Amin Nikanjam

Amin Nikanjam

Research Associate at Polytechnique Montréal

Publications

LLM-based Code Generation

  1. Majdinasab, V., Nikanjam, A., and Khomh, F., Trained Without My Consent: Detecting Code Inclusion In Language Models Trained on Code, Accepted by ACM Transactions on Software Engineering and Methodology (TOSEM) [IF:6.6], 2024. View
  2. Tambon, F., Nikanjam, A., Khomh, F., and Antoniol, G., Assessing Programming Task Difficulty for Efficient Evaluation of Large Language Models, 2024. View
  3. Majdinasab, V., Nikanjam, A., and Khomh, F., DeepCodeProbe: Towards Understanding What Models Trained on Code Learn, 2024. View
  4. Tambon, F., Moradi Dakhel, A., Nikanjam, A., Khomh, F., Desmarais, M. C., and Antoniol, G., Bugs in Large Language Models Generated Code: An Empirical Study, 2024. View
  5. Moradi Dakhel, A., Nikanjam, A., Majdinasab, V., Khomh, F., and Desmarais, M. C., Effective Test Generation Using Pre-trained Large Language Models and Mutation Testing, Information and Software Technology [IF:3.862], 107468, Elsevier, 2024. View
  6. Moradi Dakhel, A., Nikanjam, A., Khomh, F., Desmarais, M.C., Washizaki, H., An Overview on Large Language Models. In: Nguyen-Duc, A., Abrahamsson, P., Khomh, F. (eds) Generative AI for Effective Software Development. Springer, 2024. View
  7. Moradi Dakhel, A., Nikanjam, A., Khomh, F., Desmarais, M.C., Washizaki, H., Generative AI for Software Development: A Family of Studies on Code Generation. In: Nguyen-Duc, A., Abrahamsson, P., Khomh, F. (eds) Generative AI for Effective Software Development. Springer, 2024. View
  8. Moradi Dakhel, A., Majdinasab, V., Nikanjam, A., Khomh, F., Desmarais, M. C., and Jiang, Z., GitHub Copilot AI pair programmer: Asset or Liability?, Journal of Systems and Software [IF:3.514], 203, 111734, Elsevier, 2023. View

Bugs and design smells in ML

  1. Côté, P.O., Nikanjam, A., Bouchoucha, R., Basta, I, Abidi, M., and Khomh, F., Quality issues in Machine Learning Software Systems, International Journal of Empirical Software Engineering [IF:3.762], 29, Article 149, 2024. View
  2. Vidgen, B., Agrawal, A., Ahmed, A.M., …, Nikanjam, A., …, and Vanschoren, J., Introducing v0.5 of the AI Safety Benchmark from MLCommons, 2024. View
  3. Bouchoucha, R., Yahmed, A.H., Patil, D., Rajendran, J., Nikanjam, A., Chandar, S. and Khomh, F., Toward Debugging Deep Reinforcement Learning Programs with RLExplorer, Accepted by IEEE International Conference on Software Maintenance and Evolution (ICSME), IEEE, 2024.
  4. Morovati, M.M., Tambon, F., Taraghi, M., Nikanjam, A., Khomh, F., Common Challenges of Deep Reinforcement Learning Applications Development: An Empirical Study, International Journal of Empirical Software Engineering [IF:4.1], 29, Article 95, Springer, 2024. View
  5. Tambon, F., Nikanjam, A., An, L., Khomh, F., and Antoniol, G., Silent Bugs in Deep Learning Frameworks: An Empirical Study of Keras and TensorFlow, International Journal of Empirical Software Engineering [IF:4.1], 29, Article 10, Springer, 2024. View
  6. Morovati, M.M., Nikanjam, A., Tambon, F., Khomh, F. and Jiang, Z, Bug Characterization in Machine Learning-based Systems, International Journal of Empirical Software Engineering [IF:4.1], 29, Article 14, Springer, 2024. View
  7. Yahmed, A.H., Abbassi, A.A., Nikanjam, A., Li, H. and Khomh, F., Deploying Deep Reinforcement Learning Systems: A Taxonomy of Challenges, IEEE International Conference on Software Maintenance and Evolution (ICSME), pp. 26-38, IEEE, 2023. View
  8. Tambon, F., Majdinasab, V., Nikanjam, A., Khomh, F., Antoniol, G., Mutation Testing of Deep Reinforcement Learning Based on Real Faults, 16th IEEE International Conference on Software Testing, Verification and Validation (ICST), pp. 188-198, 2023. View
  9. Morovati, M.M., Nikanjam, A., Khomh, F. and Jiang, Z., Bugs in Machine Learning-based Systems: A Faultload Benchmark, International Journal of Empirical Software Engineering [IF:3.762], 28, Article 62, Springer, 2023. View
  10. Nikanjam, A., Morovati, M.M., Khomh, F. and Ben Braiek, H., Faults in deep reinforcement learning programs: a taxonomy and a detection approach, Automated Software Engineering [IF:1.677], 29(1), pp.1-32. 2022. View
  11. Openja, M., Nikanjam, A., Yahmed, A.H., Khomh, F. and Jiang, Z., An Empirical Study of Challenges in Converting Deep Learning Models, IEEE International Conference on Software Maintenance and Evolution (ICSME), pp. 13-23, IEEE, 2022. View
  12. Nikanjam, A., Braiek, H.B., Morovati, M.M. and Khomh, F., Automatic fault detection for deep learning programs using graph transformations, ACM Transactions on Software Engineering and Methodology (TOSEM) [IF:3.685], 31(1), pp.1-27. 2021. View
  13. Nikanjam, A., Khomh, F., Design smells in Deep Learning programs: an Empirical Study, IEEE International Conference on Software Maintenance and Evolution (ICSME), pp. 332-342, IEEE, 2021. View
  14. Rivera-Landos, E., Khomh, F. and Nikanjam, A., The challenge of reproducible ML: an empirical study on the impact of bugs, IEEE 21st International Conference on Software Quality, Reliability and Security (QRS), pp. 1079-1088, IEEE, 2021. View

Certification of ML-based systems

  1. Tambon, F., Laberge, G., An, L., Nikanjam, A., Mindom, P.S.N., Pequignot, Y., Khomh, F., Antoniol, G., Merlo, E. and Laviolette, F., How to certify machine learning based safety-critical systems? A systematic literature review, Automated Software Engineering [IF:1.677], 29(2), pp.1-74. 2022. View
  2. Mindom, P.S.N., Nikanjam, A., Khomh, F. and Mullins, J., On Assessing The Safety of Reinforcement Learning Algorithms Using Formal Methods, IEEE 21st International Conference on Software Quality, Reliability and Security (QRS), pp. 260-269, IEEE, 2021. View

ML and EC for SE

  1. Côté, P-O., Nikanjam, A., Ahmed, N., Humeniuk, D., Khomh, F., Data Cleaning and Machine Learning: A Systematic Literature Review, Automated Software Engineering [IF:3.4], 31, Article 54, 2024. View
  2. Mindom, P.S.N., Nikanjam, A., and Khomh, F., Harnessing Pre-trained Generalist Agents for Software Engineering Tasks, 2024. View
  3. Mindom, P.S.N., Nikanjam, A., and Khomh, F., A Comparison of Reinforcement Learning Frameworks for Software Testing Tasks, International Journal of Empirical Software Engineering [IF:3.762], 28, Article 111, Springer, 2023. View
  4. Jamshidi, S., Nikanjam, A., Hamdaqa, M.A., Khomh, F., Attack Detection by Using Deep Learning for Cyber-Physical System, In: Traore, I., Woungang, I., Saad, S. (eds) Artificial Intelligence for Cyber-Physical Systems Hardening. Engineering Cyber-Physical Systems and Critical Infrastructures, vol 2. Springer, 2023. View
  5. Roy, S., Laberge, G., Roy, B., Khomh, F., Nikanjam, A., and Mondal, S., Why Don’t XAI Techniques Agree? Characterizing the Disagreements Between Post-hoc Explanations of Defect Predictions, IEEE International Conference on Software Maintenance and Evolution (ICSME), pp. 444-448, IEEE, 2022. View
  6. Pira, E., Rafe, V., Nikanjam, A., Using Evolutionary Algorithms for Reachability Analysis of Complex Software Systems Specified through Graph Transformation, Reliability Engineering & System Safety [IF:7.247], 191, Article 106577, Elsevier, 2019. View
  7. Pira, E., Rafe, V., Nikanjam, A., Searching for Violation of Safety and Liveness Properties Using Knowledge Discovery in Complex Systems Specified through Graph Transformations, Information and Software Technology [IF:3.862], 97, pp.110-134, Elsevier, 2018. View
  8. Pira, E., Rafe, V., Nikanjam, A., Deadlock Detection in Complex Software Systems Specified through Graph Transformation Using Bayesian Optimization Algorithm, Journal of Systems and Software [IF:3.514], 131, pp.181-200, Elsevier, 2017. View
  9. Pira, E., Rafe, V., Nikanjam, A., EMCDM: Efficient Model Checking by Data Mining for Verification of Complex Software Systems Specified through Architectural Styles, Applied Soft Computing [IF:8.263], 49, pp.1185-1201, Elsevier, 2016. View
  10. Rafe, V., Moradi, M., Yousefian, R., Nikanjam, A., A Meta-Heuristic Solution for Automated Refutation of Complex Software Systems Specified Through Graph Transformations, Applied Soft Computing [IF:8.263], 33, pp.136-149, Elsevier, 2015. View
  11. Rafe, V., Paiandeha, Z., Nikanjam, A., A Hybrid Optimization Algorithm Based on Harmony Search and Differential Evolution for Continuous Domain, Journal of Intelligent and Fuzzy Systems (JIFS) [IF:1.737], 29, pp.2169-2176, IOS Press, 2015. View

AI (ML and EC)

  1. Shajoonnezhad, N., Nikanjam, A., A stochastic variance-reduced coordinate descent algorithm for learning sparse Bayesian network from discrete high-dimensional data, International Journal of Machine Learning and Cybernetics [IF:4.377], 2022. View
  2. Mahdavimoghadam, M., Nikanjam, A. and Abdoos, M., Improved reinforcement learning in cooperative multi-agent environments using knowledge transfer, The Journal of Supercomputing [IF:2.557], 78(8), pp.10455-10479. 2022. View
  3. Fozuni, M., Nikanjam, A. and Aliyari Shoorehdeli, M., Stability analysis of the particle dynamics in bat algorithm: standard and modified versions, Engineering with Computers [IF:8.083], 37(4), pp.2865-2876. 2021. View
  4. Fozuni, M., Farzi, S., Nikanjam, A., MDPCluster: A Swarm-based Community Detection Algorithm in Large-Scale Graphs, Computing [IF:2.420], 102, pp.893–922, Springer, 2020. View
  5. Saleh-Sedghpour, A., Nikanjam, A., Overlapping Community Detection in Social Networks Using a Quantum-based Genetic Algorithm, Genetic and Evolutionary Computation Conference (GECCO2017), 197-198, Berlin, Germany, ACM, 2017. View
  6. Nikanjam, A., Karshenas, H., Multi-Structure Problems: Difficult Model Learning in Discrete EDAs, IEEE Congress on Evolutionary Computation (CEC2016), 3448-3454, Vancouver, Canada, IEEE, 2016. View
  7. Sharifi, H., Nikanjam, A., Karshenas, H., Najimi, N., Complexity of Model Learning in EDAs: Multi-Structure Problems, Genetic and Evolutionary Computation Conference (GECCO2014), 55-56, Vancouver, Canada, ACM, 2014. View
  8. Nikanjam, A., Rahmani, A., Exploiting Bivariate Dependencies to Speedup Structure Learning in Bayesian Optimization Algorithm, Journal of Computer Science and Technology [IF:1.871], 27, pp.1077-1090, Springer, 2012. View
  9. Nikanjam, A., Sharifi, H., Rahmani, A., Efficient Model Building in Competent Genetic Algorithm Using DSM Clustering, AI Communications [IF:1.029], 24, pp.213-231, IOS Press, 2011. View
  10. Rafe, V., Nikanjam, A., Rezaei, M., Galoan: A Multi-Agent Approach to Herd Cows, Annals of Mathematics and Artificial Intelligence [IF:1.019], pp.333-348, Springer, 2011. View
  11. Sharifi, H., Nikanjam, A., Rahmani, A., Interaction Detection for Hybrid Decomposable Problems, Genetic and Evolutionary Computation Conference (GECCO2011), 1203-1210, Dublin, Ireland, ACM, 2011. View
  12. Nikanjam, A., Sharifi, H., Helmi, B.H., Rahmani, A., Enhancing the Efficiency of Genetic Algorithm by Identifying Linkage Groups Using DSM Clustering, IEEE Congress on Evolutionary Computation (CEC2010), 1-8, Barcelona, Spain, IEEE, 2010. View
  13. Nikanjam, A., Sharifi, H., Helmi, B.H., Rahmani, A., A New DSM Clustering Algorithm for Linkage Groups Identification, Genetic and Evolutionary Computation Conference (GECCO2010), 367-368, Portland, USA, ACM, 2010. View
  14. Karshenas, H, Nikanjam, A., Helmi, B.H., Rahmani, A., Combinatorial Effects of Local Structures and Scoring Metrics in Bayesian Optimization Algorithm, ACM/SIGEVO Summit on Genetic and Evolutionary Computation, 263-270, Shanghai, China, ACM, 2009. View
  15. Karshenas, H, Nikanjam, A., Helmi, B.H., Rahmani, A., Model Accuracy for Hierarchical Problems, IEEE International Conference on Intelligent Computing and Intelligent Systems (ICIS2009), 852-856, Shanghai, China, IEEE, 2009. View
  16. Rahmani, A., Saberi, A., Mohammadi, M., Nikanjam, A., AdeliMosabbeb, E., Abdoos, M., SHABaN Multi-Agent Team to Herd Cows, International Workshop on Programming Multi-Agent Systems (ProMAS), 248-252, Estoril, Portugal, Springer, 2008. View
  17. Mohammadi, M., Nikanjam, A., Rahmani, A., An Evolutionary Approach to Clustering Ensemble, 4th International Conference on Natural Computation (ICNC’08), 77-82, Jinan, China, IEEE, 2008. View
  18. Nikanjam, A., Rahmani, A., The Anticipatory Classifier System for Function Approximation, 12th Annual International CSI Computer Conference (CSICC2007), 2388-2391, Tehran, Iran, 2007. View
  19. Nikanjam, A., Rahmani, A., An Anticipatory Approach to Improve XCSF, Genetic and Evolutionary Computation COnference (GECCO2006), 1595-1596, Seattle, USA, ACM, 2006. View
  20. Dezfoulian, M., Kaviani, N., Nikanjam, A., Rafaee, M., Training a Simulated Soccer Agent How to Shoot Using Artificial Neural Network, 13th Multi-disciplinary Iranian Researchers Conference in Europe (IRCE), Leeds, UK, 2005. View