TY - CONF
AU - Hüsing, Sven
AU - Schulte, Carsten
AU - Sparmann, Sören
AU - Bolte, Mario
ID - 52379
T2 - Proceedings of the 55th ACM Technical Symposium on Computer Science Education V. 1
TI - Using Worked Examples for Engaging in Epistemic Programming Projects
ER -
TY - CONF
AU - Hu, Lijie
AU - Habernal, Ivan
AU - Shen, Lei
AU - Wang, Di
ED - Graham, Yvette
ED - Purver, Matthew
ID - 52827
T2 - Findings of the Association for Computational Linguistics: EACL 2024, St. Julian’s, Malta, March 17-22, 2024
TI - Differentially Private Natural Language Models: Recent Advances and Future Directions
ER -
TY - CONF
AB - Neural machine translation (NMT) is a widely popular text generation task, yet there is a considerable research gap in the development of privacy-preserving NMT models, despite significant data privacy concerns for NMT systems. Differentially private stochastic gradient descent (DP-SGD) is a popular method for training machine learning models with concrete privacy guarantees; however, the implementation specifics of training a model with DP-SGD are not always clarified in existing models, with differing software libraries used and code bases not always being public, leading to reproducibility issues. To tackle this, we introduce DP-NMT, an open-source framework for carrying out research on privacy-preserving NMT with DP-SGD, bringing together numerous models, datasets, and evaluation metrics in one systematic software package. Our goal is to provide a platform for researchers to advance the development of privacy-preserving NMT systems, keeping the specific details of the DP-SGD algorithm transparent and intuitive to implement. We run a set of experiments on datasets from both general and privacy-related domains to demonstrate our framework in use. We make our framework publicly available and welcome feedback from the community.
AU - Igamberdiev, Timour
AU - Vu, Doan Nam Long
AU - Kuennecke, Felix
AU - Yu, Zhuo
AU - Holmer, Jannik
AU - Habernal, Ivan
ED - Aletras, Nikolaos
ED - De Clercq, Orphee
ID - 52842
T2 - Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations
TI - DP-NMT: Scalable Differentially Private Machine Translation
ER -
TY - CONF
AU - Razavi, Kamran
AU - Ghafouri, Saeid
AU - Mühlhäuser, Max
AU - Jamshidi, Pooyan
AU - Wang, Lin
ID - 53095
T2 - Proceedings of the 4th Workshop on Machine Learning and Systems (EuroMLSys), colocated with EuroSys 2024
TI - Sponge: Inference Serving with Dynamic SLOs Using In-Place Vertical Scaling
ER -
TY - CONF
AU - Dann, Andreas Peter
AU - Hermann, Ben
AU - Bodden, Eric
ID - 35083
TI - UpCy: Safely Updating Outdated Dependencies
ER -
TY - JOUR
AB - As in almost every other branch of science, the major advances in data
science and machine learning have also resulted in significant improvements
regarding the modeling and simulation of nonlinear dynamical systems. It is
nowadays possible to make accurate medium to long-term predictions of highly
complex systems such as the weather, the dynamics within a nuclear fusion
reactor, of disease models or the stock market in a very efficient manner. In
many cases, predictive methods are advertised to ultimately be useful for
control, as the control of high-dimensional nonlinear systems is an engineering
grand challenge with huge potential in areas such as clean and efficient energy
production, or the development of advanced medical devices. However, the
question of how to use a predictive model for control is often left unanswered
due to the associated challenges, namely a significantly higher system
complexity, the requirement of much larger data sets and an increased and often
problem-specific modeling effort. To solve these issues, we present a universal
framework (which we call QuaSiModO:
Quantization-Simulation-Modeling-Optimization) to transform arbitrary
predictive models into control systems and use them for feedback control. The
advantages of our approach are a linear increase in data requirements with
respect to the control dimension, performance guarantees that rely exclusively
on the accuracy of the predictive model, and only little prior knowledge
requirements in control theory to solve complex control problems. In particular
the latter point is of key importance to enable a large number of researchers
and practitioners to exploit the ever increasing capabilities of predictive
models for control in a straight-forward and systematic fashion.
AU - Peitz, Sebastian
AU - Bieker, Katharina
ID - 21199
JF - Automatica
TI - On the Universal Transformation of Data-Driven Models to Control Systems
VL - 149
ER -
TY - CONF
AU - Schrader, Elena
AU - Bernijazov, Ruslan
AU - Foullois, Marc
AU - Hillebrand, Michael
AU - Kaiser, Lydia
AU - Dumitrescu, Roman
ID - 37553
T2 - 2022 IEEE International Symposium on Systems Engineering (ISSE)
TI - Examples of AI-based Assistance Systems in context of Model-Based Systems Engineering
ER -
TY - CONF
AU - Richter, Cedric
AU - Haltermann, Jan Frederik
AU - Jakobs, Marie-Christine
AU - Pauck, Felix
AU - Schott, Stefan
AU - Wehrheim, Heike
ID - 35426
T2 - 37th IEEE/ACM International Conference on Automated Software Engineering
TI - Are Neural Bug Detectors Comparable to Software Developers on Variable Misuse Bugs?
ER -
TY - CONF
AU - Schott, Stefan
AU - Pauck, Felix
ID - 36848
T2 - 2022 IEEE 22nd International Working Conference on Source Code Analysis and Manipulation (SCAM)
TI - Benchmark Fuzzing for Android Taint Analyses
ER -
TY - CONF
AU - Pauck, Felix
ID - 35427
T2 - 37th IEEE/ACM International Conference on Automated Software Engineering
TI - Scaling Arbitrary Android App Analyses
ER -
TY - GEN
AB - We consider the data-driven approximation of the Koopman operator for
stochastic differential equations on reproducing kernel Hilbert spaces (RKHS).
Our focus is on the estimation error if the data are collected from long-term
ergodic simulations. We derive both an exact expression for the variance of the
kernel cross-covariance operator, measured in the Hilbert-Schmidt norm, and
probabilistic bounds for the finite-data estimation error. Moreover, we derive
a bound on the prediction error of observables in the RKHS using a finite
Mercer series expansion. Further, assuming Koopman-invariance of the RKHS, we
provide bounds on the full approximation error. Numerical experiments using the
Ornstein-Uhlenbeck process illustrate our results.
AU - Philipp, Friedrich
AU - Schaller, Manuel
AU - Worthmann, Karl
AU - Peitz, Sebastian
AU - Nüske, Feliks
ID - 38031
T2 - arXiv:2301.08637
TI - Error bounds for kernel-based approximations of the Koopman operator
ER -
TY - GEN
AU - Pilot, Matthias
ID - 40440
TI - Updatable Privacy-Preserving Reputation System based on Blockchain
ER -
TY - CHAP
AU - Hüsing, Sven
AU - Schulte, Carsten
AU - Winkelnkemper, Felix
ID - 40511
SN - 9781350296916
T2 - Computer Science Education
TI - Epistemic Programming
ER -
TY - JOUR
AU - Castenow, Jannik
AU - Harbig, Jonas
AU - Jung, Daniel
AU - Knollmann, Till
AU - Meyer auf der Heide, Friedhelm
ID - 33947
JF - Theoretical Computer Science
KW - General Computer Science
KW - Theoretical Computer Science
SN - 0304-3975
TI - Gathering a Euclidean Closed Chain of Robots in Linear Time and Improved Algorithms for Chain-Formation
VL - 939
ER -
TY - CONF
AU - Luo, Linghui
AU - Piskachev, Goran
AU - Krishnamurthy, Ranjith
AU - Dolby, Julian
AU - Schäf, Martin
AU - Bodden, Eric
ID - 41812
T2 - IEEE International Conference on Software Testing, Verification and Validation (ICST)
TI - Model Generation For Java Frameworks
ER -
TY - CONF
AU - Shivarpatna Venkatesh, Ashwin Prasad
AU - Wang, Jiawei
AU - Li, Li
AU - Bodden, Eric
ID - 41813
T2 - IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)
TI - Enhancing Comprehension and Navigation in Jupyter Notebooks with Static Analysis
ER -
TY - JOUR
AU - Yigitbas, Enes
AU - Klauke, Jonas
AU - Gottschalk, Sebastian
AU - Engels, Gregor
ID - 34402
JF - Journal on Computer Languages (COLA)
TI - End-User Development of Interactive Web-Based Virtual Reality Scenes
ER -
TY - CONF
AU - Yigitbas, Enes
AU - Engels, Gregor
ID - 33511
T2 - 56th Hawaii International Conference on System Science (HICSS 2023)
TI - Enhancing Robot Programming through Digital Twin and Augmented Reality
ER -
TY - CONF
AU - Yigitbas, Enes
AU - Krois, Sebastian
AU - Gottschalk, Sebastian
AU - Engels, Gregor
ID - 34401
T2 - Proceedings of the 7th International Conference on Human Computer Interaction Theory and Applications (HUCAPP'23)
TI - Towards Enhanced Guiding Mechanisms in VR Training through Process Mining
ER -
TY - CONF
AU - Castenow, Jannik
AU - Harbig, Jonas
AU - Jung, Daniel
AU - Kling, Peter
AU - Knollmann, Till
AU - Meyer auf der Heide, Friedhelm
ED - Hillel, Eshcar
ED - Palmieri, Roberto
ED - Riviére, Etienne
ID - 34008
SN - 1868-8969
T2 - Proceedings of the 26th International Conference on Principles of Distributed Systems (OPODIS)
TI - A Unifying Approach to Efficient (Near-)Gathering of Disoriented Robots with Limited Visibility
VL - 253
ER -
TY - GEN
AB - The goal of this paper is to make a strong point for the usage of dynamical models when using reinforcement learning (RL) for feedback control of dynamical systems governed by partial differential equations (PDEs). To breach the gap between the immense promises we see in RL and the applicability in complex engineering systems, the main challenges are the massive requirements in terms of the training data, as well as the lack of performance guarantees. We present a solution for the first issue using a data-driven surrogate model in the form of a convolutional LSTM with actuation. We demonstrate that learning an actuated model in parallel to training the RL agent significantly reduces the total amount of required data sampled from the real system. Furthermore, we show that iteratively updating the model is of major importance to avoid biases in the RL training. Detailed ablation studies reveal the most important ingredients of the modeling process. We use the chaotic Kuramoto-Sivashinsky equation do demonstarte our findings.
AU - Werner, Stefan
AU - Peitz, Sebastian
ID - 42160
T2 - arXiv:2302.07160
TI - Learning a model is paramount for sample efficiency in reinforcement learning control of PDEs
ER -
TY - CONF
AB - Savitch's theorem states that NPSPACE computations can be simulated in
PSPACE. We initiate the study of a quantum analogue of NPSPACE, denoted
Streaming-QCMASPACE (SQCMASPACE), where an exponentially long classical proof
is streamed to a poly-space quantum verifier. Besides two main results, we also
show that a quantum analogue of Savitch's theorem is unlikely to hold, as
SQCMASPACE=NEXP. For completeness, we introduce Streaming-QMASPACE (SQMASPACE)
with an exponentially long streamed quantum proof, and show SQMASPACE=QMA_EXP
(quantum analogue of NEXP). Our first main result shows, in contrast to the
classical setting, the solution space of a quantum constraint satisfaction
problem (i.e. a local Hamiltonian) is always connected when exponentially long
proofs are permitted. For this, we show how to simulate any Lipschitz
continuous path on the unit hypersphere via a sequence of local unitary gates,
at the expense of blowing up the circuit size. This shows quantum
error-correcting codes can be unable to detect one codeword erroneously
evolving to another if the evolution happens sufficiently slowly, and answers
an open question of [Gharibian, Sikora, ICALP 2015] regarding the Ground State
Connectivity problem. Our second main result is that any SQCMASPACE computation
can be embedded into "unentanglement", i.e. into a quantum constraint
satisfaction problem with unentangled provers. Formally, we show how to embed
SQCMASPACE into the Sparse Separable Hamiltonian problem of [Chailloux,
Sattath, CCC 2012] (QMA(2)-complete for 1/poly promise gap), at the expense of
scaling the promise gap with the streamed proof size. As a corollary, we obtain
the first systematic construction for obtaining QMA(2)-type upper bounds on
arbitrary multi-prover interactive proof systems, where the QMA(2) promise gap
scales exponentially with the number of bits of communication in the
interactive proof.
AU - Gharibian, Sevag
AU - Rudolph, Dorian
ID - 31872
T2 - 14th Innovations in Theoretical Computer Science (ITCS)
TI - Quantum space, ground space traversal, and how to embed multi-prover interactive proofs into unentanglement
VL - 251
ER -
TY - JOUR
AB - Regularization is used in many different areas of optimization when solutions
are sought which not only minimize a given function, but also possess a certain
degree of regularity. Popular applications are image denoising, sparse
regression and machine learning. Since the choice of the regularization
parameter is crucial but often difficult, path-following methods are used to
approximate the entire regularization path, i.e., the set of all possible
solutions for all regularization parameters. Due to their nature, the
development of these methods requires structural results about the
regularization path. The goal of this article is to derive these results for
the case of a smooth objective function which is penalized by a piecewise
differentiable regularization term. We do this by treating regularization as a
multiobjective optimization problem. Our results suggest that even in this
general case, the regularization path is piecewise smooth. Moreover, our theory
allows for a classification of the nonsmooth features that occur in between
smooth parts. This is demonstrated in two applications, namely support-vector
machines and exact penalty methods.
AU - Gebken, Bennet
AU - Bieker, Katharina
AU - Peitz, Sebastian
ID - 27426
IS - 3
JF - Journal of Global Optimization
TI - On the structure of regularization paths for piecewise differentiable regularization terms
VL - 85
ER -
TY - GEN
AU - Lienen, Christian
AU - Middeke, Sorel Horst
AU - Platzner, Marco
ID - 43048
TI - fpgaDDS: An Intra-FPGA Data Distribution Service for ROS 2 Robotics Applications
ER -
TY - JOUR
AU - Götte, Thorsten
AU - Kolb, Christina
AU - Scheideler, Christian
AU - Werthmann, Julian
ID - 43109
JF - Theor. Comput. Sci.
TI - Beep-and-Sleep: Message and Energy Efficient Set Cover
VL - 950
ER -
TY - CONF
AU - Yigitbas, Enes
AU - Nowosad, Alexander
AU - Engels, Gregor
ID - 43424
T2 - Proceedings of the 19th IFIP TC13 International Conference on Human-Computer Interaction (INTERACT 2023)
TI - Supporting Construction and Architectural Visualization through BIM and AR/VR: A Systematic Literature Review
ER -
TY - CONF
AB - We present an approach for guaranteed constraint satisfaction by means of data-based optimal control, where the model is unknown and has to be obtained from measurement data. To this end, we utilize the Koopman framework and an eDMD-based bilinear surrogate modeling approach for control systems to show an error bound on predicted observables, i.e., functions of the state. This result is then applied to the constraints of the optimal control problem to show that satisfaction of tightened constraints in the purely data-based surrogate model implies constraint satisfaction for the original system.
AU - Schaller, Manuel
AU - Worthmann, Karl
AU - Philipp, Friedrich
AU - Peitz, Sebastian
AU - Nüske, Feliks
ID - 30125
IS - 1
T2 - IFAC-PapersOnLine
TI - Towards reliable data-based optimal and predictive control using extended DMD
VL - 56
ER -
TY - JOUR
AU - Maack, Marten
ID - 44077
IS - 3
JF - Operations Research Letters
KW - Applied Mathematics
KW - Industrial and Manufacturing Engineering
KW - Management Science and Operations Research
KW - Software
SN - 0167-6377
TI - Online load balancing on uniform machines with limited migration
VL - 51
ER -
TY - GEN
AU - Schürmann, Patrick
ID - 43374
TI - A Formal Comparison of Advanced Digital Signature Primitives
ER -
TY - CONF
AU - Gharibian, Sevag
AU - Watson, James
AU - Bausch, Johannes
ID - 20841
T2 - Proceedings of the 40th International Symposium on Theoretical Aspects of Computer Science (STACS)
TI - The Complexity of Translationally Invariant Problems beyond Ground State Energies
VL - 254
ER -
TY - CONF
AU - Ahmed, Qazi Arbab
AU - Awais, Muhammad
AU - Platzner, Marco
ID - 44194
T2 - The 24th International Symposium on Quality Electronic Design (ISQED'23), San Francisco, Califorina USA
TI - MAAS: Hiding Trojans in Approximate Circuits
ER -
TY - GEN
AU - Schweichhart, Jonas
ID - 44735
TI - Minimum Edge Cuts in Overlay Networks
ER -
TY - CHAP
AU - Castenow, Jannik
AU - Harbig, Jonas
AU - Meyer auf der Heide, Friedhelm
ID - 44769
SN - 0302-9743
T2 - Lecture Notes in Computer Science
TI - Unifying Gathering Protocols for Swarms of Mobile Robots
ER -
TY - CONF
AU - Wolters, Dennis
AU - Engels, Gregor
ID - 34294
SN - 2184-4348
T2 - MODELSWARD'23
TI - Model-driven Collaborative Design of Professional Education Programmes With Extended Online Whiteboards
ER -
TY - THES
AU - Pauck, Felix
ID - 43108
TI - Cooperative Android App Analysis
ER -
TY - CONF
AU - Werthmann, Julian
AU - Scheideler, Christian
AU - Coy, Sam
AU - Czumaj, Artur
AU - Schneider, Philipp
ID - 45188
TI - Routing Schemes for Hybrid Communication Networks
ER -
TY - CONF
AB - Market transactions are subject to information asymmetry about the delivered value proposition, causing transaction costs and adverse market effects among buyers and sellers. Information systems research has investigated how review systems can reduce information asymmetry in business-to-consumer markets. However, these systems cannot be readily applied to business-to-business markets, are vulnerable to manipulation, and suffer from conceptual weak spots since they use textual data or star ratings. Building on design science research, we conceptualize a new class of reputation systems based on monetary-based payments as quantitative ratings for each transaction stored on a blockchain. Using cryptography, we show that our system assures content confidentiality so that buyers can share and sell their ratings selectively, establishing a reputation ecosystem. Our prescriptive insights advance the design of reputation systems and offer new paths to understanding the antecedents, dynamics, and consequences to reduce information asymmetry in B2B transactions.
AU - Hemmrich, Simon
AU - Bobolz, Jan
AU - Beverungen, Daniel
AU - Blömer, Johannes
ID - 44855
T2 - ECIS 2023 Research Papers
TI - Designing Business Reputation Ecosystems — A Method for Issuing and Trading Monetary Ratings on a Blockchain
ER -
TY - GEN
AU - N., N.
ID - 45243
TI - Development and Evaluation of a Model-Based UI Prototyping Experimentation Approach
ER -
TY - CONF
AU - Karakaya, Kadiray
AU - Bodden, Eric
ID - 45312
T2 - 2023 IEEE Conference on Software Testing, Verification and Validation (ICST)
TI - Two Sparsification Strategies for Accelerating Demand-Driven Pointer Analysis
ER -
TY - GEN
AU - Koch, Angelina
ID - 43375
TI - Privacy-Preserving Collection and Evaluation of Log Files
ER -
TY - JOUR
AB - AbstractGraffiti is an urban phenomenon that is increasingly attracting the interest of the sciences. To the best of our knowledge, no suitable data corpora are available for systematic research until now. The Information System Graffiti in Germany project (Ingrid) closes this gap by dealing with graffiti image collections that have been made available to the project for public use. Within Ingrid, the graffiti images are collected, digitized and annotated. With this work, we aim to support the rapid access to a comprehensive data source on Ingrid targeted especially by researchers. In particular, we present IngridKG, an RDF knowledge graph of annotated graffiti, abides by the Linked Data and FAIR principles. We weekly update IngridKG by augmenting the new annotated graffiti to our knowledge graph. Our generation pipeline applies RDF data conversion, link discovery and data fusion approaches to the original data. The current version of IngridKG contains 460,640,154 triples and is linked to 3 other knowledge graphs by over 200,000 links. In our use case studies, we demonstrate the usefulness of our knowledge graph for different applications.
AU - Sherif, Mohamed Ahmed
AU - da Silva, Ana Alexandra Morim
AU - Pestryakova, Svetlana
AU - Ahmed, Abdullah Fathi
AU - Niemann, Sven
AU - Ngomo, Axel-Cyrille Ngonga
ID - 45484
IS - 1
JF - Scientific Data
KW - Library and Information Sciences
KW - Statistics
KW - Probability and Uncertainty
KW - Computer Science Applications
KW - Education
KW - Information Systems
KW - Statistics and Probability
SN - 2052-4463
TI - IngridKG: A FAIR Knowledge Graph of Graffiti
VL - 10
ER -
TY - THES
AU - Castenow, Jannik
ID - 45580
TI - Local Protocols for Contracting and Expanding Robot Formation Problems
ER -
TY - THES
AU - Knollmann, Till
ID - 45579
TI - Online Algorithms for Allocating Heterogeneous Resources
ER -
TY - CONF
AU - Hotegni, Sedjro Salomon
AU - Mahabadi, Sepideh
AU - Vakilian, Ali
ID - 45695
KW - Fair range clustering
T2 - Proceedings of the 40th International Conference on Machine Learning, Honolulu, Hawaii, USA. PMLR 202, 2023.
TI - Approximation Algorithms for Fair Range Clustering
ER -
TY - CONF
AU - Hebrok, Sven Niclas
AU - Nachtigall, Simon
AU - Maehren, Marcel
AU - Erinola, Nurullah
AU - Merget, Robert
AU - Somorovsky, Juraj
AU - Schwenk, Jörg
ID - 43060
T2 - 32nd USENIX Security Symposium
TI - We Really Need to Talk About Session Tickets: A Large-Scale Analysis of Cryptographic Dangers with TLS Session Tickets
ER -
TY - GEN
AU - Simon-Mertens, Florian
ID - 45762
TI - Effizienzanalyse leichtgewichtiger Neuronaler Netze für FPGA-basierte Modulationsklassifikation
ER -
TY - CONF
AB - The global megatrends of digitization and sustainability lead to new challenges for the design and management of technical products in industrial companies. Product management - as the bridge between market and company - has the task to absorb and combine the manifold requirements and make the right product-related decisions. In the process, product management is confronted with heterogeneous information, rapidly changing portfolio components, as well as increasing product, and organizational complexity. Combining and utilizing data from different sources, e.g., product usage data and social media data leads to promising potentials to improve the quality of product-related decisions. In this paper, we reinforce the need for data-driven product management as an interdisciplinary field of action. The state of data-driven product management in practice was analyzed by conducting workshops with six manufacturing companies and hosting a focus group meeting with experts from different industries. We investigate the expectations and derive requirements leading us to open research questions, a vision for data-driven product management, and a research agenda to shape future research efforts.
AU - Grigoryan, Khoren
AU - Fichtler, Timm
AU - Schreiner, Nick
AU - Rabe, Martin
AU - Panzner, Melina
AU - Kühn, Arno
AU - Dumitrescu, Roman
AU - Koldewey, Christian
ID - 45793
KW - Product Management
KW - Data Analytics
KW - Data-Driven Design
KW - Product-related data
KW - Lifecycle Data
KW - Tool-support
T2 - Procedia CIRP 33
TI - Data-Driven Product Management: A Practitioner-Driven Research Agenda
ER -
TY - CONF
AU - Özcan, Leon
AU - Fichtler, Timm
AU - Kasten, Benjamin
AU - Koldewey, Christian
AU - Dumitrescu, Roman
ID - 45812
KW - Digital Platform
KW - Platform Strategy
KW - Strategic Management
KW - Platform Life Cycle
KW - Interview Study
KW - Business Model
KW - Business-to-Business
KW - Two-sided Market
KW - Multi-sided Market
TI - Interview Study on Strategy Options for Platform Operation in B2B Markets
ER -
TY - CONF
AB - Many applications require explainable node classification in knowledge graphs. Towards this end, a popular ``white-box'' approach is class expression learning: Given sets of positive and negative nodes, class expressions in description logics are learned that separate positive from negative nodes. Most existing approaches are search-based approaches generating many candidate class expressions and selecting the best one. However, they often take a long time to find suitable class expressions. In this paper, we cast class expression learning as a translation problem and propose a new family of class expression learning approaches which we dub neural class expression synthesizers. Training examples are ``translated'' into class expressions in a fashion akin to machine translation. Consequently, our synthesizers are not subject to the runtime limitations of search-based approaches. We study three instances of this novel family of approaches based on LSTMs, GRUs, and set transformers, respectively. An evaluation of our approach on four benchmark datasets suggests that it can effectively synthesize high-quality class expressions with respect to the input examples in approximately one second on average. Moreover, a comparison to state-of-the-art approaches suggests that we achieve better F-measures on large datasets. For reproducibility purposes, we provide our implementation as well as pretrained models in our public GitHub repository at https://github.com/dice-group/NeuralClassExpressionSynthesis
AU - KOUAGOU, N'Dah Jean
AU - Heindorf, Stefan
AU - Demir, Caglar
AU - Ngonga Ngomo, Axel-Cyrille
ED - Pesquita, Catia
ED - Jimenez-Ruiz, Ernesto
ED - McCusker, Jamie
ED - Faria, Daniel
ED - Dragoni, Mauro
ED - Dimou, Anastasia
ED - Troncy, Raphael
ED - Hertling, Sven
ID - 33734
KW - Neural network
KW - Concept learning
KW - Description logics
T2 - The Semantic Web - 20th Extended Semantic Web Conference (ESWC 2023)
TI - Neural Class Expression Synthesis
VL - 13870
ER -
TY - GEN
AB - Knowledge bases are widely used for information management on the web,
enabling high-impact applications such as web search, question answering, and
natural language processing. They also serve as the backbone for automatic
decision systems, e.g. for medical diagnostics and credit scoring. As
stakeholders affected by these decisions would like to understand their
situation and verify fair decisions, a number of explanation approaches have
been proposed using concepts in description logics. However, the learned
concepts can become long and difficult to fathom for non-experts, even when
verbalized. Moreover, long concepts do not immediately provide a clear path of
action to change one's situation. Counterfactuals answering the question "How
must feature values be changed to obtain a different classification?" have been
proposed as short, human-friendly explanations for tabular data. In this paper,
we transfer the notion of counterfactuals to description logics and propose the
first algorithm for generating counterfactual explanations in the description
logic $\mathcal{ELH}$. Counterfactual candidates are generated from concepts
and the candidates with fewest feature changes are selected as counterfactuals.
In case of multiple counterfactuals, we rank them according to the likeliness
of their feature combinations. For evaluation, we conduct a user survey to
investigate which of the generated counterfactual candidates are preferred for
explanation by participants. In a second study, we explore possible use cases
for counterfactual explanations.
AU - Sieger, Leonie Nora
AU - Heindorf, Stefan
AU - Blübaum, Lukas
AU - Ngonga Ngomo, Axel-Cyrille
ID - 37937
T2 - arXiv:2301.05109
TI - Counterfactual Explanations for Concepts in ELH
ER -