@misc{KempkeMaherRehfeldtetal.2026, author = {Kempke, Nils-Christian and Maher, Stephen John and Rehfeldt, Daniel and Gleixner, Ambros and Koch, Thorsten and Uslu, Svenja}, title = {Distributed Parallel Structure-Aware Presolving for Arrowhead Linear Programs}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-103034}, year = {2026}, abstract = {We present a structure-aware parallel presolve framework specialized to arrowhead linear programs (AHLPs) and designed for high-performance computing (HPC) environments, integrated into the parallel interior point solver PIPS-IPM++. Large-scale LPs arising from automated model generation frequently contain redundancies and numerical pathologies that necessitate effective presolve, yet existing presolve techniques are primarily serial or structure-agnostic and can become time-consuming in parallel solution workflows. Within PIPS-IPM++, AHLPs are stored in distributed memory, and our presolve builds on this to apply a highly parallel, distributed presolve across compute nodes while keeping communication overhead low and preserving the underlying arrowhead structure. We demonstrate the scalability and effectiveness of our approach on a diverse set of AHLPs and compare it against state-of-the-art presolve implementations, including PaPILO and the presolve implemented within Gurobi. Even on a single machine, our presolve significantly outperforms PaPILO by a factor of 18 and Gurobi's presolve by a factor of 6 in terms of shifted geometric mean runtime, while reducing the problems by a similar amount to PaPILO. Using a distributed compute environment, we outperform Gurobi's presolve by a factor of 13.}, language = {en} } @misc{LindnerMehlBartoszuketal.2025, author = {Lindner, Niels and Mehl, Lukas and Bartoszuk, Karolina and Berendes, Sarah and Zittel, Janina}, title = {Demand Uncertainty in Energy Systems: Scenario Catalogs vs. Integrated Robust Optimization}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-102404}, year = {2025}, abstract = {Designing efficient energy systems is indispensable for shaping a more sustainable society. This involves making infrastructure investment decisions that must be valid for a long-term time horizon. While energy system optimization models constitute a powerful technique to support planning decisions, they need to cope with inherent uncertainty. For example, predicting future demand on a scale of decades is not only an intricate challenge in itself, but small fluctuations in such a forecast might also largely impact the layout of a complex energy system. In this paper, we compare two methodologies of capturing demand uncertainty for linear-programming based energy system optimization models. On one hand, we generate and analyze catalogs of varying demand scenarios, where each individual scenario is considered independently, so that the optimization produces scenario-specific investment pathways. On the other hand, we make use of robust linear programming to meet the demand of all scenarios at once. Since including a multitude of scenarios increases the size and complexity of the optimization model, we will show how to use warm-starting approaches to accelerate the computation process, by exploiting the similar structure of the linear program across different demand inputs. This allows to integrate a meaningful number of demand scenarios with fully-fledged energy system models. We demonstrate the practical use of our methods in a case study of the Berlin-Brandenburg area in Germany, a region that contains both a metropolitan area and its rural surroundings. As a backbone, we use the open-source framework oemof to create a sector-coupled optimization model for planning an energy system with up to 100\% reduction of greenhouse gas emissions. This model features a fine-grained temporal resolution of one hour for the full year 2050. We consider uncertainty in demand for electricity, hydrogen, natural gas, central, and decentral heat. Based on our computations, we analyze the trade-offs in terms of quality and computation time for scenario catalogs and the robust optimization approach. We further demonstrate that our procedure provides a valuable strategy for decision makers to gain insight on the robustness and sensitivity of solutions regarding demand variability.}, language = {en} } @misc{EbertSchlechteSchwartz2025, author = {Ebert, Patricia and Schlechte, Thomas and Schwartz, Stephan}, title = {Scheduling for German Road Inspectors}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-101999}, year = {2025}, abstract = {For the yearly over 500,000 vehicle inspections of the German Federal Logistics and Mobility Office (BALM), crew rosters must be scheduled to efficiently achieve Germany's road inspection control targets. For that, we present a model to solve the respective duty scheduling and crew rostering problem in order to obtain duty rosters that comply with numerous legal regulations while maximizing the 'control success' to achieve the control targets. We formulate the Template Assignment Problem, which can be modelled as a large scale mixed-integer linear program. Here, feasible combinations of control topics are assigned to the duties using a hypergraph approach. The model is used in production by BALM, and we prove its effectiveness on a number of real-world instances.}, language = {en} } @misc{ZakiyevaPetkovic2025, author = {Zakiyeva, Nazgul and Petkovic, Milena}, title = {Large-scale functional network time series model solved with mathematical programming approach}, journal = {Econometrics and Statistics}, doi = {10.1016/j.ecosta.2025.10.001}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-101936}, year = {2025}, abstract = {A functional network autoregressive model is proposed for studying large-scale network time series observed at high temporal resolution. The model incorporates high-dimensional curves to capture both serial and cross-sectional dependence in large-scale network functional time series. Estimation of the model is approached using a Mixed Integer Optimization method. Simulation studies confirm the consistency of parameter and adjacency matrix estimation. The method is applied to data from a real-life natural gas supply network. Compared to alternative prediction models, the proposed model delivers more accurate day-ahead hourly out-of-sample forecasts of the gas inflows and outflows at most gas nodes.}, language = {en} } @misc{ShinanoVigerske2025, author = {Shinano, Yuji and Vigerske, Stefan}, title = {Smoothie: Mixing the strongest MIP solvers to solve hard MIP instances on supercomputers - Phase I development}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-101906}, year = {2025}, abstract = {Mixed-Integer Linear Programming (MIP) is applicable to such a wide range of real-world decision problems that the competition for the best code to solve such problems has lead to tremendous progress over the last decades. While current solvers can solve some of the problems that seemed completely out-of-reach just 10 years ago, there are always relevant MIP problems that currently cannot be solved. With the Smoothie solver we intend to solve extremely hard MIP problems by building on the many years that went into the development of several state-of-the-art MIP solvers and by utilizing some of the largest computing resources available. The high-level task parallelization framework UG (Ubiquity Generator) is used and extended by Smoothie to build a solver that uses large-scale parallelization to distribute the solution of a single MIP on a shared- or distributed-memory computing infrastructure, thereby employing several established MIP solvers simultaneously. For the first development phase, which is the topic of this report, both FICO Xpress and Gurobi are used in concurrent mode on a single machine, while information on incumbent solutions and explored branch-and-bound subtrees is exchanged. A dynamic restarting mechanism ensures that solver configurations are selected that promise most suitable for the MIP to be solved. We report on initial findings using this early version of Smoothie on unsolved problems from MIPLIB 2017.}, language = {en} } @misc{PedersenLindnerRehfeldtetal.2025, author = {Pedersen, Jaap and Lindner, Niels and Rehfeldt, Daniel and Koch, Thorsten}, title = {Comparing Branching Rules for the Quota Steiner Tree Problem with Interference}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-101250}, year = {2025}, abstract = {Branching decisions play a crucial role in branch-and-bound algorithms for solving combinatorial optimization problems. In this paper, we investigate several branching rules applied to the Quota Steiner Tree Problem with Interference (QSTPI). The Quota Steiner Tree Problem (QSTP) generalizes the classical Steiner Tree Problem (STP) in graphs by seeking a minimum-cost tree that connects a subset of profit-associated vertices to meet a given quota. The extended version, QSTPI, introduces interference among vertices: Selecting certain vertices simultaneously reduces their individual contributions to the overall profit. This problem arises, for example, in positioning and connecting wind turbines, where turbines possibly shadow other turbines, reducing their energy yield. While exact solvers for standard STP-related problems often rely heavily on reduction techniques and cutting-plane methods - rarely generating large branch-and-bound trees - experiments reveal that large instances of QSTPI require significantly more branching to compute provably optimal solutions. In contrast to branching on variables, we utilize the combinatorial structure of the QSTPI by branching on the graph's vertices. We adapt classical and problem-specific branching rules and present a comprehensive computational study comparing the effectiveness of these branching strategies.}, language = {en} } @misc{MehlLindnerBartoszuketal.2025, author = {Mehl, Lukas and Lindner, Niels and Bartoszuk, Karolina and Zittel, Janina}, title = {Prototypical warm-starts for demand-robust LP-based energy system optimization}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-101242}, year = {2025}, abstract = {The expressiveness of energy system optimization models (ESOMs) depends on a multitude of exogenous parameters. For example, sound estimates of the future energy demand are essential to enable qualified decisions on long-term investments. However, the enormous demand fluctuations even on a fine-grained scale diminish the computational performance of large-scale ESOMs. We therefore propose a clustering-and-decomposition method for linear programming based ESOMs that first identifies and solves prototypical demand scenarios with the dual simplex algorithm, and then composes dual optimal prototype bases to a warm-start basis for the full model. We evaluate the feasibility and computational efficiency our approach on a real-world case study, using a sector-coupled ESOM with hourly resolution for the Berlin-Brandenburg area in Germany, based on the oemof framework.}, language = {en} } @misc{LindnerLiebchen2025, author = {Lindner, Niels and Liebchen, Christian}, title = {A two-stage model for periodic timetabling with fixed line activities}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-101234}, year = {2025}, abstract = {The timetable is a central pillar of any public transportation system. Constructing and optimizing periodic timetables in terms of passenger comfort and operational efficiency leads to NP-hard optimization problems that are also computationally challenging in applications. The Periodic Event Scheduling Problem (PESP) as standard mathematical tool benefits from its succinct formulation and rich combinatorial structure, but suffers from poor linear programming relaxations and weak dual bounds. These difficulties persist in a reduced version, where driving and dwelling activities of the lines are assumed to be fixed. In this case, fixing the initial departure time of each line fully determines the timetable, and for each pair of lines, the resulting (weighted) transfer durations can be expressed in terms of a piecewise linear non-convex function in terms of the difference of the initial times. When the number of activities between two lines is bounded, this function can be computed in polynomial time. By inserting precomputed piecewise linear functions into a mixed-integer program with the initial departure times as variables, we introduce an equivalent formulation for reduced PESP instances. The model bears analogies with quadratic semi-assignment approaches and offers alternative ways to compute primal and dual bounds. We evaluate the computational behavior of our approach on realistic benchmarking instances.}, language = {en} } @misc{RiedmuellerZittelKoch2025, author = {Riedm{\"u}ller, Stephanie and Zittel, Janina and Koch, Thorsten}, title = {Warm-starting Strategies in Scalarization Methods for Multi-Objective Optimization}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-101073}, year = {2025}, abstract = {We explore how warm-starting strategies can be integrated into scalarization-based approaches for multi-objective optimization in (mixed) integer linear programming. Scalarization methods remain widely used classical techniques to compute Pareto-optimal solutions in applied settings. They are favored due to their algorithmic simplicity and broad applicability across continuous and integer programs with an arbitrary number of objectives. While warm-starting has been applied in this context before, a systematic methodology and analysis remain lacking. We address this gap by providing a theoretical characterization of warm-starting within scalarization methods, focusing on the sequencing of subproblems. However, optimizing the order of subproblems to maximize warm-start efficiency may conflict with alternative criteria, such as early identification of infeasible regions. We quantify these trade-offs through an extensive computational study.}, language = {en} } @misc{KempkeKoch2025, author = {Kempke, Nils-Christian and Koch, Thorsten}, title = {A GPU accelerated variant of Schroeppel-Shamir's algorithm for solving the market split problem}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-100554}, year = {2025}, abstract = {The market split problem (MSP), introduced by Cornu{\´e}jols and Dawande (1998), is a challenging binary optimization problem that performs poorly on state-of-the-art linear programming-based branch-and-cut solvers. We present a novel algorithm for solving the feasibility version of this problem, derived from Schroeppel-Shamir's algorithm for the one-dimensional subset sum problem. Our approach is based on exhaustively enumerating one-dimensional solutions of MSP and utilizing GPUs to evaluate candidate solutions across the entire problem. The resulting hybrid CPU-GPU implementation efficiently solves instances with up to 10 constraints and 90 variables. We demonstrate the algorithm's performance on benchmark problems, solving instances of size (9, 80) in less than fifteen minutes and (10, 90) in up to one day.}, language = {en} } @misc{VuLitzelKoch2025, author = {Vu, Thi Huong and Litzel, Ida and Koch, Thorsten}, title = {Similarity-based fuzzy clustering scientific articles: potentials and challenges from mathematical and computational perspectives}, arxiv = {http://arxiv.org/abs/2506.04045}, year = {2025}, abstract = {Fuzzy clustering, which allows an article to belong to multiple clusters with soft membership degrees, plays a vital role in analyzing publication data. This problem can be formulated as a constrained optimization model, where the goal is to minimize the discrepancy between the similarity observed from data and the similarity derived from a predicted distribution. While this approach benefits from leveraging state-of-the-art optimization algorithms, tailoring them to work with real, massive databases like OpenAlex or Web of Science -- containing about 70 million articles and a billion citations -- poses significant challenges. We analyze potentials and challenges of the approach from both mathematical and computational perspectives. Among other things, second-order optimality conditions are established, providing new theoretical insights, and practical solution methods are proposed by exploiting the problem's structure. Specifically, we accelerate the gradient projection method using GPU-based parallel computing to efficiently handle large-scale data.}, language = {en} } @misc{VuKoch2025, author = {Vu, Thi Huong and Koch, Thorsten}, title = {Clustering scientific publications: lessons learned through experiments with a real citation network}, arxiv = {http://arxiv.org/abs/2505.18180}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-100418}, year = {2025}, abstract = {Clustering scientific publications helps uncover research structures within bibliographic databases. Graph-based methods such as spectral, Louvain, and Leiden clustering are commonly used due to their ability to model citation networks. However, their effectiveness can diminish when applied to real-world data. This study evaluates these clustering algorithms on a citation graph of about 700,000 articles and 4.6 million citations from the Web of Science. The results show that while scalable methods like Louvain and Leiden perform efficiently, their default settings often yield poor partitioning. Meaningful outcomes require careful parameter tuning, especially for large networks with uneven structures, including a dense core and loosely connected papers. These findings highlight practical lessons about the challenges of large-scale data, method selection and tuning based on specific structures of bibliometric clustering tasks.}, language = {en} } @misc{RiedmuellerBuchholzZittel2025, author = {Riedm{\"u}ller, Stephanie and Buchholz, Annika and Zittel, Janina}, title = {Enhancing Multi-Energy Modeling: The Role of Mixed-Integer Optimization Decisions}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-100329}, year = {2025}, abstract = {The goal to decarbonize the energy sector has led to increased research in modeling and optimizing multi-energy systems. One of the most promising and popular techniques for modeling and solving (multi-)energy optimization problems is (multi-objective) mixed-integer programming, valued for its ability to represent the complexities of integrated energy systems. While the literature often focuses on deriving mathematical formulations and parameter settings, less attention is given to critical post-formulation decisions. Modeling multi-energy systems as mixed-integer linear optimization programs demands decisions across multiple degrees of freedom. Key steps include reducing a real-world multi energy network into an abstract topology, defining variables, formulating the relevant (in-)equalities to represent technical requirements, setting (multiple) objectives, and integrating these elements into a mixed-integer program (MIP). However, with these elements fixed, the specific transformation of the abstract topology into a graph structure and the construction of the MIP remain non-uniquely. These choices can significantly impact user-friendliness, problem size, and computational efficiency, thus affecting the feasibility and efficiency of modeling efforts. In this work, we identify and analyze the additional degrees of freedom and describe two distinct approaches to address them. The approaches are compared regarding mathematical equivalence, suitability for solution algorithms, and clarity of the underlying topology. A case study on a realistic subarea of Berlin's district heating network involving tri-objective optimization for a unit commitment problem demonstrates the practical significance of these decisions. By highlighting these critical yet often overlooked aspects, our work equips energy system modelers with insights to improve computational efficiency, scalability, and interpretability in their optimization efforts, ultimately enhancing the practicality and effectiveness of multi-energy system models.}, language = {en} } @misc{KempkeKoch2025, author = {Kempke, Nils-Christian and Koch, Thorsten}, title = {Low-precision first-order method-based fix-and-propagate heuristics for large-scale mixed-integer linear optimization}, issn = {1438-0064}, arxiv = {http://arxiv.org/abs/2503.10344}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-99612}, year = {2025}, abstract = {We investigate the use of low-precision first-order methods (FOMs) within a fix-and-propagate (FP) framework for solving mixed-integer programming problems (MIPs). FOMs, using only matrix-vector products instead of matrix factorizations, are well suited for GPU acceleration and have recently gained more attention for their application to large-scale linear programming problems (LPs). We employ PDLP, a variant of the Primal-Dual Hybrid Gradient (PDHG) method specialized to LP problems, to solve the LP-relaxation of our MIPs to low accuracy. This solution is used to motivate fixings within our fix-and-propagate framework. We implemented four different FP variants using primal and dual LP solution information. We evaluate the performance of our heuristics on MIPLIB 2017, showcasing that the low-accuracy LP solution produced by the FOM does not lead to a loss in quality of the FP heuristic solutions when compared to a high-accuracy interior-point method LP solution. Further, we use our FP framework to produce high-accuracy solutions for large-scale (up to 243 million non-zeros and 8 million decision variables) unit-commitment energy-system optimization models created with the modeling framework REMix. For the largest problems, we can generate solutions with under 2\% primal-dual gap in less than 4 hours, whereas commercial solvers cannot generate feasible solutions within two days of runtime. This study represents the first successful application of FOMs in large-scale mixed-integer optimization, demonstrating their efficacy and establishing a foundation for future research in this domain.}, language = {en} } @misc{KempkeKuntKatamishetal.2025, author = {Kempke, Nils-Christian and Kunt, Tim and Katamish, Bassel and Vanaret, Charlie and Sasanpour, Shima and Clarner, Jan-Patrick and Koch, Thorsten}, title = {Developing heuristic solution techniques for large-scale unit commitment models}, issn = {1438-0064}, arxiv = {http://arxiv.org/abs/2502.19012}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-99555}, year = {2025}, abstract = {Shifting towards renewable energy sources and reducing carbon emissions necessitate sophisticated energy system planning, optimization, and extension. Energy systems optimization models (ESOMs) often form the basis for political and operational decision-making. ESOMs are frequently formulated as linear (LPs) and mixed-integer linear (MIP) problems. MIPs allow continuous and discrete decision variables. Consequently, they are substantially more expressive than LPs but also more challenging to solve. The ever-growing size and complexity of ESOMs take a toll on the computational time of state-of-the-art commercial solvers. Indeed, for large-scale ESOMs, solving the LP relaxation -- the basis of modern MIP solution algorithms -- can be very costly. These time requirements can render ESOM MIPs impractical for real-world applications. This article considers a set of large-scale decarbonization-focused unit commitment models with expansion decisions based on the REMix framework (up to 83 million variables and 900,000 discrete decision variables). For these particular instances, the solution to the LP relaxation and the MIP optimum lie close. Based on this observation, we investigate the application of relaxation-enforced neighborhood search (RENS), machine learning guided rounding, and a fix-and-propagate (FP) heuristic as a standalone solution method. Our approach generated feasible solutions 20 to 100 times faster than GUROBI, achieving comparable solution quality with primal-dual gaps as low as 1\% and up to 35\%. This enabled us to solve numerous scenarios without lowering the quality of our models. For some instances that Gurobi could not solve within two days, our FP method provided feasible solutions in under one hour.}, language = {en} } @misc{Lindner2025, author = {Lindner, Niels}, title = {A Multi-Commodity Flow Heuristic for Integrated Periodic Timetabling for Railway Construction Sites}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-99449}, year = {2025}, abstract = {Rescheduling a railway system comprises many aspects, such as line planning, timetabling, track allocation, and vehicle scheduling. For periodic timetables, these features can be integrated into a single mixed-integer program extending the Periodic Event Scheduling Problem (PESP) with a routing component. We develop a multi-commodity-flow-based heuristic that allows to compute better solutions faster than a black-box MIP approach on real construction site scenarios on the S-Bahn Berlin network.}, language = {en} } @misc{PedersenLindnerRehfeldtetal.2025, author = {Pedersen, Jaap and Lindner, Niels and Rehfeldt, Daniel and Koch, Thorsten}, title = {Integrated Wind Farm Design: Optimizing Turbine Placement and Cable Routing with Wake Effects}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-99218}, year = {2025}, abstract = {An accelerated deployment of renewable energy sources is crucial for a successful transformation of the current energy system, with wind energy playing a key role in this transition. This study addresses the integrated wind farm layout and cable routing problem, a challenging nonlinear optimization problem. We model this problem as an extended version of the Quota Steiner Tree Problem (QSTP), optimizing turbine placement and network connectivity simultaneously to meet specified expansion targets. Our proposed approach accounts for the wake effect - a region of reduced wind speed induced by each installed turbine - and enforces minimum spacing between turbines. We introduce an exact solution framework in terms of the novel Quota Steiner Tree Problem with interference (QSTPI). By leveraging an interference-based splitting strategy, we develop an advanced solver capable of tackling large-scale problem instances. The presented approach outperforms generic state-of-the-art mixed integer programming solvers on our dataset by up to two orders of magnitude. Moreover, we demonstrate that our integrated method significantly reduces the costs in contrast to a sequential approach. Thus, we provide a planning tool that enhances existing planning methodologies for supporting a faster and cost-efficient expansion of wind energy.}, language = {en} } @misc{KempkeRehfeldtKoch2024, author = {Kempke, Nils-Christian and Rehfeldt, Daniel and Koch, Thorsten}, title = {A Massively Parallel Interior-Point-Method for Arrowhead Linear Programs}, issn = {1438-0064}, arxiv = {http://arxiv.org/abs/2412.07731}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-98829}, year = {2024}, abstract = {In practice, non-specialized interior point algorithms often cannot utilize the massively parallel compute resources offered by modern many- and multi-core compute platforms. However, efficient distributed solution techniques are required, especially for large-scale linear programs. This article describes a new decomposition technique for systems of linear equations implemented in the parallel interior-point solver PIPS-IPM++. The algorithm exploits a matrix structure commonly found in optimization problems: a doubly-bordered block-diagonal or arrowhead structure. This structure is preserved in the linear KKT systems solved during each iteration of the interior-point method. We present a hierarchical Schur complement decomposition that distributes and solves the linear optimization problem; it is designed for high-performance architectures and scales well with the availability of additional computing resources. The decomposition approach uses the border constraints' locality to decouple the factorization process. Our approach is motivated by large-scale unit-commitment problems. We demonstrate the performance of our method on a set of mid-to large-scale instances, some of which have more than 10^9 nonzeros in their constraint matrix.}, language = {en} } @misc{HosodaMaherShinano2024, author = {Hosoda, Junko and Maher, Stephen J. and Shinano, Yuji}, title = {Combining Benders' decomposition and parallelisation to solve large-scale adaptive network supply chain management problems}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-98744}, year = {2024}, abstract = {Integrated supply chain network design—combining warehouse clustering with inter- and intra-cluster vehicle routing—is a fundamental feature of supply chain management problems. In this paper, a Benders' decomposition-based parallel heuristic approach for the integrated long-haul and local vehicle routing problem is proposed. The proposed algorithm comprises lower- and upper-bound search algorithms running in parallel to find high-quality solutions for challenging supply chain management problems. A novel Benders' decomposition approach is proposed to aid the improvement in the lower bound for large-scale problems. The results demonstrate that the Benders' decomposition approach is effective in finding strong lower bounds and is beneficial for obtaining high-quality solutions.}, language = {en} } @misc{YuekselErguenLitzelPeng2024, author = {Yueksel-Erguen, Inci and Litzel, Ida and Peng, Hanqiu}, title = {Integrating Large Citation Datasets}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-98033}, year = {2024}, abstract = {This paper explores methods for building a comprehensive citation graph using big data techniques to evaluate scientific impact more accurately. Traditional citation metrics have limitations, and this work investigates merging large citation datasets to create a more accurate picture. Challenges of big data, like inconsistent data formats and lack of unique identifiers, are addressed through deduplication efforts, resulting in a streamlined and reliable merged dataset with over 119 million records and 1.4 billion citations. We demonstrate that merging large citation datasets builds a more accurate citation graph facilitating a more robust evaluation of scientific impact.}, language = {en} }