Options
Prof. Dr.
Wrobel, Stefan
Now showing
1  10 of 11

PublicationGuideline for Designing Trustworthy Artificial Intelligence(Fraunhofer IAIS, 202302)
;Cremers, Armin B. ;Houben, Sebastian ;Sicking, Joachim ;Loh, Silke ;Stolberg, EvelynTomala, Annette DariaArtificial Intelligence (AI) has made impressive progress in recent years and represents a a crucial impact on the economy and society. Prominent use cases include applications in medical diagnostics,key technology that has predictive maintenance and, in the future, autonomous driving. However, it is clear that AI and business models based on it can only reach their full potential if AI applications are developed according to high quality standards and are effectively protected against new AI risks. For instance, AI bears the risk of unfair treatment of individuals when processing personal data e.g., to support credit lending or staff recruitment decisions. Serious false predictions resulting from minor disturbances in the input data are another example  for instance, when pedestrians are not detected by an autonomous vehicle due to image noise. The emergence of these new risks is closely linked to the fact that the process for developing AI applications, particularly those based on Machine Learning (ML), strongly differs from that of conventional software. This is because the behavior of AI applications is essentially learned from large volumes of data and is not predetermined by fixed programmed rules. 
PublicationDeutsche Normungsroadmap Künstliche Intelligenz(DIN, 20221209)
;Markert, Karla ;Meeß, Henri ;Weicken, Eva ;Zidowitz, Stephan ;Heinrich, Jana ;Görge, Rebekka ;Rauh, Lukas ;Tcholtchev, Nikolay Vassilev ;Wahlster, WolfgangWinterhalter, ChristophIm Auftrag des Bundesministeriums für Wirtschaft und Klimaschutz haben DIN und DKE im Januar 2022 die Arbeiten an der zweiten Ausgabe der Deutschen Normungsroadmap Künstliche Intelligenz gestartet. In einem breiten Beteiligungsprozess und unter Mitwirkung von mehr als 570 Fachleuten aus Wirtschaft, Wissenschaft, öffentlicher Hand und Zivilgesellschaft wurde damit der strategische Fahrplan für die KINormung weiterentwickelt. Koordiniert und begleitet wurden diese Arbeiten von einer hochrangigen Koordinierungsgruppe für KINormung und Konformität. Mit der Normungsroadmap wird eine Maßnahme der KIStrategie der Bundesregierung umgesetzt und damit ein wesentlicher Beitrag zur "KI  Made in Germany" geleistet. Die Normung ist Teil der KIStrategie und ein strategisches Instrument zur Stärkung der Innovations und Wettbewerbsfähigkeit der deutschen und europäischen Wirtschaft. Nicht zuletzt deshalb spielt sie im geplanten europäischen Rechtsrahmen für KI, dem Artificial Intelligence Act, eine besondere Rolle. Die vorliegende Normungsroadmap KI zeigt die Erfordernisse in der Normung auf, formuliert konkrete Empfehlungen und schafft so die Basis, um frühzeitig Normungsarbeiten auf nationaler, insbesondere aber auch auf europäischer und internationaler Ebene, anzustoßen. Damit zahlt sie maßgeblich auf den Artificial Intelligence Act der Europäischen Kommission ein und unterstützt dessen Umsetzung. 
PublicationThe why and how of trustworthy AI( 20220903)Artificial intelligence is increasingly penetrating industrial applications as well as areas that affect our daily lives. As a consequence, there is a need for criteria to validate whether the quality of AI applications is sufficient for their intended use. Both in the academic community and societal debate, an agreement has emerged under the term “trustworthiness” as the set of essential quality requirements that should be placed on an AI application. At the same time, the question of how these quality requirements can be operationalized is to a large extent still open. In this paper, we consider trustworthy AI from two perspectives: the product and organizational perspective. For the former, we present an AIspecific risk analysis and outline how verifiable arguments for the trustworthiness of an AI application can be developed. For the second perspective, we explore how an AI management system can be employed to assure the trustworthiness of an organization with respect to its handling of AI. Finally, we argue that in order to achieve AI trustworthiness, coordinated measures from both product and organizational perspectives are required.

PublicationA Simple Heuristic for the Graph Tukey Depth Problem with Potential Applications to Graph Mining( 2022)
;Seiffarth, FlorianWe study a recently introduced adaptation of Tukey depth to graphs and discuss its algorithmic properties and potential applications to mining and learning with graphs. In particular, since it is NPhard to compute the Tukey depth of a node, as a first contribution we provide a simple heuristic based on maximal closed set separation in graphs and show empirically on different graph datasets that its approximation error is small. Our second contribution is concerned with geodesic coreperiphery decompositions of graphs. We show empirically that the geodesic core of a graph consists of those nodes that have a high Tukey depth. This information allows for a parameterized deterministic definition of the geodesic core of a graph. 
PublicationLearning Weakly Convex Sets in Metric Spaces( 20210910)
;Stadtländer, EikeWe introduce the notion of weak convexity in metric spaces, a generalization of ordinary convexity commonly used in machine learning. It is shown that weakly convex sets can be characterized by a closure operator and have a unique decomposition into a set of pairwise disjoint connected blocks. We give two generic efficient algorithms, an extensional and an intensional one for learning weakly convex concepts and study their formal properties. Our experimental results concerning vertex classification clearly demonstrate the excellent predictive performance of the extensional algorithm. Two nontrivial applications of the intensional algorithm to polynomial PAClearnability are presented. The first one deals with learning kconvex Boolean functions, which are already known to be efficiently PAClearnable. It is shown how to derive this positive result in a fairly easy way by the generic intensional algorithm. The second one is concerned with the Euclidean space equipped with the Manhattan distance. For this metric space, weakly convex sets form a union of pairwise disjoint axisaligned hyperrectangles. We show that a weakly convex set that is consistent with a set of examples and contains a minimum number of hyperrectangles can be found in polynomial time. In contrast, this problem is known to be NPcomplete if the hyperrectangles may be overlapping. 
PublicationA Novel Regression Loss for NonParametric Uncertainty Optimization( 2021)
;Sicking, Joachim ;Pintz, Maximilian ;Fischer, AsjaQuantification of uncertainty is one of the most promising approaches to establish safe machine learning. Despite its importance, it is far from being generally solved, especially for neural networks. One of the most commonly used approaches so far is Monte Carlo dropout, which is computationally cheap and easy to apply in practice. However, it can underestimate the uncertainty. We propose a new objective, referred to as secondmoment loss (SML), to address this issue. While the full network is encouraged to model the mean, the dropout networks are explicitly used to optimize the model variance. We intensively study the performance of the new objective on various UCI regression datasets. Comparing to the stateoftheart of deep ensembles, SML leads to comparable prediction accuracies and uncertainty estimates while only requiring a single model. Under distribution shift, we observe moderate improvements. As a side result, we introduce an intuitive Wasserstein distancebased uncertainty measure that is nonsaturating and thus allows to resolve quality differences between any two uncertainty estimates. 
PublicationTrustworthy Use of Artificial Intelligence( 201907)
;Cremers, Armin B. ;Englander, Alex ;Gabriel, Markus ;Rostalski, Frauke ;Sicking, Joachim ;Volmer, Julia ;Voosholz, JanThis publication forms a basis for the interdisciplinary development of a certification system for artificial intelligence. In view of the rapid development of artificial intelligence with disruptive and lasting consequences for the economy, society, and everyday life, it highlights the resulting challenges that can be tackled only through interdisciplinary dialog between IT, law, philosophy, and ethics. As a result of this interdisciplinary exchange, it also defines six AIspecific audit areas for trustworthy use of artificial intelligence. They comprise fairness, transparency, autonomy and control, data protection as well as security and reliability while addressing ethical and legal requirements. The latter are further substantiated with the aim of operationalizability. 
PublicationSupport Estimation in Frequent Itemset Mining by Locality Sensitive Hashing( 2019)The main computational effort in generating all frequent itemsets in a transactional database is in the step of deciding whether an itemset is frequent, or not. We present a method for estimating itemset supports with twosided error. In a preprocessing step our algorithm first partitions the database into groups of similar transactions by using locality sensitive hashing and calculates a summary for each of these groups. The support of a query itemset is then estimated by means of these summaries. Our preliminary empirical results indicate that the proposed method results in a speedup of up to a factor of 50 on large datasets. The Fmeasure of the output patterns varies between 0.83 and 0.99.

PublicationMining Tree Patterns with Partially Injective Homomorphisms( 2019)
;Schulz, Till Hendrik ;Welke, PascalOne of the main differences between inductive logic programming (ILP) and graph mining lies in the pattern matching operator applied: While it is mainly defined by relational homomorphism (i.e., subsumption) in ILP, subgraph isomorphism is the most common pattern matching operator in graph mining. Using the fact that subgraph isomorphisms are injective homomorphisms, we bridge the gap between ILP and graph mining by considering a natural transition from homomorphisms to subgraph isomorphisms that is defined by partially injective homomorphisms, i.e., which require injectivity only for subsets of the vertex pairs in the pattern. Utilizing positive complexity results on deciding homomorphisms from bounded treewidth graphs, we present an algorithm mining frequent trees from arbitrary graphs w.r.t. partially injective homomorphisms. Our experimental results show that the predictive performance of the patterns obtained is comparable to that of ordinary frequent subgraphs. Thus, by preserving much from the advantageous properties of homomorphisms and subgraph isomorphisms, our approach provides a tradeoff between efficiency and predictive power. 
PublicationProbabilistic and exact frequent subtree mining in graphs beyond forests( 2019)
;Welke, PascalMotivated by the impressive predictive power of simple patterns, we consider the problem of mining frequent subtrees in arbitrary graphs. Although the restriction of the pattern language to trees does not resolve the computational complexity of frequent subgraph mining, in a recent work we have shown that it gives rise to an algorithm generating probabilistic frequent subtrees, a random subset of all frequent subtrees, from arbitrary graphs with polynomial delay. It is based on replacing each transaction graph in the input database with a forest formed by a random subset of its spanning trees. This simple technique turned out to be quite powerful on molecule classification tasks. It has, however, the drawback that the number of sampled spanning trees must be bounded by a polynomial of the size of the transaction graphs, resulting in less impressive recall even for slightly more complex structures beyond molecular graphs. To overcome this limitation, in this work we propose an algorithm mining probabilistic frequent subtrees also with polynomial delay, but by replacing each graph with a forest formed by an exponentially large implicit subset of its spanning trees. We demonstrate the superiority of our algorithm over the simple one on threshold graphs used e.g. in spectral clustering. In addition, providing sufficient conditions for the completeness and efficiency of our algorithm, we obtain a positive complexity result on exact frequent subtree mining for a novel, practically and theoretically relevant graph class that is orthogonal to all graph classes defined by some constant bound on monotone graph properties.