@article{21636, author = {{Lienen, Julian and Hüllermeier, Eyke}}, journal = {{International Journal of Approximate Reasoning}}, publisher = {{Elsevier}}, title = {{{Instance weighting through data imprecisiation}}}, year = {{2021}}, } @inproceedings{21637, author = {{Lienen, Julian and Hüllermeier, Eyke}}, booktitle = {{Proceedings of the 35th AAAI Conference on Artificial Intelligence, AAAI}}, location = {{Online}}, number = {{10}}, pages = {{8583--8591}}, publisher = {{AAAI Press}}, title = {{{From Label Smoothing to Label Relaxation}}}, volume = {{35}}, year = {{2021}}, } @inproceedings{23779, abstract = {{Produktentstehung (PE) bezieht sich auf den Prozess der Planung und Entwicklung eines Produkts sowie der damit verbundenen Dienstleistungen von der ersten Idee bis zur Herstellung und zum Vertrieb. Während dieses Prozesses gibt es zahlreiche Aufgaben, die von menschlichem Fachwissen abhängen und typischerweise von erfahrenen Experten übernommen werden. Da sich das Feld der Künstlichen Intelligenz (KI) immer weiterentwickelt und seinen Weg in den Fertigungssektor findet, gibt es viele Möglichkeiten für eine Anwendung von KI, um bei der Lösung der oben genannten Aufgaben zu helfen. In diesem Paper geben wir einen umfassenden Überblick über den aktuellen Stand der Technik des Einsatzes von KI in der PE. Im Detail analysieren wir 40 bestehende Surveys zu KI in der PE und 94 Case Studies, um herauszufinden, welche Bereiche der PE von der aktuellen Forschung in diesem Bereich vorrangig adressiert werden, wie ausgereift die diskutierten KI-Methoden sind und inwieweit datenzentrierte Ansätze in der aktuellen Forschung genutzt werden.}}, author = {{Bernijazov, Ruslan and Dicks, Alexander and Dumitrescu, Roman and Foullois, Marc and Hanselle, Jonas Manuel and Hüllermeier, Eyke and Karakaya, Gökce and Ködding, Patrick and Lohweg, Volker and Malatyali, Manuel and Meyer auf der Heide, Friedhelm and Panzner, Melina and Soltenborn, Christian}}, booktitle = {{Proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI-21)}}, keywords = {{Artificial Intelligence Product Creation Literature Review}}, location = {{Montreal, Kanada}}, title = {{{A Meta-Review on Artificial Intelligence in Product Creation}}}, year = {{2021}}, } @inproceedings{22280, author = {{Lienen, Julian and Hüllermeier, Eyke and Ewerth, Ralph and Nommensen, Nils}}, booktitle = {{Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR}}, location = {{Online}}, pages = {{14595--14604}}, title = {{{Monocular Depth Estimation via Listwise Ranking using the Plackett-Luce Model}}}, year = {{2021}}, } @unpublished{22509, abstract = {{Self-training is an effective approach to semi-supervised learning. The key idea is to let the learner itself iteratively generate "pseudo-supervision" for unlabeled instances based on its current hypothesis. In combination with consistency regularization, pseudo-labeling has shown promising performance in various domains, for example in computer vision. To account for the hypothetical nature of the pseudo-labels, these are commonly provided in the form of probability distributions. Still, one may argue that even a probability distribution represents an excessive level of informedness, as it suggests that the learner precisely knows the ground-truth conditional probabilities. In our approach, we therefore allow the learner to label instances in the form of credal sets, that is, sets of (candidate) probability distributions. Thanks to this increased expressiveness, the learner is able to represent uncertainty and a lack of knowledge in a more flexible and more faithful manner. To learn from weakly labeled data of that kind, we leverage methods that have recently been proposed in the realm of so-called superset learning. In an exhaustive empirical evaluation, we compare our methodology to state-of-the-art self-supervision approaches, showing competitive to superior performance especially in low-label scenarios incorporating a high degree of uncertainty.}}, author = {{Lienen, Julian and Hüllermeier, Eyke}}, booktitle = {{arXiv:2106.11853}}, title = {{{Credal Self-Supervised Learning}}}, year = {{2021}}, } @inproceedings{22913, author = {{Hüllermeier, Eyke and Mohr, Felix and Tornede, Alexander and Wever, Marcel Dominik}}, location = {{Bilbao (Virtual)}}, title = {{{Automated Machine Learning, Bounded Rationality, and Rational Metareasoning}}}, year = {{2021}}, } @inproceedings{27381, abstract = {{Graph neural networks (GNNs) have been successfully applied in many structured data domains, with applications ranging from molecular property prediction to the analysis of social networks. Motivated by the broad applicability of GNNs, we propose the family of so-called RankGNNs, a combination of neural Learning to Rank (LtR) methods and GNNs. RankGNNs are trained with a set of pair-wise preferences between graphs, suggesting that one of them is preferred over the other. One practical application of this problem is drug screening, where an expert wants to find the most promising molecules in a large collection of drug candidates. We empirically demonstrate that our proposed pair-wise RankGNN approach either significantly outperforms or at least matches the ranking performance of the naive point-wise baseline approach, in which the LtR problem is solved via GNN-based graph regression.}}, author = {{Damke, Clemens and Hüllermeier, Eyke}}, booktitle = {{Proceedings of The 24th International Conference on Discovery Science (DS 2021)}}, editor = {{Soares, Carlos and Torgo, Luis}}, isbn = {{9783030889418}}, issn = {{0302-9743}}, keywords = {{Graph-structured data, Graph neural networks, Preference learning, Learning to rank}}, location = {{Halifax, Canada}}, pages = {{166--180}}, publisher = {{Springer}}, title = {{{Ranking Structured Objects with Graph Neural Networks}}}, doi = {{10.1007/978-3-030-88942-5}}, volume = {{12986}}, year = {{2021}}, } @unpublished{30866, abstract = {{Automated machine learning (AutoML) strives for the automatic configuration of machine learning algorithms and their composition into an overall (software) solution - a machine learning pipeline - tailored to the learning task (dataset) at hand. Over the last decade, AutoML has developed into an independent research field with hundreds of contributions. While AutoML offers many prospects, it is also known to be quite resource-intensive, which is one of its major points of criticism. The primary cause for a high resource consumption is that many approaches rely on the (costly) evaluation of many machine learning pipelines while searching for good candidates. This problem is amplified in the context of research on AutoML methods, due to large scale experiments conducted with many datasets and approaches, each of them being run with several repetitions to rule out random effects. In the spirit of recent work on Green AI, this paper is written in an attempt to raise the awareness of AutoML researchers for the problem and to elaborate on possible remedies. To this end, we identify four categories of actions the community may take towards more sustainable research on AutoML, i.e. Green AutoML: design of AutoML systems, benchmarking, transparency and research incentives.}}, author = {{Tornede, Tanja and Tornede, Alexander and Hanselle, Jonas Manuel and Wever, Marcel Dominik and Mohr, Felix and Hüllermeier, Eyke}}, booktitle = {{arXiv:2111.05850}}, title = {{{Towards Green Automated Machine Learning: Status Quo and Future Directions}}}, year = {{2021}}, } @inproceedings{21198, author = {{Hanselle, Jonas Manuel and Tornede, Alexander and Wever, Marcel Dominik and Hüllermeier, Eyke}}, location = {{Delhi, India}}, title = {{{Algorithm Selection as Superset Learning: Constructing Algorithm Selectors from Imprecise Performance Data}}}, year = {{2021}}, } @inbook{29292, author = {{Feldhans, Robert and Wilke, Adrian and Heindorf, Stefan and Shaker, Mohammad Hossein and Hammer, Barbara and Ngonga Ngomo, Axel-Cyrille and Hüllermeier, Eyke}}, booktitle = {{Intelligent Data Engineering and Automated Learning – IDEAL 2021}}, isbn = {{9783030916077}}, issn = {{0302-9743}}, publisher = {{Springer International Publishing}}, title = {{{Drift Detection in Text Data with Document Embeddings}}}, doi = {{10.1007/978-3-030-91608-4_11}}, year = {{2021}}, } @article{24456, abstract = {{One objective of current research in explainable intelligent systems is to implement social aspects in order to increase the relevance of explanations. In this paper, we argue that a novel conceptual framework is needed to overcome shortcomings of existing AI systems with little attention to processes of interaction and learning. Drawing from research in interaction and development, we first outline the novel conceptual framework that pushes the design of AI systems toward true interactivity with an emphasis on the role of the partner and social relevance. We propose that AI systems will be able to provide a meaningful and relevant explanation only if the process of explaining is extended to active contribution of both partners that brings about dynamics that is modulated by different levels of analysis. Accordingly, our conceptual framework comprises monitoring and scaffolding as key concepts and claims that the process of explaining is not only modulated by the interaction between explainee and explainer but is embedded into a larger social context in which conventionalized and routinized behaviors are established. We discuss our conceptual framework in relation to the established objectives of transparency and autonomy that are raised for the design of explainable AI systems currently.}}, author = {{Rohlfing, Katharina J. and Cimiano, Philipp and Scharlau, Ingrid and Matzner, Tobias and Buhl, Heike M. and Buschmeier, Hendrik and Esposito, Elena and Grimminger, Angela and Hammer, Barbara and Haeb-Umbach, Reinhold and Horwath, Ilona and Hüllermeier, Eyke and Kern, Friederike and Kopp, Stefan and Thommes, Kirsten and Ngonga Ngomo, Axel-Cyrille and Schulte, Carsten and Wachsmuth, Henning and Wagner, Petra and Wrede, Britta}}, issn = {{2379-8920}}, journal = {{IEEE Transactions on Cognitive and Developmental Systems}}, keywords = {{Explainability, process ofexplaining andunderstanding, explainable artificial systems}}, number = {{3}}, pages = {{717--728}}, title = {{{Explanation as a Social Practice: Toward a Conceptual Framework for the Social Design of AI Systems}}}, doi = {{10.1109/tcds.2020.3044366}}, volume = {{13}}, year = {{2021}}, } @techreport{45616, abstract = {{Aggregation metrics in reputation systems are important for overcoming information overload. When using these metrics, technical aggregation functions such as the arithmetic mean are implemented to measure the valence of product ratings. However, it is unclear whether the implemented aggregation functions match the inherent aggregation patterns of customers. In our experiment, we elicit customers' aggregation heuristics and contrast these with reference functions. Our findings indicate that, overall, the arithmetic mean performs best in comparison with other aggregation functions. However, our analysis on an individual level reveals heterogeneous aggregation patterns. Major clusters exhibit a binary bias (i.e., an over-weighting of moderate ratings and under-weighting of extreme ratings) in combination with the arithmetic mean. Minor clusters focus on 1-star ratings or negative (i.e., 1-star and 2-star) ratings. Thereby, inherent aggregation patterns are neither affected by variation of provided information nor by individual characteristics such as experience, risk attitudes, or demographics.}}, author = {{van Straaten, Dirk and Melnikov, Vitalik and Hüllermeier, Eyke and Mir Djawadi, Behnud and Fahr, René}}, title = {{{Accounting for Heuristics in Reputation Systems: An Interdisciplinary Approach on Aggregation Processes}}}, volume = {{72}}, year = {{2021}}, } @unpublished{19603, abstract = {{Micro- and smart grids (MSG) play an important role both for integrating renewable energy sources in conventional electricity grids and for providing power supply in remote areas. Modern MSGs are largely driven by power electronic converters due to their high efficiency and flexibility. Nevertheless, controlling MSGs is a challenging task due to highest requirements on energy availability, safety and voltage quality within a wide range of different MSG topologies. This results in a high demand for comprehensive testing of new control concepts during their development phase and comparisons with the state of the art in order to ensure their feasibility. This applies in particular to data-driven control approaches from the field of reinforcement learning (RL), whose stability and operating behavior can hardly be evaluated a priori. Therefore, the OpenModelica Microgrid Gym (OMG) package, an open-source software toolbox for the simulation and control optimization of MSGs, is proposed. It is capable of modeling and simulating arbitrary MSG topologies and offers a Python-based interface for plug \& play controller testing. In particular, the standardized OpenAI Gym interface allows for easy RL-based controller integration. Besides the presentation of the OMG toolbox, application examples are highlighted including safe Bayesian optimization for low-level controller tuning.}}, author = {{Bode, Henrik and Heid, Stefan Helmut and Weber, Daniel and Hüllermeier, Eyke and Wallscheid, Oliver}}, booktitle = {{arXiv:2005.04869}}, title = {{{Towards a Scalable and Flexible Simulation and Testing Environment Toolbox for Intelligent Microgrid Control}}}, year = {{2020}}, } @inproceedings{19953, abstract = {{Current GNN architectures use a vertex neighborhood aggregation scheme, which limits their discriminative power to that of the 1-dimensional Weisfeiler-Lehman (WL) graph isomorphism test. Here, we propose a novel graph convolution operator that is based on the 2-dimensional WL test. We formally show that the resulting 2-WL-GNN architecture is more discriminative than existing GNN approaches. This theoretical result is complemented by experimental studies using synthetic and real data. On multiple common graph classification benchmarks, we demonstrate that the proposed model is competitive with state-of-the-art graph kernels and GNNs.}}, author = {{Damke, Clemens and Melnikov, Vitaly and Hüllermeier, Eyke}}, booktitle = {{Proceedings of the 12th Asian Conference on Machine Learning (ACML 2020)}}, editor = {{Jialin Pan, Sinno and Sugiyama, Masashi}}, keywords = {{graph neural networks, Weisfeiler-Lehman test, cycle detection}}, location = {{Bangkok, Thailand}}, pages = {{49--64}}, publisher = {{PMLR}}, title = {{{A Novel Higher-order Weisfeiler-Lehman Graph Convolution}}}, volume = {{129}}, year = {{2020}}, } @unpublished{20211, abstract = {{In many real-world applications, the relative depth of objects in an image is crucial for scene understanding, e.g., to calculate occlusions in augmented reality scenes. Predicting depth in monocular images has recently been tackled using machine learning methods, mainly by treating the problem as a regression task. Yet, being interested in an order relation in the first place, ranking methods suggest themselves as a natural alternative to regression, and indeed, ranking approaches leveraging pairwise comparisons as training information ("object A is closer to the camera than B") have shown promising performance on this problem. In this paper, we elaborate on the use of so-called \emph{listwise} ranking as a generalization of the pairwise approach. Listwise ranking goes beyond pairwise comparisons between objects and considers rankings of arbitrary length as training information. Our approach is based on the Plackett-Luce model, a probability distribution on rankings, which we combine with a state-of-the-art neural network architecture and a sampling strategy to reduce training complexity. An empirical evaluation on benchmark data in a "zero-shot" setting demonstrates the effectiveness of our proposal compared to existing ranking and regression methods.}}, author = {{Lienen, Julian and Hüllermeier, Eyke}}, booktitle = {{arXiv:2010.13118}}, title = {{{Monocular Depth Estimation via Listwise Ranking using the Plackett-Luce model}}}, year = {{2020}}, } @inproceedings{24146, author = {{Heid, Stefan Helmut and Ramaswamy, Arunselvan and Hüllermeier, Eyke}}, booktitle = {{Proceedings-30. Workshop Computational Intelligence: Berlin, 26.-27. November 2020}}, pages = {{247}}, title = {{{Constrained Multi-Agent Optimization with Unbounded Information Delay}}}, volume = {{26}}, year = {{2020}}, } @inproceedings{17407, author = {{Tornede, Alexander and Wever, Marcel Dominik and Hüllermeier, Eyke}}, booktitle = {{Discovery Science}}, title = {{{Extreme Algorithm Selection with Dyadic Feature Representation}}}, year = {{2020}}, } @inproceedings{17408, author = {{Hanselle, Jonas Manuel and Tornede, Alexander and Wever, Marcel Dominik and Hüllermeier, Eyke}}, booktitle = {{KI 2020: Advances in Artificial Intelligence}}, title = {{{Hybrid Ranking and Regression for Algorithm Selection}}}, year = {{2020}}, } @inproceedings{17424, author = {{Tornede, Tanja and Tornede, Alexander and Wever, Marcel Dominik and Mohr, Felix and Hüllermeier, Eyke}}, booktitle = {{Proceedings of the ECMLPKDD 2020}}, title = {{{AutoML for Predictive Maintenance: One Tool to RUL Them All}}}, doi = {{10.1007/978-3-030-66770-2_8}}, year = {{2020}}, } @unpublished{17605, abstract = {{Syntactic annotation of corpora in the form of part-of-speech (POS) tags is a key requirement for both linguistic research and subsequent automated natural language processing (NLP) tasks. This problem is commonly tackled using machine learning methods, i.e., by training a POS tagger on a sufficiently large corpus of labeled data. While the problem of POS tagging can essentially be considered as solved for modern languages, historical corpora turn out to be much more difficult, especially due to the lack of native speakers and sparsity of training data. Moreover, most texts have no sentences as we know them today, nor a common orthography. These irregularities render the task of automated POS tagging more difficult and error-prone. Under these circumstances, instead of forcing the POS tagger to predict and commit to a single tag, it should be enabled to express its uncertainty. In this paper, we consider POS tagging within the framework of set-valued prediction, which allows the POS tagger to express its uncertainty via predicting a set of candidate POS tags instead of guessing a single one. The goal is to guarantee a high confidence that the correct POS tag is included while keeping the number of candidates small. In our experimental study, we find that extending state-of-the-art POS taggers to set-valued prediction yields more precise and robust taggings, especially for unknown words, i.e., words not occurring in the training data.}}, author = {{Heid, Stefan Helmut and Wever, Marcel Dominik and Hüllermeier, Eyke}}, booktitle = {{Journal of Data Mining and Digital Humanities}}, publisher = {{episciences}}, title = {{{Reliable Part-of-Speech Tagging of Historical Corpora through Set-Valued Prediction}}}, year = {{2020}}, }