@article{46310, abstract = {{Classic automated algorithm selection (AS) for (combinatorial) optimization problems heavily relies on so-called instance features, i.e., numerical characteristics of the problem at hand ideally extracted with computationally low-demanding routines. For the traveling salesperson problem (TSP) a plethora of features have been suggested. Most of these features are, if at all, only normalized imprecisely raising the issue of feature values being strongly affected by the instance size. Such artifacts may have detrimental effects on algorithm selection models. We propose a normalization for two feature groups which stood out in multiple AS studies on the TSP: (a) features based on a minimum spanning tree (MST) and (b) nearest neighbor relationships of the input instance. To this end we theoretically derive minimum and maximum values for properties of MSTs and k-nearest neighbor graphs (NNG) of Euclidean graphs. We analyze the differences in feature space between normalized versions of these features and their unnormalized counterparts. Our empirical investigations on various TSP benchmark sets point out that the feature scaling succeeds in eliminating the effect of the instance size. A proof-of-concept AS-study shows promising results: models trained with normalized features tend to outperform those trained with the respective vanilla features.}}, author = {{Heins, Jonathan and Bossek, Jakob and Pohl, Janina and Seiler, Moritz and Trautmann, Heike and Kerschke, Pascal}}, issn = {{0304-3975}}, journal = {{Theoretical Computer Science}}, keywords = {{Feature normalization, Algorithm selection, Traveling salesperson problem}}, pages = {{123--145}}, title = {{{A study on the effects of normalized TSP features for automated algorithm selection}}}, doi = {{https://doi.org/10.1016/j.tcs.2022.10.019}}, volume = {{940}}, year = {{2023}}, } @inproceedings{48898, abstract = {{Automated Algorithm Configuration (AAC) usually takes a global perspective: it identifies a parameter configuration for an (optimization) algorithm that maximizes a performance metric over a set of instances. However, the optimal choice of parameters strongly depends on the instance at hand and should thus be calculated on a per-instance basis. We explore the potential of Per-Instance Algorithm Configuration (PIAC) by using Reinforcement Learning (RL). To this end, we propose a novel PIAC approach that is based on deep neural networks. We apply it to predict configurations for the Lin\textendash Kernighan heuristic (LKH) for the Traveling Salesperson Problem (TSP) individually for every single instance. To train our PIAC approach, we create a large set of 100000 TSP instances with 2000 nodes each \textemdash currently the largest benchmark set to the best of our knowledge. We compare our approach to the state-of-the-art AAC method Sequential Model-based Algorithm Configuration (SMAC). The results show that our PIAC approach outperforms this baseline on both the newly created instance set and established instance sets.}}, author = {{Seiler, Moritz and Rook, Jeroen and Heins, Jonathan and Preuß, Oliver Ludger and Bossek, Jakob and Trautmann, Heike}}, booktitle = {{2023 IEEE Symposium Series on Computational Intelligence (SSCI)}}, pages = {{361 -- 368}}, title = {{{Using Reinforcement Learning for Per-Instance Algorithm Configuration on the TSP}}}, doi = {{10.1109/SSCI52147.2023.10372008}}, year = {{2023}}, } @inbook{46300, author = {{Niemann, Marco and Assenmacher, Dennis and Brunk, Jens and Riehle, Dennis Maximilian and Becker, Jörg and Trautmann, Heike}}, booktitle = {{Hate Speech — Definitionen, Ausprägungen, Lösungen}}, editor = {{Weitzel, Gerrit and Mündges, Stephan}}, isbn = {{978-3-658-35658-3}}, pages = {{249–274}}, publisher = {{VS Verlag für Sozialwissenschaften}}, title = {{{(Semi-)Automatische Kommentarmoderation zur Erhaltung Konstruktiver Diskurse}}}, doi = {{10.1007/978-3-658-35658-3_13}}, year = {{2022}}, } @inproceedings{46301, author = {{Assenmacher, D and Trautmann, Heike}}, booktitle = {{Intelligent Information and Database Systems}}, editor = {{et al. Tran, T}}, pages = {{3–16}}, publisher = {{Springer International Publishing}}, title = {{{Textual One-Pass Stream Clustering with Automated Distance Threshold Adaption}}}, doi = {{10.1007/978-3-031-21743-2_1}}, year = {{2022}}, } @article{46316, abstract = {{ Computational social science uses computational and statistical methods in order to evaluate social interaction. The public availability of data sets is thus a necessary precondition for reliable and replicable research. These data allow researchers to benchmark the computational methods they develop, test the generalizability of their findings, and build confidence in their results. When social media data are concerned, data sharing is often restricted for legal or privacy reasons, which makes the comparison of methods and the replicability of research results infeasible. Social media analytics research, consequently, faces an integrity crisis. How is it possible to create trust in computational or statistical analyses, when they cannot be validated by third parties? In this work, we explore this well-known, yet little discussed, problem for social media analytics. We investigate how this problem can be solved by looking at related computational research areas. Moreover, we propose and implement a prototype to address the problem in the form of a new evaluation framework that enables the comparison of algorithms without the need to exchange data directly, while maintaining flexibility for the algorithm design. }}, author = {{Assenmacher, Dennis and Weber, Derek and Preuss, Mike and Valdez, André Calero and Bradshaw, Alison and Ross, Björn and Cresci, Stefano and Trautmann, Heike and Neumann, Frank and Grimme, Christian}}, journal = {{Social Science Computer Review}}, number = {{6}}, pages = {{1496--1522}}, title = {{{Benchmarking Crisis in Social Media Analytics: A Solution for the Data-Sharing Problem}}}, doi = {{10.1177/08944393211012268}}, volume = {{40}}, year = {{2022}}, } @inproceedings{46306, abstract = {{Hyperparameter optimization (HPO) is a key component of machine learning models for achieving peak predictive performance. While numerous methods and algorithms for HPO have been proposed over the last years, little progress has been made in illuminating and examining the actual structure of these black-box optimization problems. Exploratory landscape analysis (ELA) subsumes a set of techniques that can be used to gain knowledge about properties of unknown optimization problems. In this paper, we evaluate the performance of five different black-box optimizers on 30 HPO problems, which consist of two-, three- and five-dimensional continuous search spaces of the XGBoost learner trained on 10 different data sets. This is contrasted with the performance of the same optimizers evaluated on 360 problem instances from the black-box optimization benchmark (BBOB). We then compute ELA features on the HPO and BBOB problems and examine similarities and differences. A cluster analysis of the HPO and BBOB problems in ELA feature space allows us to identify how the HPO problems compare to the BBOB problems on a structural meta-level. We identify a subset of BBOB problems that are close to the HPO problems in ELA feature space and show that optimizer performance is comparably similar on these two sets of benchmark problems. We highlight open challenges of ELA for HPO and discuss potential directions of future research and applications.}}, author = {{Schneider, Lennart and Schäpermeier, Lennart and Prager, Raphael Patrick and Bischl, Bernd and Trautmann, Heike and Kerschke, Pascal}}, booktitle = {{Parallel Problem Solving from Nature — PPSN XVII}}, editor = {{Rudolph, Günter and Kononova, Anna V. and Aguirre, Hernán and Kerschke, Pascal and Ochoa, Gabriela and Tušar, Tea}}, isbn = {{978-3-031-14714-2}}, pages = {{575–589}}, publisher = {{Springer International Publishing}}, title = {{{HPO x ELA: Investigating Hyperparameter Optimization Landscapes by Means of Exploratory Landscape Analysis}}}, doi = {{10.1007/978-3-031-14714-2_40}}, year = {{2022}}, } @article{46308, abstract = {{Single-objective continuous optimization can be challenging, especially when dealing with multimodal problems. This work sheds light on the effects that multi-objective optimization may have in the single-objective space. For this purpose, we examine the inner mechanisms of the recently developed sophisticated local search procedure SOMOGSA. This method solves multimodal single-objective continuous optimization problems based on first expanding the problem with an additional objective (e.g., a sphere function) to the bi-objective domain and subsequently exploiting local structures of the resulting landscapes. Our study particularly focuses on the sensitivity of this multiobjectivization approach w.r.t. (1) the parametrization of the artificial second objective, as well as (2) the position of the initial starting points in the search space. As SOMOGSA is a modular framework for encapsulating local search, we integrate Nelder–Mead local search as optimizer in the respective module and compare the performance of the resulting hybrid local search to its original single-objective counterpart. We show that the SOMOGSA framework can significantly boost local search by multiobjectivization. Hence, combined with more sophisticated local search and metaheuristics, this may help solve highly multimodal optimization problems in the future.}}, author = {{Aspar, Pelin and Steinhoff, Vera and Schäpermeier, Lennart and Kerschke, Pascal and Trautmann, Heike and Grimme, Christian}}, journal = {{Natural Computing}}, pages = {{1–15}}, title = {{{The objective that freed me: a multi-objective local search approach for continuous single-objective optimization}}}, doi = {{10.1007/s11047-022-09919-w}}, volume = {{1}}, year = {{2022}}, } @inproceedings{48861, abstract = {{Generating instances of different properties is key to algorithm selection methods that differentiate between the performance of different solvers for a given combinatorial optimization problem. A wide range of methods using evolutionary computation techniques has been introduced in recent years. With this paper, we contribute to this area of research by providing a new approach based on quality diversity (QD) that is able to explore the whole feature space. QD algorithms allow to create solutions of high quality within a given feature space by splitting it up into boxes and improving solution quality within each box. We use our QD approach for the generation of TSP instances to visualize and analyze the variety of instances differentiating various TSP solvers and compare it to instances generated by established approaches from the literature.}}, author = {{Bossek, Jakob and Neumann, Frank}}, booktitle = {{Proceedings of the Genetic and Evolutionary Computation Conference}}, isbn = {{978-1-4503-9237-2}}, keywords = {{instance features, instance generation, quality diversity, TSP}}, pages = {{186–194}}, publisher = {{Association for Computing Machinery}}, title = {{{Exploring the Feature Space of TSP Instances Using Quality Diversity}}}, doi = {{10.1145/3512290.3528851}}, year = {{2022}}, } @inproceedings{48868, author = {{Bossek, Jakob and Neumann, Aneta and Neumann, Frank}}, booktitle = {{Proceedings of the Genetic and Evolutionary Computation Conference Companion}}, isbn = {{978-1-4503-9268-6}}, pages = {{824–842}}, publisher = {{Association for Computing Machinery}}, title = {{{Evolutionary Diversity Optimization for Combinatorial Optimization: Tutorial at GECCO’22, Boston, USA}}}, doi = {{10.1145/3520304.3533626}}, year = {{2022}}, } @inproceedings{48882, abstract = {{In multimodal multi-objective optimization (MMMOO), the focus is not solely on convergence in objective space, but rather also on explicitly ensuring diversity in decision space. We illustrate why commonly used diversity measures are not entirely appropriate for this task and propose a sophisticated basin-based evaluation (BBE) method. Also, BBE variants are developed, capturing the anytime behavior of algorithms. The set of BBE measures is tested by means of an algorithm configuration study. We show that these new measures also transfer properties of the well-established hypervolume (HV) indicator to the domain of MMMOO, thus also accounting for objective space convergence. Moreover, we advance MMMOO research by providing insights into the multimodal performance of the considered algorithms. Specifically, algorithms exploiting local structures are shown to outperform classical evolutionary multi-objective optimizers regarding the BBE variants and respective trade-off with HV.}}, author = {{Heins, Jonathan and Rook, Jeroen and Schäpermeier, Lennart and Kerschke, Pascal and Bossek, Jakob and Trautmann, Heike}}, booktitle = {{Parallel Problem Solving from Nature (PPSN XVII)}}, editor = {{Rudolph, Günter and Kononova, Anna V. and Aguirre, Hernán and Kerschke, Pascal and Ochoa, Gabriela and Tusar, Tea}}, isbn = {{978-3-031-14714-2}}, keywords = {{Anytime behavior, Benchmarking, Continuous optimization, Multi-objective optimization, Multimodality, Performance metric}}, pages = {{192–206}}, publisher = {{Springer International Publishing}}, title = {{{BBE: Basin-Based Evaluation of Multimodal Multi-objective Optimization Problems}}}, doi = {{10.1007/978-3-031-14714-2_14}}, year = {{2022}}, } @inproceedings{48894, abstract = {{Recently different evolutionary computation approaches have been developed that generate sets of high quality diverse solutions for a given optimisation problem. Many studies have considered diversity 1) as a mean to explore niches in behavioural space (quality diversity) or 2) to increase the structural differences of solutions (evolutionary diversity optimisation). In this study, we introduce a co-evolutionary algorithm to simultaneously explore the two spaces for the multi-component traveling thief problem. The results show the capability of the co-evolutionary algorithm to achieve significantly higher diversity compared to the baseline evolutionary diversity algorithms from the literature.}}, author = {{Nikfarjam, Adel and Neumann, Aneta and Bossek, Jakob and Neumann, Frank}}, booktitle = {{Parallel Problem Solving from Nature (PPSN XVII)}}, editor = {{Rudolph, Günter and Kononova, Anna V. and Aguirre, Hernán and Kerschke, Pascal and Ochoa, Gabriela and Tu\v sar, Tea}}, isbn = {{978-3-031-14714-2}}, keywords = {{Co-evolutionary algorithms, Evolutionary diversity optimisation, Quality diversity, Traveling thief problem}}, pages = {{237–249}}, publisher = {{Springer International Publishing}}, title = {{{Co-Evolutionary Diversity Optimisation for the Traveling Thief Problem}}}, doi = {{10.1007/978-3-031-14714-2_17}}, year = {{2022}}, } @article{48878, abstract = {{Due to the rise of continuous data-generating applications, analyzing data streams has gained increasing attention over the past decades. A core research area in stream data is stream classification, which categorizes or detects data points within an evolving stream of observations. Areas of stream classification are diverse\textemdash ranging, e.g., from monitoring sensor data to analyzing a wide range of (social) media applications. Research in stream classification is related to developing methods that adapt to the changing and potentially volatile data stream. It focuses on individual aspects of the stream classification pipeline, e.g., designing suitable algorithm architectures, an efficient train and test procedure, or detecting so-called concept drifts. As a result of the many different research questions and strands, the field is challenging to grasp, especially for beginners. This survey explores, summarizes, and categorizes work within the domain of stream classification and identifies core research threads over the past few years. It is structured based on the stream classification process to facilitate coordination within this complex topic, including common application scenarios and benchmarking data sets. Thus, both newcomers to the field and experts who want to widen their scope can gain (additional) insight into this research area and find starting points and pointers to more in-depth literature on specific issues and research directions in the field.}}, author = {{Clever, Lena and Pohl, Janina Susanne and Bossek, Jakob and Kerschke, Pascal and Trautmann, Heike}}, issn = {{2076-3417}}, journal = {{Applied Sciences}}, keywords = {{big data, data mining, data stream analysis, machine learning, stream classification, supervised learning}}, number = {{18}}, pages = {{9094}}, publisher = {{{Multidisciplinary Digital Publishing Institute}}}, title = {{{Process-Oriented Stream Classification Pipeline: A Literature Review}}}, doi = {{10.3390/app12189094}}, volume = {{12}}, year = {{2022}}, } @inproceedings{48896, abstract = {{Hardness of Multi-Objective (MO) continuous optimization problems results from an interplay of various problem characteristics, e. g. the degree of multi-modality. We present a benchmark study of classical and diversity focused optimizers on multi-modal MO problems based on automated algorithm configuration. We show the large effect of the latter and investigate the trade-off between convergence in objective space and diversity in decision space.}}, author = {{Rook, Jeroen and Trautmann, Heike and Bossek, Jakob and Grimme, Christian}}, booktitle = {{Proceedings of the Genetic and Evolutionary Computation Conference Companion}}, isbn = {{978-1-4503-9268-6}}, keywords = {{configuration, multi-modality, multi-objective optimization}}, pages = {{356–359}}, publisher = {{Association for Computing Machinery}}, title = {{{On the Potential of Automated Algorithm Configuration on Multi-Modal Multi-Objective Optimization Problems}}}, doi = {{10.1145/3520304.3528998}}, year = {{2022}}, } @article{52532, author = {{Rodrigues, Agatha S. and Kerschke, Pascal and Pereira, Carlos Alberto De Bragança and Trautmann, Heike and Wagner, Carolin and Hellingrath, Bernd and Polpo, Adriano}}, journal = {{Comput. Stat.}}, number = {{1}}, pages = {{355–379}}, title = {{{Estimation of component reliability from superposed renewal processes by means of latent variables}}}, doi = {{10.1007/S00180-021-01124-0}}, volume = {{37}}, year = {{2022}}, } @inproceedings{46307, abstract = {{Exploratory Landscape Analysis is a powerful technique for numerically characterizing landscapes of single-objective continuous optimization problems. Landscape insights are crucial both for problem understanding as well as for assessing benchmark set diversity and composition. Despite the irrefutable usefulness of these features, they suffer from their own ailments and downsides. Hence, in this work we provide a collection of different approaches to characterize optimization landscapes. Similar to conventional landscape features, we require a small initial sample. However, instead of computing features based on that sample, we develop alternative representations of the original sample. These range from point clouds to 2D images and, therefore, are entirely feature-free. We demonstrate and validate our devised methods on the BBOB testbed and predict, with the help of Deep Learning, the high-level, expert-based landscape properties such as the degree of multimodality and the existence of funnel structures. The quality of our approaches is on par with methods relying on the traditional landscape features. Thereby, we provide an exciting new perspective on every research area which utilizes problem information such as problem understanding and algorithm design as well as automated algorithm configuration and selection.}}, author = {{Seiler, Moritz and Prager, Raphael Patrick and Kerschke, Pascal and Trautmann, Heike}}, booktitle = {{Proceedings of the Genetic and Evolutionary Computation Conference}}, isbn = {{9781450392372}}, pages = {{657–665}}, publisher = {{Association for Computing Machinery}}, title = {{{A Collection of Deep Learning-based Feature-Free Approaches for Characterizing Single-Objective Continuous Fitness Landscapes}}}, doi = {{10.1145/3512290.3528834}}, year = {{2022}}, } @inproceedings{46304, abstract = {{In recent years, feature-based automated algorithm selection using exploratory landscape analysis has demonstrated its great potential in single-objective continuous black-box optimization. However, feature computation is problem-specific and can be costly in terms of computational resources. This paper investigates feature-free approaches that rely on state-of-the-art deep learning techniques operating on either images or point clouds. We show that point-cloud-based strategies, in particular, are highly competitive and also substantially reduce the size of the required solver portfolio. Moreover, we highlight the effect and importance of cost-sensitive learning in automated algorithm selection models.}}, author = {{Prager, Raphael Patrick and Seiler, Moritz and Trautmann, Heike and Kerschke, Pascal}}, booktitle = {{Parallel Problem Solving from Nature — PPSN XVII}}, editor = {{Rudolph, Günter and Kononova, Anna V. and Aguirre, Hernán and Kerschke, Pascal and Ochoa, Gabriela and Tušar, Tea}}, isbn = {{978-3-031-14714-2}}, pages = {{3–17}}, publisher = {{Springer International Publishing}}, title = {{{Automated Algorithm Selection in Single-Objective Continuous Optimization: A Comparative Study of Deep Learning and Landscape Analysis Methods}}}, doi = {{10.1007/978-3-031-14714-2_1}}, year = {{2022}}, } @inproceedings{46303, abstract = {{Social media platforms are essential for information sharing and, thus, prone to coordinated dis- and misinformation campaigns. Nevertheless, research in this area is hampered by strict data sharing regulations imposed by the platforms, resulting in a lack of benchmark data. Previous work focused on circumventing these rules by either pseudonymizing the data or sharing fragments. In this work, we will address the benchmarking crisis by presenting a methodology that can be used to create artificial campaigns out of original campaign building blocks. We conduct a proof-of-concept study using the freely available generative language model GPT-Neo in this context and demonstrate that the campaign patterns can flexibly be adapted to an underlying social media stream and evade state-of-the-art campaign detection approaches based on stream clustering. Thus, we not only provide a framework for artificial benchmark generation but also demonstrate the possible adversarial nature of such benchmarks for challenging and advancing current campaign detection methods.}}, author = {{Pohl, Janina Susanne and Assenmacher, Dennis and Seiler, Moritz and Trautmann, Heike and Grimme, Christian}}, booktitle = {{Workshop Proceedings of the 16$^th$ International Conference on Web and Social Media (ICWSM)}}, editor = {{the Advancement of Artificial Intelligence (AAAI) Association, for}}, pages = {{1–10}}, publisher = {{AAAI Press}}, title = {{{Artificial Social Media Campaign Creation for Benchmarking and Challenging Detection Approaches}}}, doi = {{10.36190/2022.91}}, year = {{2022}}, } @article{46309, abstract = {{Due to the rise of continuous data-generating applications, analyzing data streams has gained increasing attention over the past decades. A core research area in stream data is stream classification, which categorizes or detects data points within an evolving stream of observations. Areas of stream classification are diverse—ranging, e.g., from monitoring sensor data to analyzing a wide range of (social) media applications. Research in stream classification is related to developing methods that adapt to the changing and potentially volatile data stream. It focuses on individual aspects of the stream classification pipeline, e.g., designing suitable algorithm architectures, an efficient train and test procedure, or detecting so-called concept drifts. As a result of the many different research questions and strands, the field is challenging to grasp, especially for beginners. This survey explores, summarizes, and categorizes work within the domain of stream classification and identifies core research threads over the past few years. It is structured based on the stream classification process to facilitate coordination within this complex topic, including common application scenarios and benchmarking data sets. Thus, both newcomers to the field and experts who want to widen their scope can gain (additional) insight into this research area and find starting points and pointers to more in-depth literature on specific issues and research directions in the field.}}, author = {{Clever, Lena and Pohl, Janina Susanne and Bossek, Jakob and Kerschke, Pascal and Trautmann, Heike}}, journal = {{Applied Sciences}}, number = {{8}}, pages = {{1–44}}, title = {{{Process-Oriented Stream Classification Pipeline: A Literature Review}}}, doi = {{10.3390/app12189094}}, volume = {{12}}, year = {{2022}}, } @inproceedings{46302, author = {{Heins, J and Rook, J and Schäpermeier, L and Kerschke, P and Bossek, Jakob and Trautmann, Heike}}, booktitle = {{Parallel Problem Solving from Nature — PPSN XVII}}, editor = {{Rudolph, G and Kononova, AV and Aguirre, H and Kerschke, P and Ochoa, G and Tušar, T}}, isbn = {{978-3-031-14714-2}}, pages = {{192–206}}, publisher = {{Springer International Publishing}}, title = {{{BBE: Basin-Based Evaluation of Multimodal Multi-objective Optimization Problems}}}, year = {{2022}}, } @inproceedings{46305, abstract = {{Hardness of Multi-Objective (MO) continuous optimization problems results from an interplay of various problem characteristics, e. g. the degree of multi-modality. We present a benchmark study of classical and diversity focused optimizers on multi-modal MO problems based on automated algorithm configuration. We show the large effect of the latter and investigate the trade-off between convergence in objective space and diversity in decision space.}}, author = {{Rook, J and Trautmann, Heike and Bossek, Jakob and Grimme, C}}, booktitle = {{Proceedings of the Genetic and Evolutionary Computation Conference Companion}}, editor = {{Fieldsend, J and Wagner, M.}}, isbn = {{9781450392686}}, pages = {{356–359}}, publisher = {{Association for Computing Machinery}}, title = {{{On the Potential of Automated Algorithm Configuration on Multi-Modal Multi-Objective Optimization Problems}}}, doi = {{10.1145/3520304.3528998}}, year = {{2022}}, }