Interactive and Explainable Human-Centered AutoML

Funding Agency

Trust and interactivity are key factors in the future development and use of automated machine learning (AutoML), supporting developers and researchers in determining powerful task-specific machine learning pipelines, including pre-processing, predictive algorithm, their hyperparameters and -if applicable- the architecture design of deep neural networks. Although AutoML is ready for its prime time, democratization of machine learning via AutoML is still not achieved. In contrast to previously purely automation-centered approaches, ixAutoML is designed with human users at its heart in several stages. The foundation of trustful use of AutoML will be based on explanations of its results and processes. To this end, we aim for: (i) Explaining static effects of design decisions in ML pipelines optimized by state-of-the-art AutoML systems. (ii) Explaining dynamic AutoML policies for temporal aspects of dynamically adapted hyperparameters while ML models are trained. These explanations will be the base for allowing interactions allowing to combine human intuition and generalization capabilities for complex systems, and efficiency of systematic optimization approaches for AutoML.

Lead at LUHAI: Prof. Lindauer

Funding Program: ERC Starting Grant

Project Period: Dec 2022 - Nov 2027

Publications

Showing results 1 - 15 out of 15

2024

Bergman, E., Feurer, M., Bahram, A., Rezaei, A., Purucker, L., Segel, S., Lindauer, M., & Eggensperger, K. (2024). AMLTK: A Modular AutoML Toolkit in Python. The Journal of Open Source Software, 9(100), Article 6367. https://doi.org/10.21105/joss.06367

Giovanelli, J., Tornede, A., Tornede, T., & Lindauer, M. (2024). Interactive Hyperparameter Optimization in Multi-Objective Problems via Preference Learning. In M. Wooldridge, J. Dy, & S. Natarajan (Eds.), Proceedings of the 38th conference on AAAI (pp. 12172-12180). (Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 38, No. 11). https://doi.org/10.48550/arXiv.2309.03581, https://doi.org/10.1609/aaai.v38i11.29106

Lindauer, M., Karl, F., Klier, A., Moosbauer, J., Tornede, A., Müller, A., Hutter, F., Feurer, M., & Bischl, B. (2024). Position Paper: A Call to Action for a Human-Centered AutoML Paradigm. In Proceedings of the international conference on machine learning Advance online publication.

Tornede, A., Deng, D., Eimer, T., Giovanelli, J., Mohan, A., Ruhkopf, T., Segel, S., Theodorakopoulos, D., Tornede, T., Wachsmuth, H., & Lindauer, M. (2024). AutoML in the Age of Large Language Models: Current Challenges, Future Opportunities and Risks. Transactions on Machine Learning Research. Advance online publication. https://doi.org/10.48550/arXiv.2306.08107

2023

Denkena, B., Dittrich, M.-A., Noske, H., Lange, D., Benjamins, C., & Lindauer, M. (2023). Application of machine learning for fleet-based condition monitoring of ball screw drives in machine tools. The international journal of advanced manufacturing technology, 127(3-4), 1143-1164. https://doi.org/10.1007/s00170-023-11524-9

Eimer, T., Lindauer, M., & Raileanu, R. (2023). Extended Abstract: Hyperparameters in Reinforcement Learning and How To Tune Them. In The 16th European Workshop on Reinforcement Learning (EWRL 2023) Advance online publication. https://openreview.net/forum?id=N3IDYxLxgtW

Eimer, T., Lindauer, M., & Raileanu, R. (2023). Hyperparameters in Reinforcement Learning and How to Tune Them. In ICML'23: Proceedings of the 40th International Conference on Machine Learning (pp. 9104–9149). Article 366 https://doi.org/10.48550/arXiv.2306.01324, https://doi.org/10.5555/3618408.3618774

Mallik, N., Bergman, E., Hvarfner, C., Stoll, D., Janowski, M., Lindauer, M., Nardi, L., & Hutter, F. (2023). PriorBand: Practical Hyperparameter Optimization in the Age of Deep Learning. In Proceedings of the international Conference on Neural Information Processing Systems (NeurIPS) Advance online publication. https://doi.org/10.48550/arXiv.2306.12370

Mohan, A., Benjamins, C., Wienecke, K., Dockhorn, A., & Lindauer, M. (2023). AutoRL Hyperparameter Landscapes. In Conference Proceedings - Second International Conference on Automated Machine Learning (Vol. 228). (Proceedings of Machine Learning Research; Vol. 228). PMLR. https://doi.org/10.48550/arXiv.2304.02396

Mohan, A., Benjamins, C., Wienecke, K., Dockhorn, A., & Lindauer, M. (Accepted/in press). Extended Abstract: AutoRL Hyperparameter Landscapes. In The 16th European Workshop on Reinforcement Learning (EWRL 2023) https://openreview.net/forum?id=4Zu0l5lBgc

Segel, S., Graf, H., Tornede, A., Bischl, B., & Lindauer, M. (2023). Symbolic Explanations for Hyperparameter Optimization. In AutoML Conference 2023 PMLR. Advance online publication. https://openreview.net/forum?id=JQwAc91sg_x

Zoeller, M., Mauthe, F., Zeiler, P., Lindauer, M., & Huber, M. (2023). Automated Machine Learning for Remaining Useful Life Predictions. In Proceedings of the international conference on Systems Science and Engineering, Human-Machine Systems, and Cybernetics (IEEE SMC) IEEE Xplore Digital Library. Advance online publication. https://arxiv.org/abs/2306.12215

2022

Hvarfner, C., Stoll, D., Souza, A. L. F., Lindauer, M., Hutter, F., & Nardi, L. (2022). π BO: Augmenting Acquisition Functions with User Beliefs for Bayesian Optimization. In Proceedings of the International conference on Learning Representation (ICLR) https://doi.org/10.48550/arXiv.2204.11051

Mallik, N., Hvarfner, C., Stoll, D., Janowski, M., Bergman, E., Lindauer, M. T., Nardi, L., & Hutter, F. (2022). PriorBand: HyperBand + Human Expert Knowledge. In 2022 NeurIPS Workshop on Meta Learning (MetaLearn) https://openreview.net/forum?id=ds21dwfBBH

Moosbauer, J., Casalicchio, G., Lindauer, M., & Bischl, B. (2022). Enhancing Explainability of Hyperparameter Optimization via Bayesian Algorithm Execution. Advance online publication. https://doi.org/10.48550/arXiv.2206.05447

Making AutoML systems more human-centered by enabling interactivity and explainability.

Funding Agency

Publications

2024

2023

2022

Gefördert vom