@book{65408, editor = {{Menne, Anna Lena and Schulz, Christian}}, publisher = {{Transcript}}, title = {{{Unpacking [Digital] Imaginaries. Das Imaginäre im Kontext digitaler Medien}}}, year = {{2027}}, } @inbook{65061, abstract = {{Abstract One of the purposes for which XAI is often brought into play is to enable a user to act responsibly. However, responsibility is a complex normative and social phenomenon that we unfold in this chapter. We consider that the classical concepts of agency and responsibility do not fully capture what is needed for meaningful collaboration between human users and XAI. Advocating the perspective of sXAI, we argue that the growing adaptivity of AI systems will result in sXAI being considered as partners. Both partners adopt particular (dialogical) roles within a collaborative process and take responsibility for them. We expect that these roles lead to reactive attitudes toward the sXAI on the side of the human partners that make these roles relational. They resemble those reactive attitudes that we hold toward other human agents. For agents to exercise their responsibility, they need to possess agential capacities to fulfill their role with respect to the structure of a social interaction. Hence, sXAI can be expected to act responsibly. But because of XAI’s limited normative capacities, it might rather act as a marginal agent. We refer to marginal agents and show they can be scaffolded with regard to their agential capacities and their knowledge about the structure of a social interaction. The structure links the actions of the partners to each other in terms of a set of stimuli and responses to it in pursuit of a particular goal. Hence, it is important to differentiate between the different goals that a structure can impose for exercising responsibility. Therefore, we follow (Responsibility from the margins. Oxford University Press; 2015. https://doi.org/10.1093/acprof:oso/9780198715672.24001.0001 ) and offer three structures that can help to organize responsibility for decisions made with the assistance of AI systems. These structures are attributability, answerability, and accountability. Our insights will inform the development and design process of XAI to meet the guiding principles of responsible research and innovation as well as trustworthy AI. }}, author = {{Rohlfing, Katharina J. and Alpsancar, Suzana and Schulte, Carsten}}, booktitle = {{Social Explainable AI}}, isbn = {{9789819652891}}, pages = {{157--177}}, publisher = {{Springer Nature Singapore}}, title = {{{Responsibilities in sXAI}}}, doi = {{10.1007/978-981-96-5290-7_9}}, year = {{2026}}, } @inbook{65064, abstract = {{Abstract XAI can minimize the risks of being manipulated and deceived by AI but in turn entails other specific risks. This also applies to sXAI, and the specifically social character of sXAI harbors particular risks that designers and developers should be aware of. In this chapter, we shall discuss the potential opportunities and risks of sXAI. We see a particularly positive potential in the social character of sXAI, which lies in the fact that skillful users, including those with “healthy distrust,” can use the adaptivity of sXAI to produce an explanation that is actually relevant and adequate for them. However, this requires a high level of skills on the part of the user and is thus in contrast to the general promise of efficiency in the use of AI. A potential risk of XAI is that it can be (even more) persuasive, as the interactive involvement and the anthropomorphism strengthen a trustworthy appearance/performance (independent of the adequacy of the sXAI performance).}}, author = {{Alpsancar, Suzana and Klenk, Michael}}, booktitle = {{Social Explainable AI}}, isbn = {{9789819652891}}, pages = {{583--616}}, publisher = {{Springer Nature Singapore}}, title = {{{The Risk of Manipulation and Deception in sXAI}}}, doi = {{10.1007/978-981-96-5290-7_30}}, year = {{2026}}, } @book{65065, abstract = {{Abstract This introduction sets the stage for the present book. Whereas research in eXplainable AI (XAI) is motivated by societal changes and values, technology development largely ignores social aspects. This book aims to address this research gap with a systematic and comprehensive social view on explainable AI. Besides introducing many relevant concepts, the book offers first access to their possible implementation, thus advancing the development of more social XAI. The introduction starts by connecting the topic to the general research field of XAI. The second part defines the novel approach of social eXplainable AI (sXAI) along the three characteristics of social interaction such as patternedness, incrementality, and multimodality. Finally, the third part explains the structure followed by each chapter. The book offers insights not only for readers who work on technology development but also for those working in sociotechnical fields. Addressing an interdisciplinary readership, the book is an invitation for more exchange and further development of the sXAI field.}}, editor = {{Rohlfing, Katharina J. and Främling, Kary and Lim, Brian and Alpsancar, Suzana and Thommes, Kirsten}}, isbn = {{9789819652891}}, publisher = {{Springer Nature Singapore}}, title = {{{Social Explainable AI}}}, doi = {{10.1007/978-981-96-5290-7_1}}, year = {{2026}}, } @inbook{55598, author = {{Schulz, Christian}}, booktitle = {{Handbuch Social Media: Geschichte – Kultur – Ästhetik}}, editor = {{Dörre, Robert and Tuschling, Anna }}, publisher = {{Metzler Verlag}}, title = {{{Feeds. Ein zentrales Strukturprinzip sozialer Medien}}}, year = {{2026}}, } @unpublished{65544, author = {{Knauff, Markus and Butz, Martin V. and Kaup, Barbara and Kunde, Wilfried and Scharlau, Ingrid}}, booktitle = {{psyarxiv}}, keywords = {{explainability, explanation, prediction}}, pages = {{18}}, publisher = {{OSF}}, title = {{{When prediction replaces explanation: A threat to psychological science }}}, year = {{2026}}, } @article{64789, author = {{Beer, Fabian and Schulz, Christian}}, journal = {{RESET Journal (Recherches sciences sociale sur internet) Special Issue: Towards New Social and Historical Studies of Artificial Intelligence}}, publisher = {{Open Edition Journals}}, title = {{{AI has never been inherently interpretable: On a paradoxical origin of eXplainable AI (XAI)}}}, year = {{2026}}, } @inbook{63031, abstract = {{Despite decades of awareness, asymmetries in conceptual resources, data, and governance between users and developers persist. Meanwhile, socially situated ‘end-users’ experience harms, such as hidden labor, reinforced stereotypes, and increased unpredictability, as machine learning advances. However, accurately modeling social context does not constitute design justice. This paper reinterprets Giuseppe Mantovani’s model of social context in human-computer interaction (HCI) to address the relational emergence and political situatedness of social context in human-AI interaction (HAI). Drawing on the concept of a multi-perspectival algorithmic imaginary, we (1) conceptualize context as nested and entangled relations, (2) identify actors, including users, developers, models, and interfaces, and (3) foreground the organization of relations of power. Recognizing that models are performative rather than predictive, we argue that the sociopolitical situatedness of context must be acknowledged alongside its limits. To challenge design authority, we propose that HCI and HAI strategically foster intra-actional negotiability, enabling users to challenge, reinterpret, or modify their relationship with technology through critical (design) practices.}}, author = {{Menne, Anna Lena and Schulz, Christian}}, booktitle = {{HCI International 2026 Posters: 28th International Conference on Human-Computer Interaction, HCII 2026, Montreal, QC, Canada, July 26–31, 2026, Proceedings, Part I}}, editor = {{Stephanidis, Constantine and Margetis, George and Ntoa, Stavroula and Antona, Margherita and Salvendy, Gavriel}}, keywords = {{Social Context, Situatedness, Imaginaries}}, location = {{Montreal}}, pages = {{93--106}}, publisher = {{Springer International Publishing}}, title = {{{Social Context in Human-AI Interaction (HAI): Towards a Theoretical Framework Based on Multi-Perspectival Imaginaries}}}, doi = {{10.1007/978-3-032-30552-7_10}}, volume = {{3047}}, year = {{2026}}, } @inproceedings{61229, author = {{Muschalik, Maximilian and Fumagalli, Fabian and Frazzetto, Paolo and Strotherm, Janine and Hermes, Luca and Sperduti, Alessandro and Hüllermeier, Eyke and Hammer, Barbara}}, booktitle = {{The Thirteenth International Conference on Learning Representations (ICLR)}}, title = {{{Exact Computation of Any-Order Shapley Interactions for Graph Neural Networks}}}, year = {{2025}}, } @inproceedings{61232, author = {{Visser, Roel and Fumagalli, Fabian and Hüllermeier, Eyke and Hammer, Barbara}}, booktitle = {{Proceedings of the European Symposium on Artificial Neural Networks (ESANN)}}, keywords = {{FF}}, title = {{{Explaining Outliers using Isolation Forest and Shapley Interactions}}}, year = {{2025}}, } @inproceedings{61231, author = {{Fumagalli, Fabian and Muschalik, Maximilian and Hüllermeier, Eyke and Hammer, Barbara and Herbinger, Julia}}, booktitle = {{Proceedings of The 28th International Conference on Artificial Intelligence and Statistics (AISTATS)}}, pages = {{5140--5148}}, publisher = {{PMLR}}, title = {{{Unifying Feature-Based Explanations with Functional ANOVA and Cooperative Game Theory}}}, volume = {{258}}, year = {{2025}}, } @article{54667, author = {{Schulz, Christian}}, isbn = {{978-3-8376-6358-7}}, journal = {{Digital Culture & Society }}, pages = {{45--68}}, title = {{{On "Super Likes" and Algorithmic (In)Visibilities: Frictions Between Social and Economic Logics in the Context of Social Media Platforms}}}, doi = {{https://doi.org/10.14361/dcs-2023-0204}}, volume = {{2/2023}}, year = {{2025}}, } @inbook{51745, author = {{Schulz, Christian}}, booktitle = {{Digitale Schriftlichkeit – Progammieren, Prozessieren und Codieren von Schrift}}, editor = {{Bartelmus, Martin and Nebrig, Alexander}}, publisher = {{transcript }}, title = {{{Vernakulärer Code oder die Geister, die der Algorithmus rief - digitale Schriftlichkeit im Kontext von sozialen Medienplattformen}}}, doi = {{https://doi.org/10.1515/9783839468135-009}}, year = {{2024}}, } @inbook{51746, author = {{Schulz, Christian}}, booktitle = {{Die Fotografie und ihre Institutionen. Von der Lehrsammlung zum Bundesinstitut }}, editor = {{Schürmann, Anja and Yacavone, Kathrin }}, publisher = {{Reimer Verlag}}, title = {{{Vom foto-sozialen Graph zum Story-Format: Über die Institutionalisierung sozialmedialer Infrastruktur aus dem Geiste der Fotografie}}}, doi = {{doi.org/10.5771/9783496030980}}, year = {{2024}}, } @inproceedings{58224, author = {{Kenneweg, Philip and Kenneweg, Tristan and Fumagalli, Fabian and Hammer, Barbara}}, booktitle = {{2024 International Joint Conference on Neural Networks (IJCNN)}}, keywords = {{Training, Schedules, Codes, Search methods, Source coding, Computer architecture, Transformers}}, pages = {{1--8}}, title = {{{No learning rates needed: Introducing SALSA - Stable Armijo Line Search Adaptation}}}, doi = {{10.1109/IJCNN60899.2024.10650124}}, year = {{2024}}, } @inproceedings{53073, abstract = {{While shallow decision trees may be interpretable, larger ensemble models like gradient-boosted trees, which often set the state of the art in machine learning problems involving tabular data, still remain black box models. As a remedy, the Shapley value (SV) is a well-known concept in explainable artificial intelligence (XAI) research for quantifying additive feature attributions of predictions. The model-specific TreeSHAP methodology solves the exponential complexity for retrieving exact SVs from tree-based models. Expanding beyond individual feature attribution, Shapley interactions reveal the impact of intricate feature interactions of any order. In this work, we present TreeSHAP-IQ, an efficient method to compute any-order additive Shapley interactions for predictions of tree-based models. TreeSHAP-IQ is supported by a mathematical framework that exploits polynomial arithmetic to compute the interaction scores in a single recursive traversal of the tree, akin to Linear TreeSHAP. We apply TreeSHAP-IQ on state-of-the-art tree ensembles and explore interactions on well-established benchmark datasets.}}, author = {{Muschalik, Maximilian and Fumagalli, Fabian and Hammer, Barbara and Huellermeier, Eyke}}, booktitle = {{Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)}}, issn = {{2374-3468}}, keywords = {{Explainable Artificial Intelligence}}, number = {{13}}, pages = {{14388--14396}}, title = {{{Beyond TreeSHAP: Efficient Computation of Any-Order Shapley Interactions for Tree Ensembles}}}, doi = {{10.1609/aaai.v38i13.29352}}, volume = {{38}}, year = {{2024}}, } @inproceedings{55311, abstract = {{Addressing the limitations of individual attribution scores via the Shapley value (SV), the field of explainable AI (XAI) has recently explored intricate interactions of features or data points. In particular, extensions of the SV, such as the Shapley Interaction Index (SII), have been proposed as a measure to still benefit from the axiomatic basis of the SV. However, similar to the SV, their exact computation remains computationally prohibitive. Hence, we propose with SVARM-IQ a sampling-based approach to efficiently approximate Shapley-based interaction indices of any order. SVARM-IQ can be applied to a broad class of interaction indices, including the SII, by leveraging a novel stratified representation. We provide non-asymptotic theoretical guarantees on its approximation quality and empirically demonstrate that SVARM-IQ achieves state-of-the-art estimation results in practical XAI scenarios on different model classes and application domains.}}, author = {{Kolpaczki, Patrick and Muschalik, Maximilian and Fumagalli, Fabian and Hammer, Barbara and Huellermeier, Eyke}}, booktitle = {{Proceedings of The 27th International Conference on Artificial Intelligence and Statistics (AISTATS)}}, pages = {{3520–3528}}, publisher = {{PMLR}}, title = {{{SVARM-IQ: Efficient Approximation of Any-order Shapley Interactions through Stratification}}}, volume = {{238}}, year = {{2024}}, } @inproceedings{58223, abstract = {{The Shapley value (SV) is a prevalent approach of allocating credit to machine learning (ML) entities to understand black box ML models. Enriching such interpretations with higher-order interactions is inevitable for complex systems, where the Shapley Interaction Index (SII) is a direct axiomatic extension of the SV. While it is well-known that the SV yields an optimal approximation of any game via a weighted least square (WLS) objective, an extension of this result to SII has been a long-standing open problem, which even led to the proposal of an alternative index. In this work, we characterize higher-order SII as a solution to a WLS problem, which constructs an optimal approximation via SII and k-Shapley values (k-SII). We prove this representation for the SV and pairwise SII and give empirically validated conjectures for higher orders. As a result, we propose KernelSHAP-IQ, a direct extension of KernelSHAP for SII, and demonstrate state-of-the-art performance for feature interactions.}}, author = {{Fumagalli, Fabian and Muschalik, Maximilian and Kolpaczki, Patrick and Hüllermeier, Eyke and Hammer, Barbara}}, booktitle = {{Proceedings of the 41st International Conference on Machine Learning (ICML)}}, pages = {{14308–14342}}, publisher = {{PMLR}}, title = {{{KernelSHAP-IQ: Weighted Least Square Optimization for Shapley Interactions}}}, volume = {{235}}, year = {{2024}}, } @inproceedings{61228, author = {{Muschalik, Maximilian and Baniecki, Hubert and Fumagalli, Fabian and Kolpaczki, Patrick and Hammer, Barbara and Huellermeier, Eyke}}, booktitle = {{Advances in Neural Information Processing Systems (NeurIPS)}}, pages = {{130324–130357}}, title = {{{shapiq: Shapley interactions for machine learning}}}, volume = {{37}}, year = {{2024}}, } @inproceedings{61230, author = {{Kolpaczki, Patrick and Bengs, Viktor and Muschalik, Maximilian and Hüllermeier, Eyke}}, booktitle = {{Proceedings of the AAAI conference on Artificial Intelligence (AAAI)}}, number = {{12}}, pages = {{13246–13255}}, title = {{{Approximating the shapley value without marginal contributions}}}, volume = {{38}}, year = {{2024}}, }