This paper introduces the DBpedia Temporal Knowledge Graph (DBpedia-TKG), an extension of the DBpedia extraction process to generate temporal versions of the knowledge graph. DBpedia has long served as a vital resource in the Semantic Web community and as a primary data source for research, offering structured information extracted from Wikipedia. However, it lacks a temporal dimension that captures the evolving nature of knowledge. Our approach addresses this gap by enabling the creation of temporal graph versions that reflect changes in Wikipedia pages across various revisions sourced from the Wikipedia meta-history dumps. Our implementation runs in a containerized data extraction system, scaling across an eight-node cluster to extract the first version in under three days. Our setup facilitates the generation of distinct DBpedia temporal graph variants through configurable settings, using different page extractors, temporal filters, and DBpedia ontology versions. In our initial evaluation, we present comprehensive statistics demonstrating the impact of Wikipedia changes on the extracted data and provide insights into the temporal diversity of the knowledge graph. Finally, we discuss the potential benefits of DBpedia Temporal KG for various research domains. The first English version consists of around 1.7 billion extracted triples between 270 million different time points. Resource type: Dataset License: CC BY-SA 4.0 Dataset DOI: https://doi.org/10.5281/zenodo.14532571 Code URL: https://github.com/dbpedia/dbpedia-temporal .

International audience

Abstract In 3D printing processes, there are many thermal stress related defects that can have a significant negative impact on the shape and size of the structure. Such anomalies in the heat transfer of the printing process need to be detected at an early stage. Understanding heat transfer is crucial, and simulation models can offer insights while reducing the need for costly experiments. Traditional numerical solvers for heat transfer can be complex to adapt to diverse printed part geometries, and their reliance on predefined mathematical models limits their flexibility. Our physics-informed deep learning (PIDL) approach eliminates the need for discretization, simplifying the analysis of complex geometries and enabling automation. The drawback of parametric PIDL is their scalability for high-dimensional problems. Computational time, energy and cost of training prevent real-time analysis. It often takes only a few seconds to print a single layer. We can show an energy efficient transfer and training strategy to reduce the computational effort of PIDL significantly. The approach is able to quantify relevant effects of thermal stresses and mitigate errors during selective laser melting (SLM). To this end, heat transfer is modelled, simulated and analysed using high-dimensional data obtained from printing experiments with different geometries of metal components. The proposed method is applied to the solving forward problem of heat transfer prediction. The governing results are based on the heat equation, which is integrated into a deep neural network (DNN).

In an industrial plant it is necessary to monitor the operation of the equipment. Deviations from normal operation should be detected as early as possible to avoid production failures or to keep their impact as small as possible. Valves are core components of plants and critical damage can occur if they are set to switch but in reality do not switch. Therefore, plant operators would like to detect such failures as early as possible. Valves with electrodynamic actuators offer a unique diagnostics option that allows for the early detection of valve malfunctions by their intrinsic properties alone. In particular, we measure the inrush current of the valve as a function of time. From the resulting signal, we derive the information, if the valve has switched or not. Machine learning (ML) methods can be used to accurately predict these valve errors. In this paper, a long-short term memory (LSTM)-convolutional neural network (CNN) and two differential equation-inspired neural networks are presented for encoding valves function anomalies to ensure the production capability of an industrial plant. For this purpose, derivatives of the inrush currents are considered and integrated into the deep neural networks (DNNs). The implementation of this diagnostics option is cheap and robust as no extra sensor on the valve is required.

Machine learning (ML) can help fight pandemics like COVID-19 by enabling rapid screening of large volumes of images.To perform data analysis while maintaining patient privacy, we create ML models that satisfy Differential Privacy (DP).Previous works exploring private COVID-19 models are in part based on small datasets, provide weaker or unclear privacy guarantees, and do not investigate practical privacy.We suggest improvements to address these open gaps.We account for inherent class imbalances and evaluate the utility-privacy trade-off more extensively and over stricter privacy budgets.Our evaluation is supported by empirically estimating practical privacy through black-box Membership Inference Attacks (MIAs).The introduced DP should help limit leakage threats posed by MIAs, and our practical analysis is the first to test this hypothesis on the COVID-19 classification task.Our results indicate that needed privacy levels might differ based on the task-dependent practical threat from MIAs.The results further suggest that with increasing DP guarantees, empirical privacy leakage only improves marginally, and DP therefore appears to have a limited impact on practical MIA defense.Our findings identify possibilities for better utility-privacy trade-offs, and we believe that empirical attack-specific privacy estimation can play a vital role in tuning for practical privacy.

Data integration tasks such as the creation and extension of knowledge graphs involve the fusion of heterogeneous entities from many sources. Matching and fusion of such entities require to also match and combine their properties (attributes). However, previous schema matching approaches mostly focus on two sources only and often rely on simple similarity measurements. They thus face problems in challenging use cases such as the integration of heterogeneous product entities from many sources. We therefore present a new machine learning-based property matching approach called LEAPME (LEArning-based Property Matching with Embeddings) that utilizes numerous features of both property names and instance values. The approach heavily makes use of word embeddings to better utilize the domain-specific semantics of both property names and instance values. The use of supervised machine learning helps exploit the predictive power of word embeddings. Our comparative evaluation against five baselines for several multi-source datasets with real-world data shows the high effectiveness of LEAPME. We also show that our approach is even effective when training data from another domain (transfer learning) is used.

Abstract Temporal property graphs are graphs whose structure and properties change over time. Temporal graph datasets tend to be large due to stored historical information, asking for scalable analysis capabilities. We give a complete overview of Gradoop, a graph dataflow system for scalable, distributed analytics of temporal property graphs which has been continuously developed since 2005. Its graph model TPGM allows bitemporal modeling not only of vertices and edges but also of graph collections. A declarative analytical language called GrALa allows analysts to flexibly define analytical graph workflows by composing different operators that support temporal graph analysis. Built on a distributed dataflow system, large temporal graphs can be processed on a shared-nothing cluster. We present the system architecture of Gradoop, its data model TPGM with composable temporal graph operators, like snapshot, difference, pattern matching, graph grouping and several implementation details. We evaluate the performance and scalability of selected operators and a composed workflow for synthetic and real-world temporal graphs with up to 283 M vertices and 1.8 B edges, and a graph lifetime of about 8 years with up to 20 M new edges per year. We also reflect on lessons learned from the Gradoop effort.

Data integration tasks such as the creation and extension of knowledge graphs involve the fusion of heterogeneous entities from many sources. Matching and fusion of such entities require to also match and combine their properties (attributes) . However, previous schema matching approaches mostly focus on two sources only and often rely on simple similarity measurements. They thus face problems in challenging use cases such as the integration of heterogeneous product entities from many sources. We therefore present a new machine learning-based property matching approach called LEAPME (LEArning-based Property Matching with Embeddings) that utilizes numerous features of both property names and instance values. The approach heavily makes use of word embeddings to better utilize the domain-specific semantics of both property names and instance values. The use of supervised machine learning helps exploit the predictive power of word embeddings.Our comparative evaluation against five baselines for several multi-source datasets with real-world data shows the high effectiveness of LEAPME.

Entity resolution targets at identifying records that represent the same real-world entity from one or more datasets. A major challenge in learning-based entity resolution is how to reduce the label cost for training. Due to the quadratic nature of record pair comparison, labeling is a costly task that often requires a significant effort from human experts. Inspired by recent advances of generative adversarial network (GAN), we propose a novel deep learning method, called ErGAN, to address the challenge. ErGAN consists of two key components: a label generator and a discriminator which are optimized alternatively through adversarial learning. To alleviate the issues of overfitting and highly imbalanced distribution, we design two novel modules for diversity and propagation, which can greatly improve the model generalization power. We have conducted extensive experiments to empirically verify the labeling and learning efficiency of ErGAN. The experimental results show that ErGAN beats the state-of-the-art baselines, including unsupervised, semi-supervised, and unsupervised learning methods.

Privacy-preserving record linkage (PPRL) is increasingly demanded in real-world applications, e.g., in the health-care domain, to combine person-related data for data analysis while preserving the privacy of individuals. However, the adoption of PPRL is hampered by the absence of easy-to-use and powerful PPRL tools covering the entire PPRL process. We therefore demonstrate Primat, a flexible and scalable tool that enables the definition and application of tailored PPRL workflows as well as the comparative evaluation of different PPRL methods. We introduce the main requirements for PPRL tools and discuss previous tool efforts that do not fully meet the requirements and have not been applied in practice. By contrast, Primat covers the whole PPRL life-cycle and improves applicability by providing various components for data owners and the central linkage to be executed by a trusted linkage unit.

We demonstrate G radoop , an open source framework that combines and extends features of graph database systems with the benefits of distributed graph processing. Using a rich graph data model and powerful graph operators, users can declaratively express graph analytical programs for distributed execution without needing advanced programming experience or a deeper understanding of the underlying system. Visitors of the demo can declare graph analytical programs using the G radoop operators and also visually experience two of our advanced operators: graph pattern matching and graph grouping. We provide real world and artificial social network data with up to 10 billion edges and allow running the programs either locally or on a remote research cluster to demonstrate scalability.

Transactional frequent subgraph mining identifies frequent structural patterns in a collection of graphs. This research problem has wide applicability and increasingly requires higher scalability over single machine solutions to address the needs of Big Data use cases. We introduce DIMSpan, an advanced approach to frequent subgraph mining that utilizes the features provided by distributed in-memory dataflow systems such as Apache Flink or Apache Spark. It determines the complete set of frequent subgraphs from arbitrary string-labeled directed multigraphs as they occur in social, business and knowledge networks. DIMSpan is optimized to runtime and minimal network traffic but memory-aware. An extensive performance evaluation on large graph collections shows the scalability of DIMSpan and the effectiveness of its optimization techniques.

The temporal linkage of census data allows the detailed analysis of population-related changes in an area of interest. It should not only link records about the same person but also support the linkage of groups of related persons such as households. In this paper, we thus propose a new approach to both temporal record and group (household) linkage for census data and study its application for change analysis. The approach utilizes the relationships between individuals to determine the similarity of groups and their members within a graph-based method. The approach is also iterative by first identifying high quality matches that are subsequently extended by matches found with less restrictive similarity criteria. A comprehensive evaluation using historical census data from the UK indicates a high effectiveness of the proposed approach. Furthermore, the linkage enables an insightful analysis of household changes determined by so-called evolution patterns.

Entity resolution (ER) is a common data cleaning task that involves determining which records from one or more data sets refer to the same real-world entities. Because a pairwise comparison of all records scales quadratically with the number of records in the data sets to be matched, it is common to use blocking or indexing techniques to reduce the number of comparisons required. These techniques split the data sets into blocks and only records within blocks are compared with each other. Most existing blocking techniques do not provide control over the size of the generated blocks, despite this control being important in many practical applications of ER, such as privacy-preserving record linkage and real-time ER. We propose two novel hierarchical clustering approaches which can generate blocks within a specified size range, and we present a penalty function which allows control of the trade-off between block quality and block size in the clustering process. We evaluate our techniques on three real-world data sets and compare them against three baseline approaches. The results show our proposed techniques perform well on the measures of pairs completeness and reduction ratio compared to the baseline approaches, while also satisfying the block size restrictions.

OBJECTIVE: To address the problem of mapping local laboratory terminologies to Logical Observation Identifiers Names and Codes (LOINC). To study different ontology matching algorithms and investigate how the probability of term combinations in LOINC helps to increase match quality and reduce manual effort. MATERIALS AND METHODS: We proposed two matching strategies: full name and multi-part. The multi-part approach also considers the occurrence probability of combined concept parts. It can further recommend possible combinations of concept parts to allow more local terms to be mapped. Three real-world laboratory databases from Taiwanese hospitals were used to validate the proposed strategies with respect to different quality measures and execution run time. A comparison with the commonly used tool, Regenstrief LOINC Mapping Assistant (RELMA) Lab Auto Mapper (LAM), was also carried out. RESULTS: The new multi-part strategy yields the best match quality, with F-measure values between 89% and 96%. It can automatically match 70-85% of the laboratory terminologies to LOINC. The recommendation step can further propose mapping to (proposed) LOINC concepts for 9-20% of the local terminology concepts. On average, 91% of the local terminology concepts can be correctly mapped to existing or newly proposed LOINC concepts. CONCLUSIONS: The mapping quality of the multi-part strategy is significantly better than that of LAM. It enables domain experts to perform LOINC matching with little manual work. The probability of term combinations proved to be a valuable strategy for increasing the quality of match results, providing recommendations for proposed LOINC conepts, and decreasing the run time for match processing.

We demonstrate BIIIG (Business Intelligence with Integrated Instance Graphs), a new system for graph-based data integration and analysis. It aims at improving business analytics compared to traditional OLAP approaches by comprehensively tracking relationships between entities and making them available for analysis. BIIIG supports a largely automatic data integration pipeline for metadata and instance data. Metadata from heterogeneous sources are integrated in a so-called Unified Metadata Graph (UMG) while instance data is combined in a single integrated instance graph (IIG). A unique feature of BIIIG is the concept of business transaction graphs, which are derived from the IIG and which reflect all steps involved in a specific business process. Queries and analysis tasks can refer to the entire instance graph or sets of business transaction graphs. In the demonstration, we perform all data integration steps and present analytic queries including pattern matching and graph-based aggregation of business measures.

Product matching is a challenging variation of entity resolution to identify representations and offers referring to the same product. Product matching is highly difficult due to the broad spectrum of products, many similar but different products, frequently missing or wrong values, and the textual nature of product titles and descriptions. We propose the use of tailored approaches for product matching based on a preprocessing of product offers to extract and clean new attributes usable for matching. In particular, we propose a new approach to extract and use so-called product codes to identify products and distinguish them from similar product variations. We evaluate the effectiveness of the proposed approaches with challenging real-life datasets with product offers from online shops. We also show that the UPC information in product offers is often error-prone and can lead to insufficient match decisions.

Programmatic data integration approaches such as mashups have become a viable approach to dynamically integrate web data at runtime. Key data sources for mashups include entity search engines and hidden databases that need to be queried via source-specific search interfaces or web forms. Current mashups are typically restricted to simple query approaches such as using keyword search. Such approaches may need a high number of queries if many objects have to be found. Furthermore, the effectiveness of the queries may be limited, i.e., they may miss relevant results. We therefore propose more advanced search strategies that aim at finding a set of entities with high efficiency and high effectiveness. Our strategies use different kinds of queries that are determined by source-specific query generators. Furthermore, the queries are selected based on the characteristics of input entities. We introduce a flexible model for entity search strategies that includes a ranking of candidate queries determined by different query generators. We describe different query generators and outline their use within four entity search strategies. These strategies apply different query ranking and selection approaches to optimize efficiency and effectiveness. We evaluate our search strategies in detail for two domains: product search and publication search. The comparison with a standard keyword search shows that the proposed search strategies provide significant improvements in both domains.

The effectiveness and scalability of MapReduce-based implementations of complex data-intensive tasks depend on an even redistribution of data between map and reduce tasks. In the presence of skewed data, sophisticated redistribution approaches thus become necessary to achieve load balancing among all reduce tasks to be executed in parallel. For the complex problem of entity resolution, we propose and evaluate two approaches for such skew handling and load balancing. The approaches support blocking techniques to reduce the search space of entity resolution, utilize a preprocessing MapReduce job to analyze the data distribution, and distribute the entities of large blocks among multiple reduce tasks. The evaluation on a real cloud infrastructure shows the value and effectiveness of the proposed load balancing approaches.

Mapping complex metadata structures is crucial in a number of domains such as data integration, ontology alignment or model management. To speed up the generation of such mappings, automatic matching systems were developed to compute mapping suggestions that can be corrected by a user. However, constructing and tuning match strategies still requires a high manual effort by matching experts as well as correct mappings to evaluate generated mappings. We therefore propose a self-configuring schema matching system that is able to automatically adapt to the given mapping problem at hand. Our approach is based on analyzing the input schemas as well as intermediate matching results. A variety of matching rules use the analysis results to automatically construct and adapt an underlying matching process for a given match task. We comprehensively evaluate our approach on different mapping problems from the schema, ontology and model management domains. The evaluation shows that our system is able to robustly return good quality mappings across different mapping problems and domains.

MOTIVATION: Ontologies are used in the annotation and analysis of biological data. As knowledge accumulates, ontologies and annotation undergo constant modifications to reflect this new knowledge. These modifications may influence the results of statistical applications such as functional enrichment analyses that describe experimental data in terms of ontological groupings. Here, we investigate to what degree modifications of the Gene Ontology (GO) impact these statistical analyses for both experimental and simulated data. The analysis is based on new measures for the stability of result sets and considers different ontology and annotation changes. RESULTS: Our results show that past changes in the GO are non-uniformly distributed over different branches of the ontology. Considering the semantic relatedness of significant categories in analysis results allows a more realistic stability assessment for functional enrichment studies. We observe that the results of term-enrichment analyses tend to be surprisingly stable despite changes in ontology and annotation.

Abstract Summary: Life science ontologies substantially change over time to meet the requirements of their users and to include the newest domain knowledge. Thus, an important task is to know what has been modified between two versions of an ontology (diff). This diff should contain all performed changes as compact and understandable as possible. We present CODEX (Complex Ontology Diff Explorer), a tool that allows determining semantic changes between two versions of an ontology, which users can interactively analyze in multiple ways. Availability and implementation: CODEX is available under http://www.izbi.de/codex and is supported by all major browsers. It is implemented in Java based on Google Web Toolkit technology. Additionally, users can access a web service interface to use the diff functionality in their applications and analyses. Contact: [email protected]

We demonstrate a new powerful mashup tool called WETSUIT (Web EnTity Search and fUsIon Tool) to search and integrate web data from diverse sources and domain-specific entity search engines. WETSUIT supports adaptive search strategies to query sets of relevant entities with a minimum of communication overhead. Mashups can be composed using a set of high-level operators based on the Java-compatible language Scala. The operator implementation supports a high degree of parallel processing, in particular a streaming of entities between all data transformation operations facilitating a fast presentation of intermediate results. WETSUIT has already been applied to solve challenging integration tasks from different domains.

We demonstrate a powerful and easy-to-use tool called Dedoop (Deduplication with Hadoop) for MapReduce-based entity resolution (ER) of large datasets. Dedoop supports a browser-based specification of complex ER workflows including blocking and matching steps as well as the optional use of machine learning for the automatic generation of match classifiers. Specified workflows are automatically translated into MapReduce jobs for parallel execution on different Hadoop clusters. To achieve high performance Dedoop supports several advanced load balancing strategies.

Researchers maintain bibliographies and extensive sets of PDF files of scholarly publications on their desktop. The lack of proper metadata of downloaded PDFs makes this task a tedious one. With PDFMeat we present a solution to automatically determine publication metadata for scholarly papers within the user's desktop environment and link the metadata to the files. PDFMeat effectively matches local full texts to an online repository. In an evaluation for more than 2.000 diverse PDF files it worked highly reliable and showed excellent accuracy of up to 98 percent. We demonstrate PDFMeat for different sets of papers, highlighting the semantic integration and use of the retrieved metadata within the file browser of the desktop environment.

The effectiveness and scalability of MapReduce-based implementations of complex data-intensive tasks depend on an even redistribution of data between map and reduce tasks. In the presence of skewed data, sophisticated redistribution approaches thus become necessary to achieve load balancing among all reduce tasks to be executed in parallel. For the complex problem of entity resolution with blocking, we propose BlockSplit, a load balancing approach that supports blocking techniques to reduce the search space of entity resolution. The evaluation on a real cloud infrastructure shows the value and effectiveness of the proposed approach.

Semi-automatic schema matching systems have been developed to compute mapping suggestions that can be corrected by a user. However, constructing and tuning match strategies still requires a high manual effort. We therefore propose a self-configuring schema matching system that is able to automatically adapt to the given mapping problem at hand. Our approach is based on analyzing the input schemas as well as intermediate match results. A variety of matching rules use the analysis results to automatically construct and adapt an underlying matching process for a given match task. The evaluation shows that our system is able to robustly return good quality mappings across different mapping problems and domains.

We present the Auto Mapping Core (AMC), a new framework that supports fast construction and tuning of schema matching approaches for specific domains such as ontology alignment, model matching or database-schema matching. Distinctive features of our framework are new visualisation techniques for modelling matching processes, stepwise tuning of parameters, intermediate result analysis and performance-oriented rewrites. Furthermore, existing matchers can be plugged into the framework to comparatively evaluate them in a common environment. This allows deeper analysis of behaviour and shortcomings in existing complex matching systems.

The proliferation of ontologies and taxonomies in many domains increasingly demands the integration of multiple such ontologies to provide a unified view on them. We demonstrate a new automatic approach to merge large taxonomies such as product catalogs or web directories. Our approach is based on an equivalence matching between a source and target taxonomy to merge them. It is target-driven, i.e. it preserves the structure of the target taxonomy as much as possible. Further, we show how the approach can utilize additional relationships between source and target concepts to semantically improve the merge result.

A recurring manual task in data integration, ontology alignment or model management is finding mappings between complex meta data structures. In order to reduce the manual effort, many matching algorithms for semi-automatically computing mappings were introduced. Unfortunately, current matching systems severely lack performance when matching large schemas. Recently, some systems tried to tackle the performance problem within individual matching approaches. However, none of them developed solutions on the level of matching processes. In this paper we introduce a novel rewrite-based optimization technique that is generally applicable to different types of matching processes. We introduce filter-based rewrite rules similar to predicate push-down in query optimization. In addition we introduce a modeling tool and recommendation system for rewriting matching processes. Our evaluation on matching large web service message types shows significant performance improvements without losing the quality of automatically computed results.

Despite the huge amount of recent research efforts on entity resolution (matching) there has not yet been a comparative evaluation on the relative effectiveness and efficiency of alternate approaches. We therefore present such an evaluation of existing implementations on challenging real-world match tasks. We consider approaches both with and without using machine learning to find suitable parameterization and combination of similarity functions. In addition to approaches from the research community we also consider a state-of-the-art commercial entity resolution implementation. Our results indicate significant quality and efficiency differences between different approaches. We also find that some challenging resolution tasks such as matching product entities from online shops are not sufficiently solved with conventional approaches based on the similarity of attribute values.

BACKGROUND: Numerous ontologies have recently been developed in life sciences to support a consistent annotation of biological objects, such as genes or proteins. These ontologies underlie continuous changes which can impact existing annotations. Therefore, it is valuable for users of ontologies to study the stability of ontologies and to see how many and what kind of ontology changes occurred. RESULTS: We present OnEX (Ontology Evolution EXplorer) a system for exploring ontology changes. Currently, OnEX provides access to about 560 versions of 16 well-known life science ontologies. The system is based on a three-tier architecture including an ontology version repository, a middleware component and the OnEX web application. Interactive workflows allow a systematic and explorative change analysis of ontologies and their concepts as well as the semi-automatic migration of out-dated annotations to the current version of an ontology. CONCLUSION: OnEX provides a user-friendly web interface to explore information about changes in current life science ontologies. It is available at http://www.izbi.de/onex.

We present FEVER, a new evaluation platform for entity resolution approaches. The modular structure of the FEVER framework supports the incorporation or reconstruction of many previously proposed approaches for entity resolution. A distinctive feature of FEVER is that it not only evaluates traditional measures such as precision and recall but also the effort for configuring (e.g., parameter tuning, training) a good entity resolution approach. FEVER thus strives for a fair comparative evaluation of different approaches by considering both the effectiveness and configuration effort.

A common task in many database applications is the migration of legacy data from multiple sources into a new one. This requires identifying semantically related elements of the source and target systems and the creation of mapping expressions to transform instances of those elements from the source format to the target format. Currently, data migration is typically done manually, a tedious and timeconsuming process, which is difficult to scale to a high number of data sources. In this paper, we describe QuickMig, a new semi-automatic approach to determining semantic correspondences between schema elements for data migration applications. QuickMig advances the state of the art with a set of new techniques exploiting sample instances, domain ontologies, and reuse of existing mappings to detect not only element correspondences but also their mapping expressions. QuickMig further includes new mechanisms to effectively incorporate domain knowledge of users into the matching process. The results from a comprehensive evaluation using real-world schemas and data indicate the high quality and practicability of the overall approach.

BACKGROUND: Genome-wide expression, sequence and association studies typically yield large sets of gene candidates, which must then be further analysed and interpreted. Information about these genes is increasingly being captured and organized in ontologies, such as the Gene Ontology. Relationships between the gene sets identified by experimental methods and biological knowledge can be made explicit and used in the interpretation of results. However, it is often difficult to assess the statistical significance of such analyses since many inter-dependent categories are tested simultaneously. RESULTS: We developed the program package FUNC that includes and expands on currently available methods to identify significant associations between gene sets and ontological annotations. Implemented are several tests in particular well suited for genome wide sequence comparisons, estimates of the family-wise error rate, the false discovery rate, a sensitive estimator of the global significance of the results and an algorithm to reduce the complexity of the results. CONCLUSION: FUNC is a versatile and useful tool for the analysis of genome-wide data. It is freely available under the GPL license and also accessible via a web service.

We demonstrate the schema and ontology matching tool COMA++. It extends our previous prototype COMA utilizing a composite approach to combine different match algorithms [3]. COMA++ implements significant improvements and offers a comprehensive infrastructure to solve large real-world match problems. It comes with a graphical interface enabling a variety of user interactions. Using a generic data representation, COMA++ uniformly supports schemas and ontologies, e.g. the powerful standard languages W3C XML Schema and OWL. COMA++ includes new approaches for ontology matching, in particular the utilization of shared taxonomies. Furthermore, different match strategies can be applied including various forms of reusing previously determined match results and a so-called fragment-based match approach which decomposes a large match problem into smaller problems. Finally, COMA++ cannot only be used to solve match problems but also to comparatively evaluate the effectiveness of different match algorithms and strategies.

Model management is an approach to simplify the programming of metadata-intensive applications. It offers developers powerful operators, such as Compose, Diff, and Merge, that are applied to models, such as database schemas or interface specifications, and to mappings between models. Prior model management solutions focused on a simple class of mappings that do not have executable semantics. Yet many metadata applications require that mappings be executable, expressed in SQL, XSLT, or other data transformation languages.In this paper, we develop a semantics for model-management operators that allows applying the operators to executable mappings. Our semantics captures previously-proposed desiderata and is language-independent: the effect of the operators is expressed in terms of what they do to the instances of models and mappings. We describe an implemented prototype in which mappings are represented as dependencies between relational schemas, and discuss algebraic optimization of model-management scripts.

Model management aims at reducing the amount of programming needed for the development of metadata-intensive applications. We present a first complete prototype of a generic model management system, in which high-level operators are used to manipulate models and mappings between models. We define the key conceptual structures: models, morphisms, and selectors, and describe their use and implementation. We specify the semantics of the known model-management operators applied to these structures, suggest new ones, and develop new algorithms for implementing the individual operators. We examine the solutions for two model-management tasks that involve manipulations of relational schemas, XML schemas, and SQL views.

Abstract Parallel processing is a key to high performance in very large data warehouse applications that execute complex analytical queries on huge amounts of data. Although parallel database systems (PDBSs) have been studied extensively in the past decades, the specifics of load balancing in parallel data warehouses have not been addressed in detail. In this study, we investigate how the load balancing potential of a Shared Disk (SD) architecture can be utilized for data warehouse applications. We propose an integrated scheduling strategy that simultaneously considers both processors and disks, regarding not only the total workload on each resource but also the distribution of load over time. We evaluate the performance of the new method in a comprehensive simulation study and compare it to several other approaches. The analysis incorporates skew aspects and considers typical data warehouse features such as star schemas with large fact tables and bitmap indices. Copyright © 2003 John Wiley & Sons, Ltd.

Matching elements of two data schemas or two data instances plays a key role in data warehousing, e-business, or even biochemical applications. In this paper we present a matching algorithm based on a fixpoint computation that is usable across different scenarios. The algorithm takes two graphs (schemas, catalogs, or other data structures) as input, and produces as output a mapping between corresponding nodes of the graphs. Depending on the matching goal, a subset of the mapping is chosen using filters. After our algorithm runs, we expect a human to check and if necessary adjust the results. As a matter of fact, we evaluate the 'accuracy' of the algorithm by counting the number of needed adjustments. We conducted a user study, in which our accuracy metric was used to estimate the labor savings that the users could obtain by utilizing our algorithm to obtain an initial matching. Finally, we illustrate how our matching algorithm is deployed as one of several high-level operators in an implemented testbed for managing information models and mappings.

TID hash joins are a simple and memory-efficient method for processing large join queries.They are based on standard hash join algorithms but only store TID/key pairs in the hash table instead of entire ttrples.This typically reduces memory requirements by more than art order of magnitude bringing substantial benefits.In particular, performance for joins on Gigs-Byte relations can substantially be improved by reducing the amount of disk f/O to a large extent.Furthermore, efficient processing of mixed multi-user workloads consisting of both join queries and OLTP transactions is supported.We present a detailed simulation study to analyze the performance of TID hash joins.In particular, we identify the conditions under which TID hash joins are most beneficial.Furthermore, we compare TID hash join with adaptive hash join algorithms that have been proposed to deal with mixed workloads.

Closely coupled systems aim at a more efficient communication and cooperation between processing nodes compared to loosely coupled systems. This can be achieved by using globally shared semiconductor memory to speed up the exchange of messages or to store global data structures. For distributed database processing, the database sharing (shared disk) architecture can benefit most from such a close coupling. The author presents a detailed simulation study of closely coupled database sharing systems. A shared store called global extended memory (GEM) was used for system-wide concurrency and coherency control, and to improve input/output (I/O) performance. The performance of such an architecture is evaluated and compared with loosely coupled database sharing systems employing the primary copy approach for concurrency and coherency control. In particular, the impact of different update strategies (FORCE vs. NOFORCE) and workload allocation schemes (random vs. affinity-based routing) is studied. The use of shared disk caches implementing a global database buffer is also considered. Simulation results are presented for synthetically generated debit-credit workloads and a real-life workload represented by a database trace.>

Database Sharing (DB-sharing) refers to a general approach for building a distributed high performance transaction system. The nodes of a DB-sharing system are locally coupled via a high-speed interconnect and share a common database at the disk level. This is also known as a “shared disk” approach. We compare database sharing with the database partitioning (shared nothing) approach and discuss the functional DBMS components that require new and coordinated solutions for DB-sharing. The performance of DB-sharing systems critically depends on the protocols used for concurrency and coherency control. The frequency of communication required for these functions has to be kept as low as possible in order to achieve high transation rates and short response times. A trace-driven simulation system for DB-sharing complexes has been developed that allows a realistic performance comparison of four different concurrency and coherency control protocols. We consider two locking and two optimistic schemes which operate either under central or distributed control. For coherency control, we investigate so-called on-request and broadcast invalidation schemes, and employ buffer-to-buffer communication to exchange modified pages directly between different nodes. The performance impact of random routing versus affinity-based load distribution and different communication costs is also examined. In addition, we analyze potential performance bottlenecks created by hot spot pages.

No abstract available.

The use of non-volatile semiconductor memory within an extended storage hierarchy promises significant performance improvements for transaction processing. Although page-addressable semiconductor memories like extended memory, solid-state disks and disk caches are commercially available since several years, no detailed investigation of their use for transaction processing has been performed so far. We present a comprehensive simulation study that compares the performance of these storage types and of different usage forms. The following usage forms are considered: allocation of entire log and database files in non-volatile semiconductor memory, using a so-called write buffer to perform disk writes asynchronously, and caching of database pages at intermediate storage levels (in addition to main memory caching). Simulation results will be presented for the debit-credit workload frequently used in transaction processing benchmarks.

A distributed optimistic concurrency control (OCC) method followed by locking, such that locking is an integral part of distributed validation and two-phase commit is presented. This OCC method ensures that a transaction failing its validation will not be reexecuted more than once, in general. Furthermore, deadlocks, which are difficult to handle in a distributed environment, are avoided by serializing lock requests. Implementation details are outlined, and the performance of the schemes is compared with distributed two-phase locking (2PL) through a detailed simulation, which incorporates queueing effects at the devices of the computer systems, buffer management, concurrency control, and commit processing. It is shown that in the case of higher data contention levels, the hybrid OCC method allows a much higher maximum transaction throughput than distributed 2PL. The performance of the method with respect to variable-size transactions is reported. It is shown that by restricting the number of restarts to one, the performance achieved for variable-size transactions is comparable to fixed-size transactions with the same mean size.>