@phdthesis{TorcatoMordido2021, author = {Torcato Mordido, Gon{\c{c}}alo Filipe}, title = {Diversification, compression, and evaluation methods for generative adversarial networks}, doi = {10.25932/publishup-53546}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-535460}, school = {Universit{\"a}t Potsdam}, pages = {xiii, 148}, year = {2021}, abstract = {Generative adversarial networks (GANs) have been broadly applied to a wide range of application domains since their proposal. In this thesis, we propose several methods that aim to tackle different existing problems in GANs. Particularly, even though GANs are generally able to generate high-quality samples, the diversity of the generated set is often sub-optimal. Moreover, the common increase of the number of models in the original GANs framework, as well as their architectural sizes, introduces additional costs. Additionally, even though challenging, the proper evaluation of a generated set is an important direction to ultimately improve the generation process in GANs. We start by introducing two diversification methods that extend the original GANs framework to multiple adversaries to stimulate sample diversity in a generated set. Then, we introduce a new post-training compression method based on Monte Carlo methods and importance sampling to quantize and prune the weights and activations of pre-trained neural networks without any additional training. The previous method may be used to reduce the memory and computational costs introduced by increasing the number of models in the original GANs framework. Moreover, we use a similar procedure to quantize and prune gradients during training, which also reduces the communication costs between different workers in a distributed training setting. We introduce several topology-based evaluation methods to assess data generation in different settings, namely image generation and language generation. Our methods retrieve both single-valued and double-valued metrics, which, given a real set, may be used to broadly assess a generated set or separately evaluate sample quality and sample diversity, respectively. Moreover, two of our metrics use locality-sensitive hashing to accurately assess the generated sets of highly compressed GANs. The analysis of the compression effects in GANs paves the way for their efficient employment in real-world applications. Given their general applicability, the methods proposed in this thesis may be extended beyond the context of GANs. Hence, they may be generally applied to enhance existing neural networks and, in particular, generative frameworks.}, language = {en} } @inproceedings{JacqminOezdemirFellKurbanetal.2021, author = {Jacqmin, Julien and {\"O}zdemir, Paker Doğu and Fell Kurban, Caroline and Tun{\c{c}} Pekkan, Zelha and Koskinen, Johanna and Suonp{\"a}{\"a}, Maija and Seng, Cheyvuth and Carlon, May Kristine Jonson and Gayed, John Maurice and Cross, Jeffrey S. and Langseth, Inger and Jacobsen, Dan Yngve and Haugsbakken, Halvdan and Bethge, Joseph and Serth, Sebastian and Staubitz, Thomas and Wuttke, Tobias and Nordemann, Oliver and Das, Partha-Pratim and Meinel, Christoph and Ponce, Eva and Srinath, Sindhu and Allegue, Laura and Perach, Shai and Alexandron, Giora and Corti, Paola and Baudo, Valeria and Turr{\´o}, Carlos and Moura Santos, Ana and Nilsson, Charlotta and Maldonado-Mahauad, Jorge and Valdiviezo, Javier and Carvallo, Juan Pablo and Samaniego-Erazo, Nicolay and Poce, Antonella and Re, Maria Rosaria and Valente, Mara and Karp Gershon, Sa'ar and Ruip{\´e}rez-Valiente, Jos{\´e} A. and Despujol, Ignacio and Busquets, Jaime and Kerr, John and Lorenz, Anja and Sch{\"o}n, Sandra and Ebner, Martin and Wittke, Andreas and Beirne, Elaine and Nic Giolla Mhich{\´i}l, Mair{\´e}ad and Brown, Mark and Mac Lochlainn, Conch{\´u}r and Topali, Paraskevi and Chounta, Irene-Angelica and Ortega-Arranz, Alejandro and Villagr{\´a}-Sobrino, Sara L. and Mart{\´i}nez-Mon{\´e}s, Alejandra and Blackwell, Virginia Katherine and Wiltrout, Mary Ellen and Rami Gaddem, Mohamed and Hern{\´a}ndez Reyes, C{\´e}sar Augusto and Nagahama, Toru and Buchem, Ilona and Okatan, Ebru and Khalil, Mohammad and Casiraghi, Daniela and Sancassani, Susanna and Brambilla, Federica and Mihaescu, Vlad and Andone, Diana and Vasiu, Radu and Şahin, Muhittin and Egloffstein, Marc and Bothe, Max and Rohloff, Tobias and Schenk, Nathanael and Schwerer, Florian and Ifenthaler, Dirk and Hense, Julia and Bernd, Mike}, title = {EMOOCs 2021}, editor = {Meinel, Christoph and Staubitz, Thomas and Schweiger, Stefanie and Friedl, Christian and Kiers, Janine and Ebner, Martin and Lorenz, Anja and Ubachs, George and Mongenet, Catherine and Ruip{\´e}rez-Valiente, Jos{\´e} A. and Cortes Mendez, Manoel}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-512-5}, doi = {10.25932/publishup-51030}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-510300}, pages = {vii, 295}, year = {2021}, abstract = {From June 22 to June 24, 2021, Hasso Plattner Institute, Potsdam, hosted the seventh European MOOC Stakeholder Summit (EMOOCs 2021) together with the eighth ACM Learning@Scale Conference. Due to the COVID-19 situation, the conference was held fully online. The boost in digital education worldwide as a result of the pandemic was also one of the main topics of this year's EMOOCs. All institutions of learning have been forced to transform and redesign their educational methods, moving from traditional models to hybrid or completely online models at scale. The learnings, derived from practical experience and research, have been explored in EMOOCs 2021 in six tracks and additional workshops, covering various aspects of this field. In this publication, we present papers from the conference's Experience Track, the Policy Track, the Business Track, the International Track, and the Workshops.}, language = {en} } @article{GruenerMuehleMeinel2021, author = {Gr{\"u}ner, Andreas and M{\"u}hle, Alexander and Meinel, Christoph}, title = {ATIB}, series = {IEEE access : practical research, open solutions / Institute of Electrical and Electronics Engineers}, volume = {9}, journal = {IEEE access : practical research, open solutions / Institute of Electrical and Electronics Engineers}, publisher = {Institute of Electrical and Electronics Engineers}, address = {New York, NY}, issn = {2169-3536}, doi = {10.1109/ACCESS.2021.3116095}, pages = {138553 -- 138570}, year = {2021}, abstract = {Identity management is a principle component of securing online services. In the advancement of traditional identity management patterns, the identity provider remained a Trusted Third Party (TTP). The service provider and the user need to trust a particular identity provider for correct attributes amongst other demands. This paradigm changed with the invention of blockchain-based Self-Sovereign Identity (SSI) solutions that primarily focus on the users. SSI reduces the functional scope of the identity provider to an attribute provider while enabling attribute aggregation. Besides that, the development of new protocols, disregarding established protocols and a significantly fragmented landscape of SSI solutions pose considerable challenges for an adoption by service providers. We propose an Attribute Trust-enhancing Identity Broker (ATIB) to leverage the potential of SSI for trust-enhancing attribute aggregation. Furthermore, ATIB abstracts from a dedicated SSI solution and offers standard protocols. Therefore, it facilitates the adoption by service providers. Despite the brokered integration approach, we show that ATIB provides a high security posture. Additionally, ATIB does not compromise the ten foundational SSI principles for the users.}, language = {en} } @article{Perscheid2021, author = {Perscheid, Cindy}, title = {Integrative biomarker detection on high-dimensional gene expression data sets}, series = {Briefings in bioinformatics}, volume = {22}, journal = {Briefings in bioinformatics}, number = {3}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {1467-5463}, doi = {10.1093/bib/bbaa151}, pages = {18}, year = {2021}, abstract = {Gene expression data provide the expression levels of tens of thousands of genes from several hundred samples. These data are analyzed to detect biomarkers that can be of prognostic or diagnostic use. Traditionally, biomarker detection for gene expression data is the task of gene selection. The vast number of genes is reduced to a few relevant ones that achieve the best performance for the respective use case. Traditional approaches select genes based on their statistical significance in the data set. This results in issues of robustness, redundancy and true biological relevance of the selected genes. Integrative analyses typically address these shortcomings by integrating multiple data artifacts from the same objects, e.g. gene expression and methylation data. When only gene expression data are available, integrative analyses instead use curated information on biological processes from public knowledge bases. With knowledge bases providing an ever-increasing amount of curated biological knowledge, such prior knowledge approaches become more powerful. This paper provides a thorough overview on the status quo of biomarker detection on gene expression data with prior biological knowledge. We discuss current shortcomings of traditional approaches, review recent external knowledge bases, provide a classification and qualitative comparison of existing prior knowledge approaches and discuss open challenges for this kind of gene selection.}, language = {en} } @article{Perscheid2021, author = {Perscheid, Cindy}, title = {Comprior}, series = {BMC Bioinformatics}, volume = {22}, journal = {BMC Bioinformatics}, publisher = {Springer Nature}, address = {London}, issn = {1471-2105}, doi = {10.1186/s12859-021-04308-z}, pages = {1 -- 15}, year = {2021}, abstract = {Background Reproducible benchmarking is important for assessing the effectiveness of novel feature selection approaches applied on gene expression data, especially for prior knowledge approaches that incorporate biological information from online knowledge bases. However, no full-fledged benchmarking system exists that is extensible, provides built-in feature selection approaches, and a comprehensive result assessment encompassing classification performance, robustness, and biological relevance. Moreover, the particular needs of prior knowledge feature selection approaches, i.e. uniform access to knowledge bases, are not addressed. As a consequence, prior knowledge approaches are not evaluated amongst each other, leaving open questions regarding their effectiveness. Results We present the Comprior benchmark tool, which facilitates the rapid development and effortless benchmarking of feature selection approaches, with a special focus on prior knowledge approaches. Comprior is extensible by custom approaches, offers built-in standard feature selection approaches, enables uniform access to multiple knowledge bases, and provides a customizable evaluation infrastructure to compare multiple feature selection approaches regarding their classification performance, robustness, runtime, and biological relevance. Conclusion Comprior allows reproducible benchmarking especially of prior knowledge approaches, which facilitates their applicability and for the first time enables a comprehensive assessment of their effectiveness}, language = {en} } @article{LosterKoumarelasNaumann2021, author = {Loster, Michael and Koumarelas, Ioannis and Naumann, Felix}, title = {Knowledge transfer for entity resolution with siamese neural networks}, series = {ACM journal of data and information quality}, volume = {13}, journal = {ACM journal of data and information quality}, number = {1}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {1936-1955}, doi = {10.1145/3410157}, pages = {25}, year = {2021}, abstract = {The integration of multiple data sources is a common problem in a large variety of applications. Traditionally, handcrafted similarity measures are used to discover, merge, and integrate multiple representations of the same entity-duplicates-into a large homogeneous collection of data. Often, these similarity measures do not cope well with the heterogeneity of the underlying dataset. In addition, domain experts are needed to manually design and configure such measures, which is both time-consuming and requires extensive domain expertise.
We propose a deep Siamese neural network, capable of learning a similarity measure that is tailored to the characteristics of a particular dataset. With the properties of deep learning methods, we are able to eliminate the manual feature engineering process and thus considerably reduce the effort required for model construction. In addition, we show that it is possible to transfer knowledge acquired during the deduplication of one dataset to another, and thus significantly reduce the amount of data required to train a similarity measure. We evaluated our method on multiple datasets and compare our approach to state-of-the-art deduplication methods. Our approach outperforms competitors by up to +26 percent F-measure, depending on task and dataset. In addition, we show that knowledge transfer is not only feasible, but in our experiments led to an improvement in F-measure of up to +4.7 percent.}, language = {en} } @article{NavarroOrejasPinoetal.2021, author = {Navarro, Marisa and Orejas, Fernando and Pino, Elvira and Lambers, Leen}, title = {A navigational logic for reasoning about graph properties}, series = {Journal of logical and algebraic methods in programming}, volume = {118}, journal = {Journal of logical and algebraic methods in programming}, publisher = {Elsevier Science}, address = {Amsterdam [u.a.]}, issn = {2352-2208}, doi = {10.1016/j.jlamp.2020.100616}, pages = {33}, year = {2021}, abstract = {Graphs play an important role in many areas of Computer Science. In particular, our work is motivated by model-driven software development and by graph databases. For this reason, it is very important to have the means to express and to reason about the properties that a given graph may satisfy. With this aim, in this paper we present a visual logic that allows us to describe graph properties, including navigational properties, i.e., properties about the paths in a graph. The logic is equipped with a deductive tableau method that we have proved to be sound and complete.}, language = {en} } @phdthesis{Makowski2021, author = {Makowski, Silvia}, title = {Discriminative Models for Biometric Identification using Micro- and Macro-Movements of the Eyes}, school = {Universit{\"a}t Potsdam}, pages = {xi, 91}, year = {2021}, abstract = {Human visual perception is an active process. Eye movements either alternate between fixations and saccades or follow a smooth pursuit movement in case of moving targets. Besides these macroscopic gaze patterns, the eyes perform involuntary micro-movements during fixations which are commonly categorized into micro-saccades, drift and tremor. Eye movements are frequently studied in cognitive psychology, because they reflect a complex interplay of perception, attention and oculomotor control. A common insight of psychological research is that macro-movements are highly individual. Inspired by this finding, there has been a considerable amount of prior research on oculomotoric biometric identification. However, the accuracy of known approaches is too low and the time needed for identification is too long for any practical application. This thesis explores discriminative models for the task of biometric identification. Discriminative models optimize a quality measure of the predictions and are usually superior to generative approaches in discriminative tasks. However, using discriminative models requires to select a suitable form of data representation for sequential eye gaze data; i.e., by engineering features or constructing a sequence kernel and the performance of the classification model strongly depends on the data representation. We study two fundamentally different ways of representing eye gaze within a discriminative framework. In the first part of this thesis, we explore the integration of data and psychological background knowledge in the form of generative models to construct representations. To this end, we first develop generative statistical models of gaze behavior during reading and scene viewing that account for viewer-specific distributional properties of gaze patterns. In a second step, we develop a discriminative identification model by deriving Fisher kernel functions from these and several baseline models. We find that an SVM with Fisher kernel is able to reliably identify users based on their eye gaze during reading and scene viewing. However, since the generative models are constrained to use low-frequency macro-movements, they discard a significant amount of information contained in the raw eye tracking signal at a high cost: identification requires about one minute of input recording, which makes it inapplicable for real world biometric systems. In the second part of this thesis, we study a purely data-driven modeling approach. Here, we aim at automatically discovering the individual pattern hidden in the raw eye tracking signal. To this end, we develop a deep convolutional neural network DeepEyedentification that processes yaw and pitch gaze velocities and learns a representation end-to-end. Compared to prior work, this model increases the identification accuracy by one order of magnitude and the time to identification decreases to only seconds. The DeepEyedentificationLive model further improves upon the identification performance by processing binocular input and it also detects presentation-attacks. We find that by learning a representation, the performance of oculomotoric identification and presentation-attack detection can be driven close to practical relevance for biometric applications. Eye tracking devices with high sampling frequency and precision are expensive and the applicability of eye movement as a biometric feature heavily depends on cost of recording devices. In the last part of this thesis, we therefore study the requirements on data quality by evaluating the performance of the DeepEyedentificationLive network under reduced spatial and temporal resolution. We find that the method still attains a high identification accuracy at a temporal resolution of only 250 Hz and a precision of 0.03 degrees. Reducing both does not have an additive deteriorating effect.}, language = {en} } @article{GautamZhangLandwehretal.2021, author = {Gautam, Khem Raj and Zhang, Guoqiang and Landwehr, Niels and Adolphs, Julian}, title = {Machine learning for improvement of thermal conditions inside a hybrid ventilated animal building}, series = {Computers and electronics in agriculture : COMPAG online ; an international journal}, volume = {187}, journal = {Computers and electronics in agriculture : COMPAG online ; an international journal}, publisher = {Elsevier Science}, address = {Amsterdam [u.a.]}, issn = {0168-1699}, doi = {10.1016/j.compag.2021.106259}, pages = {10}, year = {2021}, abstract = {In buildings with hybrid ventilation, natural ventilation opening positions (windows), mechanical ventilation rates, heating, and cooling are manipulated to maintain desired thermal conditions. The indoor temperature is regulated solely by ventilation (natural and mechanical) when the external conditions are favorable to save external heating and cooling energy. The ventilation parameters are determined by a rule-based control scheme, which is not optimal. This study proposes a methodology to enable real-time optimum control of ventilation parameters. We developed offline prediction models to estimate future thermal conditions from the data collected from building in operation. The developed offline model is then used to find the optimal controllable ventilation parameters in real-time to minimize the setpoint deviation in the building. With the proposed methodology, the experimental building's setpoint deviation improved for 87\% of time, on average, by 0.53 degrees C compared to the current deviations.}, language = {en} } @article{BorchertMockTomczaketal.2021, author = {Borchert, Florian and Mock, Andreas and Tomczak, Aurelie and H{\"u}gel, Jonas and Alkarkoukly, Samer and Knurr, Alexander and Volckmar, Anna-Lena and Stenzinger, Albrecht and Schirmacher, Peter and Debus, J{\"u}rgen and J{\"a}ger, Dirk and Longerich, Thomas and Fr{\"o}hling, Stefan and Eils, Roland and Bougatf, Nina and Sax, Ulrich and Schapranow, Matthieu-Patrick}, title = {Correction to: Knowledge bases and software support for variant interpretation in precision oncology}, series = {Briefings in bioinformatics}, volume = {22}, journal = {Briefings in bioinformatics}, number = {6}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {1467-5463}, doi = {10.1093/bib/bbab246}, pages = {1}, year = {2021}, language = {en} } @article{CombiOliboniWeskeetal.2021, author = {Combi, Carlo and Oliboni, Barbara and Weske, Mathias and Zerbato, Francesca}, title = {Seamless conceptual modeling of processes with transactional and analytical data}, series = {Data \& knowledge engineering}, volume = {134}, journal = {Data \& knowledge engineering}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0169-023X}, doi = {10.1016/j.datak.2021.101895}, pages = {14}, year = {2021}, abstract = {In the field of Business Process Management (BPM), modeling business processes and related data is a critical issue since process activities need to manage data stored in databases. The connection between processes and data is usually handled at the implementation level, even if modeling both processes and data at the conceptual level should help designers in improving business process models and identifying requirements for implementation. Especially in data -and decision-intensive contexts, business process activities need to access data stored both in databases and data warehouses. In this paper, we complete our approach for defining a novel conceptual view that bridges process activities and data. The proposed approach allows the designer to model the connection between business processes and database models and define the operations to perform, providing interesting insights on the overall connected perspective and hints for identifying activities that are crucial for decision support.}, language = {en} } @article{KoerppenUllrichBertheau2021, author = {K{\"o}rppen, Tim and Ullrich, Andr{\´e} and Bertheau, Clementine}, title = {Durchblick statt Bauchgef{\"u}hl - Transformation zur Data-Driven Organization}, series = {Wirtschaftsinformatik \& Management}, volume = {13}, journal = {Wirtschaftsinformatik \& Management}, number = {6}, publisher = {Springer Gabler}, address = {Wiesbaden}, issn = {1867-5905}, doi = {10.1365/s35764-021-00370-7}, pages = {452 -- 459}, year = {2021}, abstract = {Um in der digitalisierten Wirtschaft mitzuspielen, m{\"u}ssen Unternehmen, Markt und insbesondere Kunden detailliert verstanden werden. Neben den „Big Playern" aus dem Silicon Valley sieht der deutsche Mittelstand, der zu großen Teilen noch auf gewachsenen IT-Infrastrukturen und Prozessen agiert, oft alt aus. Um in den n{\"a}chsten Jahren nicht g{\"a}nzlich abgeh{\"a}ngt zu werden, ist ein Umbruch notwendig. Sowohl Leistungserstellungsprozesse als auch Leistungsangebot m{\"u}ssen transparent und datenbasiert ausgerichtet werden. Nur so k{\"o}nnen Gesch{\"a}ftsvorf{\"a}lle, das Marktgeschehen sowie Handeln der Akteure integrativ bewertet und fundierte Entscheidungen getroffen werden. In diesem Beitrag wird das Konzept der Data-Driven Organization vorgestellt und aufgezeigt, wie Unternehmen den eigenen Analyticsreifegrad ermitteln und in einem iterativen Transformationsprozess steigern k{\"o}nnen.}, language = {de} } @article{UllrichTeichmannGronau2021, author = {Ullrich, Andr{\´e} and Teichmann, Malte and Gronau, Norbert}, title = {Fast trainable capabilities in software engineering-skill development in learning factories}, series = {Ji suan ji jiao yu = Computer Education / Qing hua da xue}, journal = {Ji suan ji jiao yu = Computer Education / Qing hua da xue}, number = {12}, publisher = {[Verlag nicht ermittelbar]}, address = {Bei jing shi}, issn = {1672-5913}, doi = {10.16512/j.cnki.jsjjy.2020.12.002}, pages = {2 -- 10}, year = {2021}, abstract = {The increasing demand for software engineers cannot completely be fulfilled by university education and conventional training approaches due to limited capacities. Accordingly, an alternative approach is necessary where potential software engineers are being educated in software engineering skills using new methods. We suggest micro tasks combined with theoretical lessons to overcome existing skill deficits and acquire fast trainable capabilities. This paper addresses the gap between demand and supply of software engineers by introducing an actionoriented and scenario-based didactical approach, which enables non-computer scientists to code. Therein, the learning content is provided in small tasks and embedded in learning factory scenarios. Therefore, different requirements for software engineers from the market side and from an academic viewpoint are analyzed and synthesized into an integrated, yet condensed skills catalogue. This enables the development of training and education units that focus on the most important skills demanded on the market. To achieve this objective, individual learning scenarios are developed. Of course, proper basic skills in coding cannot be learned over night but software programming is also no sorcery.}, language = {en} } @inproceedings{AbramovaGundlachBilda2021, author = {Abramova, Olga and Gundlach, Jana and Bilda, Juliane}, title = {Understanding the role of newsfeed clutter in stereotype activation}, series = {PACIS 2021 proceedings}, booktitle = {PACIS 2021 proceedings}, number = {473}, publisher = {AIS Electronic Library (AISeL)}, address = {[Erscheinungsort nicht ermittelbar]}, isbn = {978-1-7336325-7-7}, year = {2021}, abstract = {Despite the phenomenal growth of Big Data Analytics in the last few years, little research is done to explicate the relationship between Big Data Analytics Capability (BDAC) and indirect strategic value derived from such digital capabilities. We attempt to address this gap by proposing a conceptual model of the BDAC - Innovation relationship using dynamic capability theory. The work expands on BDAC business value research and extends the nominal research done on BDAC - innovation. We focus on BDAC's relationship with different innovation objects, namely product, business process, and business model innovation, impacting all value chain activities. The insights gained will stimulate academic and practitioner interest in explicating strategic value generated from BDAC and serve as a framework for future research on the subject}, language = {en} } @article{CsehJuhos2021, author = {Cseh, {\´A}gnes and Juhos, Attila}, title = {Pairwise preferences in the stable marriage problem}, series = {ACM Transactions on Economics and Computation / Association for Computing Machinery}, volume = {9}, journal = {ACM Transactions on Economics and Computation / Association for Computing Machinery}, number = {1}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {2167-8375}, doi = {10.1145/3434427}, pages = {28}, year = {2021}, abstract = {We study the classical, two-sided stable marriage problem under pairwise preferences. In the most general setting, agents are allowed to express their preferences as comparisons of any two of their edges, and they also have the right to declare a draw or even withdraw from such a comparison. This freedom is then gradually restricted as we specify six stages of orderedness in the preferences, ending with the classical case of strictly ordered lists. We study all cases occurring when combining the three known notions of stability-weak, strong, and super-stability-under the assumption that each side of the bipartite market obtains one of the six degrees of orderedness. By designing three polynomial algorithms and two NP-completeness proofs, we determine the complexity of all cases not yet known and thus give an exact boundary in terms of preference structure between tractable and intractable cases.}, language = {en} } @article{CsehKavitha2021, author = {Cseh, {\´A}gnes and Kavitha, Telikepalli}, title = {Popular matchings in complete graphs}, series = {Algorithmica : an international journal in computer science}, volume = {83}, journal = {Algorithmica : an international journal in computer science}, number = {5}, publisher = {Springer}, address = {New York}, issn = {0178-4617}, doi = {10.1007/s00453-020-00791-7}, pages = {1493 -- 1523}, year = {2021}, abstract = {Our input is a complete graph G on n vertices where each vertex has a strict ranking of all other vertices in G. The goal is to construct a matching in G that is popular. A matching M is popular if M does not lose a head-to-head election against any matching M ': here each vertex casts a vote for the matching in {M,M '} in which it gets a better assignment. Popular matchings need not exist in the given instance G and the popular matching problem is to decide whether one exists or not. The popular matching problem in G is easy to solve for odd n. Surprisingly, the problem becomes NP-complete for even n, as we show here. This is one of the few graph theoretic problems efficiently solvable when n has one parity and NP-complete when n has the other parity.}, language = {en} } @article{BredeBotta2021, author = {Brede, Nuria and Botta, Nicola}, title = {On the correctness of monadic backward induction}, series = {Journal of functional programming}, volume = {31}, journal = {Journal of functional programming}, publisher = {Cambridge University Press}, address = {Cambridge}, issn = {1469-7653}, doi = {10.1017/S0956796821000228}, pages = {39}, year = {2021}, abstract = {In control theory, to solve a finite-horizon sequential decision problem (SDP) commonly means to find a list of decision rules that result in an optimal expected total reward (or cost) when taking a given number of decision steps. SDPs are routinely solved using Bellman's backward induction. Textbook authors (e.g. Bertsekas or Puterman) typically give more or less formal proofs to show that the backward induction algorithm is correct as solution method for deterministic and stochastic SDPs. Botta, Jansson and Ionescu propose a generic framework for finite horizon, monadic SDPs together with a monadic version of backward induction for solving such SDPs. In monadic SDPs, the monad captures a generic notion of uncertainty, while a generic measure function aggregates rewards. In the present paper, we define a notion of correctness for monadic SDPs and identify three conditions that allow us to prove a correctness result for monadic backward induction that is comparable to textbook correctness proofs for ordinary backward induction. The conditions that we impose are fairly general and can be cast in category-theoretical terms using the notion of Eilenberg-Moore algebra. They hold in familiar settings like those of deterministic or stochastic SDPs, but we also give examples in which they fail. Our results show that backward induction can safely be employed for a broader class of SDPs than usually treated in textbooks. However, they also rule out certain instances that were considered admissible in the context of Botta et al. 's generic framework. Our development is formalised in Idris as an extension of the Botta et al. framework and the sources are available as supplementary material.}, language = {en} } @article{BensonMakaitRabl2021, author = {Benson, Lawrence and Makait, Hendrik and Rabl, Tilmann}, title = {Viper}, series = {Proceedings of the VLDB Endowment}, volume = {14}, journal = {Proceedings of the VLDB Endowment}, number = {9}, publisher = {Association for Computing Machinery}, address = {New York}, issn = {2150-8097}, doi = {10.14778/3461535.3461543}, pages = {1544 -- 1556}, year = {2021}, abstract = {Key-value stores (KVSs) have found wide application in modern software systems. For persistence, their data resides in slow secondary storage, which requires KVSs to employ various techniques to increase their read and write performance from and to the underlying medium. Emerging persistent memory (PMem) technologies offer data persistence at close-to-DRAM speed, making them a promising alternative to classical disk-based storage. However, simply drop-in replacing existing storage with PMem does not yield good results, as block-based access behaves differently in PMem than on disk and ignores PMem's byte addressability, layout, and unique performance characteristics. In this paper, we propose three PMem-specific access patterns and implement them in a hybrid PMem-DRAM KVS called Viper. We employ a DRAM-based hash index and a PMem-aware storage layout to utilize the random-write speed of DRAM and efficient sequential-write performance PMem. Our evaluation shows that Viper significantly outperforms existing KVSs for core KVS operations while providing full data persistence. Moreover, Viper outperforms existing PMem-only, hybrid, and disk-based KVSs by 4-18x for write workloads, while matching or surpassing their get performance.}, language = {en} } @inproceedings{KrauseBaumann2021, author = {Krause, Hannes-Vincent and Baumann, Annika}, title = {The devil in disguise}, series = {ICIS 2021: user behaviors, engagement, and consequences}, booktitle = {ICIS 2021: user behaviors, engagement, and consequences}, publisher = {AIS Electronic Library (AISeL)}, address = {[Erscheinungsort nicht ermittelbar]}, year = {2021}, abstract = {Envy constitutes a serious issue on Social Networking Sites (SNSs), as this painful emotion can severely diminish individuals' well-being. With prior research mainly focusing on the affective consequences of envy in the SNS context, its behavioral consequences remain puzzling. While negative interactions among SNS users are an alarming issue, it remains unclear to which extent the harmful emotion of malicious envy contributes to these toxic dynamics. This study constitutes a first step in understanding malicious envy's causal impact on negative interactions within the SNS sphere. Within an online experiment, we experimentally induce malicious envy and measure its immediate impact on users' negative behavior towards other users. Our findings show that malicious envy seems to be an essential factor fueling negativity among SNS users and further illustrate that this effect is especially pronounced when users are provided an objective factor to mask their envy and justify their norm-violating negative behavior.}, language = {en} } @article{XuRazaghiMoghadamNikoloski2021, author = {Xu, Rudan and Razaghi-Moghadam, Zahra and Nikoloski, Zoran}, title = {Maximization of non-idle enzymes improves the coverage of the estimated maximal in vivo enzyme catalytic rates in Escherichia coli}, series = {Bioinformatics}, volume = {37}, journal = {Bioinformatics}, number = {21}, publisher = {Oxford Univ. Press}, address = {Oxford}, issn = {1367-4803}, doi = {10.1093/bioinformatics/btab575}, pages = {3848 -- 3855}, year = {2021}, abstract = {Motivation: Constraint-based modeling approaches allow the estimation of maximal in vivo enzyme catalytic rates that can serve as proxies for enzyme turnover numbers. Yet, genome-scale flux profiling remains a challenge in deploying these approaches to catalogue proxies for enzyme catalytic rates across organisms. Results: Here, we formulate a constraint-based approach, termed NIDLE-flux, to estimate fluxes at a genome-scale level by using the principle of efficient usage of expressed enzymes. Using proteomics data from Escherichia coli, we show that the fluxes estimated by NIDLE-flux and the existing approaches are in excellent qualitative agreement (Pearson correlation > 0.9). We also find that the maximal in vivo catalytic rates estimated by NIDLE-flux exhibits a Pearson correlation of 0.74 with in vitro enzyme turnover numbers. However, NIDLE-flux results in a 1.4-fold increase in the size of the estimated maximal in vivo catalytic rates in comparison to the contenders. Integration of the maximum in vivo catalytic rates with publically available proteomics and metabolomics data provide a better match to fluxes estimated by NIDLE-flux. Therefore, NIDLE-flux facilitates more effective usage of proteomics data to estimate proxies for kcatomes.}, language = {en} }