@article{7141,
  abstract     = {                  This tutorial provides a comprehensive and intuitive journey through the evolution of deep generative models, tracing a clear path from the foundations of Principal Component Analysis (PCA) to modern Variational Autoencoders (VAEs), showing how each method solves the limitations of the previous one. We begin with PCA, a linear tool for reducing data dimensions. Its inability to model non-linear patterns motivates the use of Autoencoders (AEs), which use neural networks to learn flexible, compressed representations. However, AEs lack a probabilistic framework, preventing them from generating new data. VAEs address this by treating the latent space as a probability distribution, enabling data generation. We compare the three methods through theoretical analysis, experiments, and step-by-step numerical examples that show exactly how each model compresses data—a detail often missing elsewhere. Unlike resources that treat these topics separately, we connect them into a single narrative, building intuition progressively from linear to probabilistic deep generative models.
                },
  author       = {Tharwat, Alaa and Eid, Mahmoud M.},
  issn         = {2571-905X},
  journal      = {Stats},
  number       = {2},
  publisher    = {MDPI AG},
  title        = {{The Path from PCA to Autoencoders to Variational Autoencoders: Building Intuition for Deep Generative Modeling}},
  doi          = {10.3390/stats9020023},
  volume       = {9},
  year         = {2026},
}

@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},
}

@article{5853,
  author       = {Eid, Mahmoud M. and ElDahshan, Kamal and Abouali, Abdelatif H. and Tharwat, Alaa},
  issn         = {1999-4893},
  journal      = {Algorithms},
  number       = {3},
  publisher    = {MDPI AG},
  title        = {{Using Optimization Algorithms for Effective Missing-Data Imputation: A Case Study of Tabular Data Derived from Video Surveillance}},
  doi          = {10.3390/a18030119},
  volume       = {18},
  year         = {2025},
}

@book{5854,
  author       = {Tharwat, Alaa},
  isbn         = {979-8-8688-1066-4},
  publisher    = {Apress},
  title        = {{Python Adventures for Young Coders. Explore the World of Programming}},
  doi          = {10.1007/979-8-8688-1067-1},
  year         = {2025},
}

@article{5495,
  author       = {Tharwat, Alaa and Schenck, Wolfram},
  issn         = {1558-2191},
  journal      = {IEEE Transactions on Knowledge and Data Engineering},
  number       = {8},
  pages        = {4317--4330},
  publisher    = {Institute of Electrical and Electronics Engineers (IEEE)},
  title        = {{Using Methods From Dimensionality Reduction for Active Learning With Low Query Budget}},
  doi          = {10.1109/TKDE.2024.3365189},
  volume       = {36},
  year         = {2024},
}

@article{5566,
  author       = {Tharwat, Alaa and Schenck, Wolfram},
  issn         = {1558-2191},
  journal      = {IEEE Transactions on Knowledge and Data Engineering},
  number       = {8},
  pages        = {4317--4330},
  publisher    = {Institute of Electrical and Electronics Engineers (IEEE)},
  title        = {{Using Methods From Dimensionality Reduction for Active Learning With Low Query Budget}},
  doi          = {10.1109/TKDE.2024.3365189},
  volume       = {36},
  year         = {2024},
}

@article{5568,
  author       = {Tharwat, Alaa and Schenck, Wolfram},
  issn         = {2162-2388},
  journal      = {IEEE Transactions on Neural Networks and Learning Systems},
  number       = {2},
  pages        = {3273--3287},
  publisher    = {Institute of Electrical and Electronics Engineers (IEEE)},
  title        = {{Active Learning for Handling Missing Data}},
  doi          = {10.1109/TNNLS.2024.3352279},
  volume       = {36},
  year         = {2024},
}

@inproceedings{5570,
  author       = {Tharwat, Alaa and Herde, Marek  and Pham, Minh Tuan and Sick, Bernhard },
  location     = {Vilnius, Lithuania},
  title        = {{Tutorial: Interactive Adaptive Learning}},
  year         = {2024},
}

@article{2774,
  author       = {Tharwat, Alaa and Schenck, Wolfram},
  issn         = {2227-7390},
  journal      = {Mathematics},
  number       = {4},
  publisher    = {MDPI AG},
  title        = {{A Survey on Active Learning: State-of-the-Art, Practical Challenges and Research Directions}},
  doi          = {10.3390/math11040820},
  volume       = {11},
  year         = {2023},
}

@inproceedings{5569,
  author       = {Tharwat, Alaa and Bunse, Mirko  and Hammer, Barbara  and Krempl, Georg  and Lemaire, Vincent  and Amal,  Saadallah},
  location     = {Torino, Italy},
  title        = {{Tutorial: Interactive Adaptive Learning.}},
  year         = {2023},
}

@article{2775,
  author       = {Tharwat, Alaa and Schenck, Wolfram},
  issn         = {2227-7390},
  journal      = {Mathematics},
  number       = {7},
  publisher    = {MDPI AG},
  title        = {{A Novel Low-Query-Budget Active Learner with Pseudo-Labels for Imbalanced Data}},
  doi          = {10.3390/math10071068},
  volume       = {10},
  year         = {2022},
}

@article{2777,
  author       = {Tharwat, Alaa and Schenck, Wolfram},
  issn         = {22106502},
  journal      = {Swarm and Evolutionary Computation},
  publisher    = {Elsevier BV},
  title        = {{Population initialization techniques for evolutionary algorithms for single-objective constrained optimization problems: Deterministic vs. stochastic techniques}},
  doi          = {10.1016/j.swevo.2021.100952},
  volume       = {67},
  year         = {2021},
}

@article{1202,
  author       = {Tharwat, Alaa and Schenck, Wolfram},
  issn         = {0957-4174},
  journal      = {Expert Systems with Applications},
  publisher    = {Elsevier BV},
  title        = {{A conceptual and practical comparison of PSO-style optimization algorithms}},
  doi          = {10.1016/j.eswa.2020.114430},
  volume       = {167},
  year         = {2021},
}

@article{1204,
  author       = {Tharwat, Alaa and Schenck, Wolfram},
  issn         = {0950-7051},
  journal      = {Knowledge-Based Systems},
  publisher    = {Elsevier BV},
  title        = {{Balancing Exploration and Exploitation: A novel active learner for imbalanced data}},
  doi          = {10.1016/j.knosys.2020.106500},
  volume       = {210},
  year         = {2020},
}

@inproceedings{1206,
  author       = {Pelkmann, David and Tharwat, Alaa and Schenck, Wolfram},
  booktitle    = {2020 7th Swiss Conference on Data Science (SDS)},
  location     = {Luzern, Switzerland},
  pages        = {61--62},
  publisher    = {IEEE},
  title        = {{How to Label? Combining Experts’ Knowledge for German Text Classification}},
  doi          = {10.1109/SDS49233.2020.00023},
  year         = {2020},
}