set

Gabriel Laberge, Yann Pequignot, Foutse Khomh, Mario Marchand, Alexandre Mathieu, 2023

 

• Crypto’Graph: Leveraging Privacy-Preserving Distributed Link Prediction for Robust Graph Learning

Sofiane Azogagh, Zelma Aubin Birba, Sébastien Gambs, Marc-Olivier Killijian, 2023

 

• Out-of-distribution detection for regression tasks: parameter versus predictor entropy

Yann Pequignot, Mathieu Alain, Patrick Dallaire, Alireza Yeganehparast, Pascal Germain, Josée Desharnais, François Laviolette 2023

 

• Revisiting column-generation-based matheuristic for learning classification trees

Krunal Kishor Patel, Guy Desaulniers, Andrea Lodi 2023

 

• Learning Hybrid Interpretable Models: Theory, Taxonomy, and Methods

Julien Ferry, Gabriel Laberge, Ulrich Aïvodji 2023

 

2022

Journal articles

• DiverGet: a Search-Based Software Testing approach for Deep Neural Network Quantization assessment

Ahmed Haj Yahmed, Houssem Ben Braiek, Foutse Khomh, Sonia Bouzidi, Rania Zaatour

Empirical Software Engineering, 2022, 27 (7), pp.193. ⟨10.1007/s10664-022-10202-w⟩

 

• PROBONITE: PRivate One-Branch-Only Non-Interactive decision Tree Evaluation

Sofiane Azogagh, Victor Delfour, Sébastien Gambs, Marc-Olivier Killijian

WAHC’22: Proceedings of the 10th Workshop on Encrypted Computing & Applied Homomorphic Cryptography, 2022, pp.23-33. ⟨10.1145/3560827.3563377⟩

 

• How to certify machine learning based safety-critical systems? A systematic literature review

Florian Tambon, Gabriel Laberge, Le An, Amin Nikanjam, Paulina Stevia Nouwou Mindom, Yann Pequignot, Foutse Khomh, Giulio Antoniol, Ettore Merlo, François Laviolette

Automated Software Engineering, 2022, 29 (2), pp.38. ⟨10.1007/s10515-022-00337-x⟩

 

• Faults in deep reinforcement learning programs: a taxonomy and a detection approach

Amin Nikanjam, Mohammad Mehdi Morovati, Foutse Khomh, Houssem Ben Braiek

Automated Software Engineering, 2022, 29 (1), pp.8. ⟨10.1007/s10515-021-00313-x⟩

 

Conference papers

• Characterizing the risk of fairwashing

Ulrich Aïvodji, Hiromi Arai, Sébastien Gambs, Satoshi Hara

Advances in Neural Information Processing Systems 34 (NeurIPS 2021), Dec 2022, New Orleans (Louisiana), United States. pp.14822–14834, ⟨10.48550/arXiv.2106.07504⟩

 

• SmOOD: Smoothness-based Out-of-Distribution Detection Approach for Surrogate Neural Networks in Aircraft Design

Houssem Ben Braiek, Ali Tfaily, Foutse Khomh, Thomas Reid, Ciro Guida

ASE ’22: 37th IEEE/ACM International Conference on Automated Software Engineering, Oct 2022, Rochester, MI, United States. pp.1-13, ⟨10.1145/3551349.3556936⟩

 

• An Empirical Study of Challenges in Converting Deep Learning Models

Moses Openja, Amin Nikanjam, Ahmed Haj Yahmed, Foutse Khomh, Zhen Ming Jack Jiang

2022 IEEE International Conference on Software Maintenance and Evolution (ICSME), Oct 2022, Limassol, Cyprus. pp.13-23, ⟨10.1109/ICSME55016.2022.00010⟩

 

• Studying the Practices of Deploying Machine Learning Projects on Docker

Moses Openja, Forough Majidi, Foutse Khomh, Bhagya Chembakottu, Heng Li

EASE 2022: The International Conference on Evaluation and Assessment in Software Engineering 2022, Jun 2022, Gothenburg, Sweden. pp.190-200, ⟨10.1145/3530019.3530039⟩

 

• Identification of out-of-distribution cases of CNN using class-based surprise adequacy

Mira Marhaba, Ettore Merlo, Foutse Khomh, Giuliano Antoniol

CAIN ’22: 1st Conference on AI Engineering – Software Engineering for AI, May 2022, Pittsburgh Pennsylvania, United States. pp.39-40, ⟨10.1145/3522664.3528617⟩

 

• Sample Efficient Deep Reinforcement Learning via Uncertainty Estimation

Vincent Mai, Kaustubh Mani, Liam Paull, International Conference on Learning Representations (ICLR 2022), Apr 2022, Virtual conference, Unknown Region. ⟨10.48550/arXiv.2201.01666⟩

 

2021

Journal articles

• Automatic Fault Detection for Deep Learning Programs Using Graph Transformations

Amin Nikanjam, Houssem Ben Braiek, Mohammad Mehdi Morovati, Foutse Khomh

ACM Transactions on Software Engineering and Methodology, In press

 

Conference papers

• Batch Inverse-Variance Weighting: Deep Heteroscedastic Regression

Vincent Mai, Waleed Khamies, Liam Paull

ICML 2021 Workshop on Uncertainty & Robustness in Deep Learning, Jul 2021, Virtual, Unknown Region. ⟨10.48550/arXiv.2107.04497⟩

 

2020

Conference papers

• Models of Computational Profiles to Study the Likelihood of DNN Metamorphic Test Cases

Ettore Merlo, Mira Marhaba, Foutse Khomh, Houssem Ben Braiek, Giuliano Antoniol

iMLSE 2020 2nd International Workshop on Machine Learning Systems Engineering​ ​, Dec 2020, Singapore, Singapore. ⟨10.48550/arXiv.2107.13491⟩