Contrasting Explanations in Machine Learning. Efficiency, Robustness & Applications
Artelt A (2024)
Bielefeld: Universität Bielefeld.
postdoc
aartelt@techfak.uni-bielefeld.de +49 521 106-12147Room: CITEC 2-109
André Artelt studied B.Sc. Congnitive Informatics (2017) and M.Sc. Intelligent Systems (2019) at Bielefeld University.
Since 2019 he is a researcher in the Machine Learning group at Bielefeld University. Prior to that he spent some time in industry working in the software development department at Schüco International KG (2013-2019).
His primary area of research is trustworthy AI, and his secondary area of research is AI for critical infrastructure. He mainly focuses on eXplainable AI (XAI) — in particular on contrasting explanations. Besides fundamental research, he also works on applications of XAI, such as to water distribution networks, transportation, and decision support systems for business owners.
Contrasting Explanations in Machine Learning. Efficiency, Robustness & Applications
Artelt A (2024)
Bielefeld: Universität Bielefeld.
Kuhl U, Artelt A, Hammer B (2023)
Frontiers in Computer Science 5: 1087929.
Unsupervised Unlearning of Concept Drift with Autoencoders
Artelt A, Malialis K, Panayiotou CG, Polycarpou MM, Hammer B (2023)
In: 2023 IEEE Symposium Series on Computational Intelligence (SSCI). IEEE: 703-710.
Spatial Graph Convolution Neural Networks for Water Distribution Systems
Ashraf I, Hermes L, Artelt A, Hammer B (2023)
In: Advances in Intelligent Data Analysis XXI. 21st International Symposium on Intelligent Data Analysis, IDA 2023, Louvain-la-Neuve, Belgium, April 12–14, 2023, Proceedings. Crémilleux B, Hess S, Nijssen S (Eds); Lecture Notes in Computer Science. Cham: Springer Nature Switzerland: 29-41.
Kuhl U, Artelt A, Hammer B (2023)
In: Explainable Artificial Intelligence. First World Conference, xAI 2023, Lisbon, Portugal, July 26–28, 2023, Proceedings, Part III. Longo L (Ed); Communications in Computer and Information Science. Cham: Springer Nature Switzerland: 280-300.
"I do not know! but why?"- Local model-agnostic example-based explanations of reject
Artelt A, Visser R, Hammer B (2023)
Neurocomputing 558: 126722.
Adversarial Attacks on Leakage Detectors in Water Distribution Networks
Stahlhofen P, Artelt A, Hermes L, Hammer B (2023)
In: Advances in Computational Intelligence. 17th International Work-Conference on Artificial Neural Networks, IWANN 2023, Ponta Delgada, Portugal, June 19–21, 2023, Proceedings, Part II. Rojas I, Joya G, Catala A (Eds); Lecture Notes in Computer Science. Cham: Springer Nature Switzerland: 451-463.
Interpretable SAM-kNN Regressor for Incremental Learning on High-Dimensional Data Streams
Jakob J, Artelt A, Hasenjäger M, Hammer B (2023)
Applied Artificial Intelligence 37(1): 2198846.
"Why Here and not There?": Diverse Contrasting Explanations of Dimensionality Reduction
Artelt A, Schulz A, Hammer B (2023)
In: Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods. Setúbal, Portugal: SCITEPRESS - Science and Technology Publications: 27-38.
Contrasting Explanations for Understanding and Regularizing Model Adaptations
Artelt A, Hinder F, Vaquet V, Feldhans R, Hammer B (2022)
Neural Processing Letters 55: 5273–5297.
Artelt A, Geminn C, Hammer B, Manzeschke A, Mavrina L, Weber C (2022)
DuEPublico: Duisburg-Essen Publications online, University of Duisburg-Essen, Germany.
Localization of Concept Drift: Identifying the Drifting Datapoints
Hinder F, Vaquet V, Brinkrolf J, Artelt A, Hammer B (2022)
In: 2022 International Joint Conference on Neural Networks (IJCNN). IEEE: 1-9.
SAM-kNN Regressor for Online Learning in Water Distribution Networks
Jakob J, Artelt A, Hasenjäger M, Hammer B (2022)
In: Artificial Neural Networks and Machine Learning – ICANN 2022. 31st International Conference on Artificial Neural Networks, Bristol, UK, September 6–9, 2022, Proceedings, Part III. Pimenidis E, Angelov P, Jayne C, Papaleonidas A, Aydin M (Eds); Lecture Notes in Computer Science, 13531. Cham: Springer Nature : 752-762.
“Even if …” – Diverse Semifactual Explanations of Reject
Artelt A, Hammer B (2022)
In: 2022 IEEE Symposium Series on Computational Intelligence (SSCI). Ishibuchi H (Ed); Piscataway, NJ: IEEE: 854-859.
Explaining Reject Options of Learning Vector Quantization Classifiers
Artelt A, Brinkrolf J, Visser R, Hammer B (2022)
In: Proceedings of the 14th International Joint Conference on Computational Intelligence. SCITEPRESS - Science and Technology Publications: 249-261.
Kuhl U, Artelt A, Hammer B (2022)
In: 2022 ACM Conference on Fairness, Accountability, and Transparency. New York, NY, USA: ACM: 2125-2137.
Localization of Concept Drift: Identifying the Drifting Datapoints
Hinder F, Vaquet V, Brinkrolf J, Artelt A, Hammer B (2022) .
One Explanation to Rule them All — Ensemble Consistent Explanations
Artelt A, Vrachimis S, Eliades D, Polycarpou M, Hammer B (2022)
ArXiv:2205.08974 .
Taking care of our drinking water: Dealing with Sensor Faults in Water Distribution Networks
Vaquet V, Artelt A, Brinkrolf J, Hammer B (2022)
Presented at the 31st International Conference on Artificial Neural Networks, Bristol.
Explainable Artificial Intelligence for Improved Modeling of Processes
Velioglu R, Göpfert JP, Artelt A, Hammer B (2022)
In: Intelligent Data Engineering and Automated Learning – IDEAL 2022. 23rd International Conference, IDEAL 2022, Manchester, UK, November 24–26, 2022, Proceedings. Yin H, Camacho D, Tino P (Eds); Lecture Notes in Computer Science, 13756. Cham: Springer International Publishing: 313-325.
Convex optimization for actionable & plausible counterfactual explanations
Artelt A, Hammer B (2021)
arXiv: 2105.07630v1.
Efficient computation of contrastive explanations
Artelt A, Hammer B (2021)
In: 2021 International Joint Conference on Neural Networks (IJCNN). New York: Institute of Electrical and Electronics Engineers (IEEE): 1-9.
Contrastive Explanations for Explaining Model Adaptations
Artelt A, Hinder F, Vaquet V, Feldhans R, Hammer B (2021)
In: Advances in Computational Intelligence. 16th International Work-Conference on Artificial Neural Networks, IWANN 2021, Virtual Event, June 16–18, 2021, Proceedings, Part I. Rojas I, Joya G, Catala A (Eds); Lecture Notes in Computer Science. Cham: Springer : 101-112.
Szczuka J, Artelt A, Geminn C, Hammer B, Kopp S, Manzeschke A, Rossnagel A, Slawik P, Strathmann C, Szymczyk N, Varonina L, et al. (2021)
Essen: Universität Duisburg-Essen, Universitätsbibliothek.
Artelt A, Hammer B (2021)
Neurocomputing 470(VSI: ESANN 2020): 304-317.
Evaluating Robustness of Counterfactual Explanations
Artelt A, Vaquet V, Velioglu R, Hinder F, Brinkrolf J, Schilling M, Hammer B (2021)
In: 2021 IEEE Symposium Series on Computational Intelligence (SSCI). Piscataway, NJ: IEEE: 01-09.
Improving and Evaluating Conversational User Interfaces for Children
Krämer N, Szczuka J, Rossnagel A, Geminn C, Kopp S, Hammer B, Mavrina L, Artelt A, Manzeschke A, Weber C (2020)
In: IUI '20: Proceedings of the 25th International Conference on Intelligent User Interfaces. New York: Association for Computing Machinery.
Kinder als Nutzende smarter Sprachassistenten Spezieller Gestaltungsbedarf zum Schutz von Kindern
Geminn CL, Szczuka J, Weber C, Artelt A, Varonina L (2020)
Datenschutz und Datensicherheit - DuD 44(9): 600-605.
Hinder F, Artelt A, Hammer B (2020)
In: Proceedings of the 37th International Conference on Machine Learning.
Efficient computation of counterfactual explanations of LVQ models
Artelt A, Hammer B (2020)
In: ESANN 2020 - proceedings. Verleysen M (Ed); Louvain-la-Neuve: Ciaco : 19-24.
Convex Density Constraints for Computing Plausible Counterfactual Explanations
Artelt A, Hammer B (2020)
In: Artificial Neural Networks and Machine Learning - ICANN 2020 - 29th International Conference on Artificial Neural Networks, Bratislava, Slovakia, September 15-18, 2020, Proceedings, Part {I}. Farkas I, Masulli P, Wermter S (Eds); Lecture Notes in Computer Science, 12396. Cham: Springer: 353-365.
On the computation of counterfactual explanations - A survey
Artelt A, Hammer B (2019)
arXiv: 1911.07749v1.
CEML - Counterfactuals for Explaining Machine Learning models - A Python toolbox
Artelt A (2019)
Bielefeld University.
Continuous online user authentication based on keystroke dynamics
Artelt A, Jakob J, Vaquet V (2019)
Presented at the Interdisciplinary College (IK), Günne/Möhnesee, Germany.
Lecture Notes on Applied Optimization
Paaßen B, Artelt A, Hammer B (2019)
Faculty of Technology, Bielefeld University.
Krämer N, Artelt A, Geminn C, Hammer B, Kopp S, Manzeschke A, Rossnagel A, Slawik P, Szczuka J, Varonina L, Weber C (2019)
Universität Duisburg-Essen, Universitätsbibliothek.
Introduction to Machine Learning - Supplementary notes
Artelt A (2019) .