Foutse Khomh

houssem.ben-braiek@polymtl.ca

Biographie

Foutse Khomh est professeur titulaire de génie logiciel à Polytechnique Montréal, titulaire d'une chaire en IA Canada-CIFAR dans le domaine des systèmes logiciels d'apprentissage automatique fiables, et titulaire d'une chaire de recherche FRQ-IVADO sur l'assurance qualité des logiciels pour les applications d'apprentissage automatique.

Il a obtenu un doctorat en génie logiciel de l'Université de Montréal en 2011, avec une bourse d'excellence. Il a également reçu le prix CS-Can/Info-Can du meilleur jeune chercheur en informatique en 2019. Ses recherches portent sur la maintenance et l'évolution des logiciels, l'ingénierie des systèmes d'apprentissage automatique, l'ingénierie en nuage et l’IA/apprentissage automatique fiable et digne de confiance.

Ses travaux ont été récompensés par quatre prix de l’article le plus important Most Influential Paper en dix ans et six prix du meilleur article ou de l’article exceptionnel (Best/Distinguished Paper). Il a également siégé au comité directeur de plusieurs conférences et rencontres : SANER (comme président), MSR, PROMISE, ICPC (comme président) et ICSME (en tant que vice-président). Il a initié et coorganisé le symposium Software Engineering for Machine Learning Applications (SEMLA) et la série d'ateliers Release Engineering (RELENG).

Il est cofondateur du projet CRSNG CREATE SE4AI : A Training Program on the Development, Deployment, and Servicing of Artificial Intelligence-based Software Systems et l'un des chercheurs principaux du projet Dependable Explainable Learning (DEEL). Il est également cofondateur de l'initiative québécoise sur l'IA digne de confiance (Confiance IA Québec). Il fait partie du comité de rédaction de plusieurs revues internationales de génie logiciel (dont IEEE Software, EMSE, JSEP) et est membre senior de l'Institute of Electrical and Electronics Engineers (IEEE).

Étudiants actuels

Houssem Ben Braiek

Postdoctorat - Polytechnique

Doctorat - Polytechnique

forough.majidi@mila.quebec

Site web

anthonia-oluchukwu.njoku@mila.quebec

Anthonia Oluchukwu Njoku

Doctorat - Polytechnique

khouloud.oueslati@mila.quebec

Khouloud Oueslati

Maîtrise recherche - Polytechnique

Arian Qazvini

Maîtrise recherche - Polytechnique

arian.qazvini@mila.quebec

Site web

Github

Elnathan Tiokou Tiokou Fangang

Maîtrise recherche - Polytechnique

elnathan.tiokou@mila.quebec

Ben Braiek Yasmine

Maîtrise recherche - Polytechnique

yasmine.ben-braiek@mila.quebec

Publications

A Taxonomy of Inefficiencies in LLM-Generated Python Code

Altaf Allah Abbassi

Leuson Da Silva

Amin Nikanjam

Large Language Models (LLMs) are widely adopted for automated code generation with promising results. Although prior research has assessed L… (voir plus)LM-generated code and identified various quality issues- such as redundancy, poor maintainability, and sub-optimal performance- a systematic understanding and categorization of these inefficiencies remain unexplored. Therefore, we empirically investigate inefficiencies in LLM-generated Python code by state-of-the-art models, i.e., CodeLlama, DeepSeek-Coder, and CodeGemma. To do so, we manually analyze 492 generated Python code snippets in the HumanEval+ dataset. We then construct a taxonomy of inefficiencies in LLM-generated Python code that includes 5 categories (General Logic, Performance, Readability, Maintainability, and Errors) and 19 subcategories of inefficiencies. We validate the obtained taxonomy through an online survey with 58 LLM practitioners and researchers. The surveyed participants affirmed the completeness of the proposed taxonomy, and the relevance and the popularity of the identified code inefficiency patterns. Our qualitative findings indicate that inefficiencies are diverse and interconnected, affecting multiple aspects of code quality, with logic and performance-related inefficiencies being the most frequent and often co-occurring while impacting overall code quality. Our taxonomy provides a structured basis for evaluating the quality of LLM-generated code and guiding future research to improve code generation efficiency.

2024-12-31

ICSME (publié)

Towards Enhancing the Reproducibility of Deep Learning Bugs: An Empirical Study

Mehil B. Shah

Mohammad Masudur Rahman

2024-12-31

Empir. Softw. Eng. (publié)

Trained Without My Consent: Detecting Code Inclusion In Language Models Trained on Code

Vahid Majdinasab

Amin Nikanjam

Code auditing ensures that the developed code adheres to standards, regulations, and copyright protection by verifying that it does not cont… (voir plus)ain code from protected sources. The recent advent of Large Language Models (LLMs) as coding assistants in the software development process poses new challenges for code auditing. The dataset for training these models is mainly collected from publicly available sources. This raises the issue of intellectual property infringement as developers' codes are already included in the dataset. Therefore, auditing code developed using LLMs is challenging, as it is difficult to reliably assert if an LLM used during development has been trained on specific copyrighted codes, given that we do not have access to the training datasets of these models. Given the non-disclosure of the training datasets, traditional approaches such as code clone detection are insufficient for asserting copyright infringement. To address this challenge, we propose a new approach, TraWiC; a model-agnostic and interpretable method based on membership inference for detecting code inclusion in an LLM's training dataset. We extract syntactic and semantic identifiers unique to each program to train a classifier for detecting code inclusion. In our experiments, we observe that TraWiC is capable of detecting 83.87% of codes that were used to train an LLM. In comparison, the prevalent clone detection tool NiCad is only capable of detecting 47.64%. In addition to its remarkable performance, TraWiC has low resource overhead in contrast to pair-wise clone detection that is conducted during the auditing process of tools like CodeWhisperer reference tracker, across thousands of code snippets.

2024-12-31

ACM Trans. Softw. Eng. Methodol. (publié)

Editorial: Special Issue on Software Engineering and AI for Data Quality

Andreas Metzger

Phu Nguyen

Sagar Sen

This editorial summarizes the content of the Special Issue on Software Engineering and AI for Data Quality of the Journal of Data and Inform… (voir plus)ation Quality (JDIQ).

2024-12-18

Journal of Data and Information Quality (publié)

Leveraging Data Characteristics for Bug Localization in Deep Learning Programs

Ruchira Manke

Mohammad Wardat

Hridesh Rajan

Deep Learning (DL) is a class of machine learning algorithms that are used in a wide variety of applications. Like any software system, DL p… (voir plus)rograms can have bugs. To support bug localization in DL programs, several tools have been proposed in the past. As most of the bugs that occur due to improper model structure known as structural bugs lead to inadequate performance during training, it is challenging for developers to identify the root cause and address these bugs. To support bug detection and localization in DL programs, in this paper, we propose Theia, which detects and localizes structural bugs in DL programs. Unlike the previous works, Theia considers the training dataset characteristics to automatically detect bugs in DL programs developed using two deep learning libraries, Keras and PyTorch . Since training the DL models is a time-consuming process, Theia detects these bugs at the beginning of the training process and alerts the developer with informative messages containing the bug's location and actionable fixes which will help them to improve the structure of the model. We evaluated Theia on a benchmark of 40 real-world buggy DL programs obtained from Stack Overflow . Our results show that Theia successfully localizes 57/75 structural bugs in 40 buggy programs, whereas NeuraLint, a state-of-the-art approach capable of localizing structural bugs before training localizes 17/75 bugs.

2024-12-15

ACM Transactions on Software Engineering and Methodology (publié)

Fault Localization in Deep Learning-based Software: A System-level Approach

Mohammad Mehdi Morovati

Amin Nikanjam

2024-11-11

ArXiv (prépublication)

Impact of LLM-based Review Comment Generation in Practice: A Mixed Open-/Closed-source User Study

Doriane Olewicki

Leuson Da Silva

Suhaib Mujahid

Arezou Amini

Benjamin Mah

Marco Castelluccio

Sarra Habchi

Bram Adams

2024-11-10

ArXiv (prépublication)

Towards Optimizing SQL Generation via LLM Routing

Mohammadhossein Malekpour

Nour Shaheen

Amine Mhedhbi

Text-to-SQL enables users to interact with databases through natural language, simplifying access to structured data. Although highly capabl… (voir plus)e large language models (LLMs) achieve strong accuracy for complex queries, they incur unnecessary latency and dollar cost for simpler ones. In this paper, we introduce the first LLM routing approach for Text-to-SQL, which dynamically selects the most cost-effective LLM capable of generating accurate SQL for each query. We present two routing strategies (score- and classification-based) that achieve accuracy comparable to the most capable LLM while reducing costs. We design the routers for ease of training and efficient inference. In our experiments, we highlight a practical and explainable accuracy-cost trade-off on the BIRD dataset.

2024-11-05

ArXiv (prépublication)

Doctoral Symposium Committee

Anthony Cleve

Christian Lange

Silvia Breu

Manar H. Alalfi

Mario Luca Bernardi

Cornelia Boldyreff

Marco D'Ambros

Simon Denier

Natalia Dragan

Ekwa Duala-Ekoko

Fausto Fasano

Adnane Ghannem

Carmine Gravino

Maen Hammad

Imed Hammouda

Salima Hassaine

Yue Jia

Zhen Ming (Jack) Jiang

Adam Kiezun … (voir 11 de plus)

Jay Kothari

Jonathan Memaitre

Naouel Moha

Rocco Oliveto

Denys Poshyvanyk

Michele Risi

Giuseppe Scanniello

Bonita Sharif

Andrew Sutton

Anis Yousefi

Eugenio Zimeo

Manar H. Alalfi Mario Luca Bernardi Cornelia Boldyreff Anthony Cleve Marco D'Ambros Simon Denier Natalia Dragan Ekwa Duala-Ekoko Fausto Fasa… (voir plus)no Adnane Ghannem Carmine Gravino Maen Hammad Imed Hammouda Salima Hassaine Yue Jia Zhen Ming Jiang Foutse Khomh Adam Kiezun Jay Kothari Jonathan Memaitre Naouel Moha Rocco Oliveto Denys Poshyvanyk Michele Risi Giuseppe Scanniello Bonita Sharif Andrew Sutton Anis Yousefi Eugenio Zimeo

2024-10-27

2024 IEEE 35th International Symposium on Software Reliability Engineering Workshops (ISSREW) (publié)

In-Simulation Testing of Deep Learning Vision Models in Autonomous Robotic Manipulators

Dmytro Humeniuk

Houssem Ben Braiek

Thomas Reid

2024-10-26

Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering (publié)

LIBS-Raman Multimodal Architecture for Automated Lunar Prospecting

Jérôme Pigeon

Richard Boudreault

Ahmed Ashraf

Pooneh Maghoul

2024-10-09

Earth and Space 2024 (publié)

Toward Debugging Deep Reinforcement Learning Programs with RLExplorer

Rached Bouchoucha

Ahmed Haj Yahmed

Darshan Patil

Janarthanan Rajendran

Amin Nikanjam

Sarath Chandar

Deep reinforcement learning (DRL) has shown success in diverse domains such as robotics, computer games, and recommendation systems. However… (voir plus), like any other software system, DRL-based software systems are susceptible to faults that pose unique challenges for debugging and diagnosing. These faults often result in unexpected behavior without explicit failures and error messages, making debugging difficult and time-consuming. Therefore, automating the monitoring and diagnosis of DRL systems is crucial to alleviate the burden on developers. In this paper, we propose RLExplorer, the first fault diagnosis approach for DRL-based software systems. RLExplorer automatically monitors training traces and runs diagnosis routines based on properties of the DRL learning dynamics to detect the occurrence of DRL-specific faults. It then logs the results of these diagnoses as warnings that cover theoretical concepts, recommended practices, and potential solutions to the identified faults. We conducted two sets of evaluations to assess RLExplorer. Our first evaluation of faulty DRL samples from Stack Overflow revealed that our approach can effectively diagnose real faults in 83% of the cases. Our second evaluation of RLExplorer with 15 DRL experts/developers showed that (1) RLExplorer could identify 3.6 times more defects than manual debugging and (2) RLExplorer is easily integrated into DRL applications.

2024-10-05

IEEE International Conference on Software Maintenance and Evolution (publié)