@inproceedings{6898, abstract = {The labeling process for supervised learning is costly and time-consuming, and is often impractical to scale due to real-world constraints. Active learning (AL) addresses this challenge by strategically selecting representative and informative data points to reduce labeling efforts. This paper focuses on an AL scenario in which only a very limited number of labels can be acquired. We propose an algorithm operating in two phases: (1) an exploration phase that prioritizes representative and diverse data points using density-driven criteria, and (2) an exploitation phase that combines predictive uncertainty with density weighting to select informative samples from densely populated regions. This enhances both representativeness and informativeness. Our results demonstrate significant improvements in model quality compared to other algorithms typically employed for this scenario, across various scenarios involving imbalanced data in classification tasks and skewness in regression tasks. Through this work, we aim to provide a new algorithm for this scenario and investigate general principles for AL. While most AL studies focus on either classification or regression, our work applies the algorithms to both. Therefore, we can analyze the differences between classification and regression problems and their effects on AL strategies. Furthermore, we explore different categories of AL criteria and their effectiveness in the low-budget regime. These results also provide insight into the cold-start problem, which involves selecting an initial labeled set and is faced by many model-based AL methods.}, author = {Jaster, Bjarne and Tharwat, Alaa and Sheikh, Eiram Mahera and Kohlhase, Martin and Schenck, Wolfram}, booktitle = {Machine Learning and Principles and Practice of Knowledge Discovery in Databases. International Workshops of ECML PKDD 2025, Porto, Portugal, September 15–19, 2025, Revised Selected Papers, Part IV}, editor = {Koprinska, Irena and Mendes-Moreira, João and Branco, Paula}, isbn = {978-3-032-19104-5}, issn = {1865-0937}, location = {Porto, Portugal}, pages = {5--21}, publisher = {Springer Nature Switzerland}, title = {{Low Query Budget Active Learning for Classification and Regression}}, doi = {10.1007/978-3-032-19105-2_1}, year = {2026}, } @article{6655, author = {Tharwat, Alaa and Jaster, Bjarne and Schenck, Wolfram and Kohlhase, Martin}, issn = {09521976}, journal = {Engineering Applications of Artificial Intelligence}, publisher = {Elsevier BV}, title = {{Active learning evaluation metrics for classification and regression frameworks}}, doi = {10.1016/j.engappai.2026.114295}, volume = {171}, year = {2026}, } @inproceedings{6267, author = {Bültemeier, Julian and Holst, Christoph-Alexander and Lohweg, Volker and Schöne, Marvin and Jaster, Bjarne and Kohlhase, Martin}, booktitle = {2025 IEEE 30th International Conference on Emerging Technologies and Factory Automation (ETFA)}, location = {Porto, Portugal}, pages = {1--4}, publisher = {IEEE}, title = {{AI Workflow for Scarce Data: A Modular Approach to Optimise Processes}}, doi = {10.1109/ETFA65518.2025.11205664}, year = {2025}, } @inbook{6273, author = {Schöne, Marvin and Jaster, Bjarne and Bültemeier, Julian and Kohlhase, Martin}, booktitle = {Kongress KI@HSBI2025 Zukunft im Fokus – Posterbeiträge}, pages = {26--27}, publisher = {Hochschule Bielefeld}, title = {{Informed Active Learning with Decision Trees to Balance Exploration and Exploitation}}, doi = {10.60802/sidas.2025.2}, volume = {2}, year = {2025}, } @inproceedings{5905, author = {Jaster, Bjarne and Kohlhase, Martin}, booktitle = {2025 IEEE Symposium on Trustworthy, Explainable and Responsible Computational Intelligence (CITREx Companion)}, keywords = {Active Learning, Trustworthiness, Evaluation-methods}, location = {Trondheim, Norway}, pages = {1--5}, publisher = {IEEE}, title = {{Trust Issues in Active Learning and Their Impact on Real-World Applications}}, doi = {10.1109/CITRExCompanion65208.2025.10981492}, year = {2025}, } @inproceedings{6045, author = {Jaster, Bjarne and Kohlhase, Martin}, booktitle = {2025 IEEE Symposium on Trustworthy, Explainable and Responsible Computational Intelligence (CITREx Companion)}, keywords = {Active Learning, Trustworthiness, Evaluation-methods}, location = {Trondheim, Norway}, pages = {1--5}, publisher = {IEEE}, title = {{Trust Issues in Active Learning and Their Impact on Real-World Applications}}, doi = {10.57720/6045}, year = {2025}, } @inproceedings{6049, author = {Schöne, Marvin and Jaster, Bjarne and Bültemeier, Julian and Kösters, Justus and Holst, Christoph-Alexander and Kohlhase, Martin}, booktitle = {2025 IEEE Symposium on Trustworthy, Explainable and Responsible Computational Intelligence (CITREx)}, keywords = {Interpretability, Classification, Pool-based Active Learning, Decision Trees}, location = {Trondheim, Norway}, pages = {1--9}, publisher = {IEEE}, title = {{Pool-based Active Learning with Decision Trees: Incorporate the Tree Structure to Explore and Exploit}}, doi = {10.57720/6049}, year = {2025}, } @inproceedings{5904, author = {Schöne, Marvin and Jaster, Bjarne and Bültemeier, Julian and Kösters, Justus and Holst, Christoph-Alexander and Kohlhase, Martin}, booktitle = {2025 IEEE Symposium on Trustworthy, Explainable and Responsible Computational Intelligence (CITREx)}, keywords = {Interpretability, Classification, Pool-based Active Learning, Decision Trees}, location = {Trondheim, Norway}, pages = {1--9}, publisher = {IEEE}, title = {{Pool-based Active Learning with Decision Trees: Incorporate the Tree Structure to Explore and Exploit}}, doi = {10.1109/CITREx64975.2025.10974940}, year = {2025}, } @article{6299, author = {Katter, Vincent and Jaster, Bjarne and Schöne, Marvin}, journal = {Schriftenreihe des Institute for Data Science Solutions}, publisher = {Hochschule Bielefeld}, title = {{Evaluierung der Leistungsfähigkeit von LSTM-Modellen für die Approximation physikalischer Systeme }}, doi = {10.60802/SIDAS.2024.2}, volume = {2}, year = {2024}, } @inproceedings{3713, author = {Jaster, Bjarne and Kohlhase, Martin}, booktitle = {Proceedings - 33. Workshop Computational Intelligence}, editor = {Schulte, Horst and Hoffmann, Frank and Mikut, Ralf}, isbn = {978-3-7315-1324-7}, location = {Berlin}, pages = {9 -- 29}, publisher = {Karlsruher Institut für Technologie (KIT)}, title = {{Active Learning for Regression Problems with Ensemble Methods}}, doi = {10.5445/KSP/1000162754}, year = {2023}, } @article{6498, author = {Guss, William Hebgen and Milani, Stephanie and Topin, Nicholay and Houghton, Brandon and Mohanty, Sharada and Melnik, Andrew and Harter, Augustin and Buschmaas, Benoit and Jaster, Bjarne and Berganski, Christoph and Heitkamp, Dennis and Henning, Marko and Ritter, Helge and Wu, Chengjie and Hao, Xiaotian and Lu, Yiming and Mao, Hangyu and Mao, Yihuan and Wang, Chao and Opanowicz, Michal and Kanervisto, Anssi and Schraner, Yanick and Scheller, Christian and Zhou, Xiren and Liu, Lu and Nishio, Daichi and Tsuneda, Toi and Ramanauskas, Karolis and Juceviciute, Gabija}, journal = {arXiv}, publisher = {arXiv}, title = {{Towards robust and domain agnostic reinforcement learning competitions}}, doi = {10.48550/ARXIV.2106.03748}, year = {2021}, }