In recent years, entity matching methods based on graph neural networks have significantly improved the ability of entity structure representation through multilayer neighborhood aggregation. However, such methods still suffer from oversmoothing and noise diffusion in local structures, as well as insufficient global topological consistency and limited geometric expression. Existing methods usually rely on local aggregation to obtain structural representations, making it difficult to explicitly model the global topological patterns and hierarchical structures between entities. Especially in heterogeneous or cross‐lingual graphs, traditional Euclidean embedding spaces cannot fully represent complex semantic hierarchies and multiscale geometric relationships. To this end, this paper proposes a Triview Dual‐space Contrastive Perception Matching (TriDCPM) method, which unifies the modeling of local correlations, global topologies, and cross‐graph consistency under a multiview representation and geometric collaborative learning framework. Specifically, TriDCPM constructs a triview framework consisting of local, global, and cross‐graph views and simultaneously learns multiscale entity representations in both Euclidean and hyperbolic geometric spaces. A global structure enhancement module based on singular value decomposition (SVD) is adopted to extract key topological patterns, and a gated residual unit (GRU) is introduced to alleviate noise propagation and oversmoothing. In the local encoding stage, multilayer attention aggregation and a degree‐aware relation fusion mechanism are employed to further enhance heterogeneous neighborhood and relational semantic features. Finally, a dual‐level contrastive consistency learning mechanism is adopted to jointly optimize feature consistency between the local–global levels and the Euclidean–hyperbolic spaces, achieving collaborative perception and discriminative unification of multiview representations. Experimental results on four public benchmark datasets demonstrate that the proposed method significantly outperforms existing structure‐driven entity alignment approaches in terms of Hit@1, MRR, and other metrics, with particularly outstanding performance in relation‐heterogeneous and cross‐lingual scenarios. Further ablation experiments and visualization analysis verify the effectiveness and stability of the proposed method in global structure modeling, noise suppression, and multispace contrastive optimization.

Multiplayer Online Battle Arena (MOBA) games, one of the most popular esports genres, have been extensively studied in the fields of game AI and game analytics. Open-source large language models (LLMs), such as Llama, have become essential tools in artificial intelligence (AI) research. However, previous battlefield information prediction studies have largely assumed that all in-game data are readily accessible, using sequential models to analyze samples containing numerous data items collected over a period, which present challenges for users to collect and input. In this work, we introduce MobaQA, a MOBA battlefield information prediction model based on LLMs fine-tuning. Instead of utilizing extensive data inputs, MobaQA employs a minimal set of key data items to construct its dataset. By fine-tuning LLMs, MobaQA generates predictions based on input battlefield information text. Using samples collected from two major game versions over a span of two years, we design multiple Q&A templates and conduct extensive experiments on fine-tuned MobaQA models derived from three different base LLMs, under varying training volumes and with various levels of missing data. Experimental results indicate MobaQA can effectively predict real-time winrate and match outcome.

Explainable recommendation has attracted great attention due to its capability of enhancing user trust and satisfaction. Users’ curiosities highly affect the recommendation accuracy and the effectiveness of explanations. Different target users have different levels of curiosities, while the curiosity of the same user changes dynamically. However, existing techniques cannot capture users’ dynamic curiosities from the historical user-item interactions for effective explainable recommendation. In this article, we propose a novel explainable recommendation approach for effective D ynamic C uriosity-aware E xplainable R ecommendation (DCER). Specifically, we first propose a novel multi-view representation learning to model the temporal user-item interactions. Then, we propose a new curiosity-enhanced recommendation to dynamically capture users’ curiosities, which improves the recommendation quality in a mutual promotion manner. Finally, we propose an adaptive rule-guided hybrid explanation generation strategy that enables more personalized explanations and well reflects the users’ dynamic psychological states behind the transactions. The experimental results demonstrate the high effectiveness of our proposed model.

With the rapid growth of multi-source and heterogeneous health data, achieving efficient and trustworthy crosschain sharing while ensuring privacy and security has become a critical challenge in blockchain-based healthcare applications. To address this, this paper proposes a secure health data sharing method based on a cross-chain blockchain architecture. A fourlayer system framework is constructed, and two original core modules, D-FBAC and HAEPP, are designed. The D-FBAC module introduces a reputation-weighted attribute mechanism to achieve resilient and fine-grained access control. The HAEPP module combines hybrid encryption strategies with a key lifecycle management mechanism to enhance privacy protection during both on-chain and cross-chain data flows. To improve system interpretability and user trust, an off-chain explainable access rejection module is also integrated, enabling rule-level traceability and feedback for access denials. The experimental evaluation is conducted on real-world healthcare datasets using a comprehensive set of metrics, results show that the proposed system significantly outperforms existing approaches across multiple performance dimensions, offering valuable insights for the interoperability and trusted governance of healthcare information systems.

Fairness-aware recommendation has emerged as a pivotal research area in recent years. Current fairness studies primarily examine two independent dimensions: user-side fairness and item-side fairness. However, most approaches address each side's fairness in isolation while neglecting their complex interdependencies. In this paper, we propose an LLM-Enhanced DiscriminAtive Counterfactual Debiasing Model for Two-sided Fairness in Recommendation (LeadFairRec). Specifically, we first design a two-sided causal graph that jointly models provider-customer fairness interactions through their causal relationships. Then we propose a discriminative counterfactual debiasing method, which effectively removes spurious correlations while maintaining true user-item interactions. Finally, we propose an LLM-enhanced counterfactual inference method to derive noise-resistant user/item representations from interaction data, enhancing the robustness of causal debiasing. The experimental results demonstrate the high effectiveness of our proposed model. We provide our code at https://github.com/houyimin660/LeadFairRec.

A good group recommender system should be capable of modeling how a consensus among group members is reached. However, existing works fail to adequately capture the dynamic consensus that underlies group members’ behavioral sequences for effective sequential group recommendation. In this paper, we propose a multi-modal Contrastive Fusion framework to learn dynamic consensus for Sequential Group Recommendation (CF-SGR). Specifically, we utilize user-item interactions, group-item interactions, and side information to encode both collaborative and semantic signals, further learning the group consensus in these different modalities. Subsequently, we employ a multi-modal contrastive fusion strategy to effectively integrate the latent embeddings of these modalities. We also propose a strategy for generating explanations, which integrates LLMs with CPT (Continuous Prompt Tuning). Our method outperforms state-of-the-art group recommendation methods on two real-world datasets.

Deep entity resolution (ER) identifies matching entities across data sources using techniques based on deep learning. It involves two steps: a blocker for identifying the potential matches to generate the candidate pairs, and a matcher for accurately distinguishing the matches and non-matches among these candidate pairs. Recent deep ER approaches utilize pretrained language models (PLMs) to extract similarity features for blocking and matching, achieving state-of-the-art performance. However, they often fail to balance the consensus and discrepancy between the blocker and matcher, emphasizing the consensus while neglecting the discrepancy. This paper proposes MutualER, a deep entity resolution framework that integrates and jointly trains the blocker and matcher, balancing both the consensus and discrepancy between them. Specifically, we firstly introduce a lightweight PLM in siamese structure for the blocker and a heavier PLM in cross structure or an autoregressive large language model (LLM) for the matcher. Two optimization techniques named Mutual Sample Selection (MSS) and Similarity Knowledge Transferring (SKT) are designed to jointly train the blocker and matcher. MSS enables the blocker and matcher to mutually select the customized training samples for each other to maintain the discrepancy, while SKT allows them to share the similarity knowledge for improving their blocking and matching capabilities respectively to maintain the consensus. Extensive experiments on five datasets demonstrate that MutualER significantly outperforms existing PLM-based and LLM-based approaches, achieving leading performance in both effectiveness and efficiency.

High-quality data is essential for data science and machine learning applications, but unfortunately, real-world data often contains significant amounts of errors, such as typos, missing values, and data inconsistencies. Despite all the efforts in cleaning data using either logical or learning-based methods, in practice, data cleaning still requires high human cost, for either manually providing data repairing rules or preparing labeled datasets for training machine learning models. In this paper, we introduce GARF, a novel data cleaning system based on sequence generative adversarial networks (SeqGAN). One key information GARF tries to learn is data repair rules. To automatically extracts data repair rules from dirty data, GARF employs a SeqGAN to capture the dependency relationships, and converts the information learned by machine to interpretable data repair rules for humans. Additionally, considering that both generated rules and data may not be fully trusted, GARF provides a co-cleaning process to iteratively update inaccurate rules and repair dirty data until there is no tuple violating rules. We have implemented and deployed GARF as an open-sourced system, and demonstrated its usability on data cleaning in real-world scenarios.

Entity resolution (ER) is a key task in data integration and data science applications. The state-of-the-art approaches in ER have been achieved through designing various deep learning-based methods. However, these methods typically require a large amount of high-quality labeled resources, which are difficult to obtain in the real world. In this paper, we propose a novel ER framework called LRER, which efficiently maintains the low-resource settings while using hybrid information from different perspectives of entities. In the first stage of LRER, we construct a self-supervised contrastive pre-training module, which contains reasonable contrastive instances and a novel training objective to pre-train the representation model without using any labeled data. In the second stage of LRER, we propose a hybrid information fine-tuning module, which contains a structure-aware processing for relational entities to capture the structural information and fine-tune the model with hybrid information. Experimental results on real-world datasets show that LRER outperforms the existing methods under low-resource settings.

Entity matching (EM) determines whether two records from different data sources refer to the same real-world entity. It is a fundamental task in knowledge graph construction and data integration. Currently, deep learning (DL) based EM methods have achieved state-of-the-art (SOTA) results. However, apply-ing DL-based EM methods often costs a lot of human efforts to label the data. To address this challenge, we propose a new do-main adaptation (DA) framework for EM called Matching Fea-ture Separation Network (MFSN). We implement DA by sepa-rating private and common matching features. Briefly, MFSN first uses three encoders to explicitly model the private and common matching features in both the source and target do-mains. Then, it transfers the knowledge learned from the source common matching features to the target domain. We also pro-pose an enhanced variant called Feature Representation and Separation Enhanced MFSN (MFSN-FRSE). Compared with MFSN, it has superior feature representation and separation capabilities. We evaluate the effectiveness of MFSN and MFSN-FRSE on twelve DA in EM tasks. The results show that our framework is approximately 7% higher in F1 score on average than the previous SOTA methods. Then, we verify the effec-tiveness of each module in MFSN and MFSN-FRSE by ablation study. Finally, we explore the optimal strategy of each module in MFSN and MFSN-FRSE through detailed tests.

Abstract An accurate short-term load forecasting plays an important role in modern power system’s operation and economic development. However, short-term load forecasting is affected by multiple factors, and due to the complexity of the relationships between factors, the graph structure in this task is unknown. On the other hand, existing methods do not fully aggregating data information through the inherent relationships between various factors. In this paper, we propose a short-term load forecasting framework based on graph neural networks and dilated 1D-CNN, called GLFN-TC. GLFN-TC uses the graph learning module to automatically learn the relationships between variables to solve problem with unknown graph structure. GLFN-TC effectively handles temporal and spatial dependencies through two modules. In temporal convolution module, GLFN-TC uses dilated 1D-CNN to extract temporal dependencies from historical data of each node. In densely connected residual convolution module, in order to ensure that data information is not lost, GLFN-TC uses the graph convolution of densely connected residual to make full use of the data information of each graph convolution layer. Finally, the predicted values are obtained through the load forecasting module. We conducted five studies to verify the outperformance of GLFN-TC. In short-term load forecasting, using MSE as an example, the experimental results of GLFN-TC decreased by 0.0396, 0.0137, 0.0358, 0.0213 and 0.0337 compared to the optimal baseline method on ISO-NE, AT, AP, SH and NCENT datasets, respectively. Results show that GLFN-TC can achieve higher prediction accuracy than the existing common methods.

Data imbalance is a common phenomenon in machine learning. In the imbalanced data classification, minority samples are far less than majority samples, which makes it difficult for minority to be effectively learned by classifiers. A synthetic minority oversampling technique (SMOTE) improves the sensitivity of classifiers to minority by synthesizing minority samples without repetition. However, the process of synthesizing new samples in the SMOTE algorithm may lead to problems such as "noisy samples" and "boundary samples." Based on the above description, we propose a synthetic minority oversampling technique based on Gaussian mixture model filtering (GMF-SMOTE). GMF-SMOTE uses the expected maximum algorithm based on the Gaussian mixture model to group the imbalanced data. Then, the expected maximum filtering algorithm is used to filter out the "noisy samples" and "boundary samples" in the subclasses after grouping. Finally, to synthesize majority and minority samples, we design two dynamic oversampling ratios. Experimental results show that the GMF-SMOTE performs better than the traditional oversampling algorithms on 20 UCI datasets. The population averages of sensitivity and specificity indexes of random forest (RF) on the UCI datasets synthesized by GMF-SMOTE are 97.49% and 97.02%, respectively. In addition, we also record the G-mean and MCC indexes of the RF, which are 97.32% and 94.80%, respectively, significantly better than the traditional oversampling algorithms. More importantly, the two statistical tests show that GMF-SMOTE is significantly better than the traditional oversampling algorithms.

Deep Entity Matching (EM) is one of the core research topics in data integration. Typical existing works construct EM models by training deep neural networks (DNNs) based on the training samples with onehot labels. However, these sharp supervision signals of onehot labels harm the generalization of EM models, causing them to overfit the training samples and perform badly in unseen datasets. To solve this problem, we first propose that the challenge of training a well-generalized EM model lies in achieving the compromise between fitting the training samples and imposing regularization, i.e., the bias-variance tradeoff. Then, we propose a novel Soft Target-EnhAnced Matching (Steam) framework, which exploits the automatically generated soft targets as label-wise regularizers to constrain the model training. Specifically, Steam regards the EM model trained in previous iteration as a virtual teacher and takes its softened output as the extra regularizer to train the EM model in the current iteration. As such, Steam effectively calibrates the obtained EM model, achieving the bias-variance tradeoff without any additional computational cost. We conduct extensive experiments over open datasets and the results show that our proposed Steam outperforms the state-of-the-art EM approaches in terms of effectiveness and label efficiency.

Entity matching (EM) is a core problem of data mining and data integration. Existing EM solutions achieve great successes by designing and training the deep learning model for the specific domain, e.g., watches and shoes. However, these methods require a high training cost (e.g., model engineering and data preprocessing) in realistic EM applications. In this paper, we develop a deep learning-based solution in the manner of the domain-generic pre-training that targets low training cost for EM through a novel combination of the domain alignment and domain antagonism. In domain alignment, we design a novel contrastive learning method that align the representation distribution of different domains. And in domain antagonism, we conduct the domain adversarial training to force the encoder to focus the domain-generic knowledge. These two optimizations ensure that the pre-trained EM model can capture the general matching knowledge and be fine-tuned into specific domains at a fairly low cost. Empirical evaluation demonstrates that this combination achieves state-of-the-art performance in both in-domain and out-of-domain settings.

Mobility data collected from location-based social networks are imperative for user movement behaviour analysis and marketing strategy customization. However, due to personal privacy and temporary failure of GPS devices, mobility data suffer from missing data issues. The missing mobility data hide beneficial information that can lead to distorted data analysis. To this end, we propose a multi-task generative adversarial network, termed as MDI-MG, to mitigate the negative impact of missing mobility data by imputing possible missing records. Specifically, in MDI-MG, we first introduce region-awareness modelling to fully capture sequential dependencies. Then, the generator is designed as a multi-task network, which unifies two highly pertinent tasks, including the primary task and the auxiliary missing POI region imputation task. The joint training on the two tasks enhances presentation capabilities and brings additional benefits. Besides, we adopt a discriminator to evaluate the generated sequences. The generator and the discriminator are optimized with a minimax two-player game. Experiments on two real-world datasets show that, MDI-MG achieves better performance in terms of both imputation accuracy and effectiveness, compared with state-of-the-art methods.

We study the problem of self-supervised and interpretable data cleaning, which automatically extracts interpretable data repair rules from dirty data. In this paper, we propose a novel framework, namely Garf, based on sequence generative adversarial networks (SeqGAN). One key information Garf tries to capture is data repair rules (for example, if the city is "Dothan", then the county should be "Houston"). Garf employs a SeqGAN consisting of a generator G and a discriminator D that trains G to learn the dependency relationships ( e.g. , given a city value "Dothan" as input, the county can be determined as "Houston"). After training, the generator G can be used to generate data repair rules, but may contain both trusted and untrusted rules, especially when learning from dirty data. To mitigate this problem, Garf further updates the learned relationships with another discriminator D' to iteratively improve the quality of both rules and data. Garf takes advantages of both logical and learning-based methods, which allow cleaning dirty data with high interpretability and have no requirements for prior knowledge and training data. Extensive experiments on real-world and synthetic datasets demonstrate the effectiveness of Garf. Garf achieves new state-of-the-art data cleaning result with high accuracy, through learning from dirty datasets without human supervision.

Finding a team that is both competent in performing the task and compatible in working together has been extensively studied. However, most methods for team formation tend to rely on a set of skills only. In order to solve this problem, we present an efficient team formation method based on Constrained Pattern Graph (called CPG). Unlike traditional methods, our method takes into account both structure constraints and communication constraints on team members, which can better meet the requirements of users. First, a CPG preprocessing method is proposed to normalize a CPG and represent it as a CoreCPG in order to establish the basis for efficient matching. Second, a Communication Cost Index (called CCI) is constructed to speed up the matching between a CPG and its corresponding social network. Third, a CCI-based node matching algorithm is proposed to minimize the total number of intermediate results. Moreover, a set of incremental maintenance strategies for the changes of social networks are proposed. We conduct experimental studies based on two real-world social networks. The experiments demonstrate the effectiveness and the efficiency of our proposed method in comparison with traditional methods.

Nowadays, people prefer to take part in multiple social networks to enjoy different kinds of services. Consequently, a significant task is to identify users across networks. Most state-of-the-art works on this issue exploit user local structure features (e.g., friend, follow and followed). In this paper, we first proposes the notion of user global view features, which represent the location of users in the network. Then, we present an iterative two-stage algorithm (GAUI) using Global view features with user Attribute features to solve User Identification. In GAUI, we iteratively update pairwise similarity and predict new matching users. Certainly, we present a community based core anchor link filter strategy to reduce the computation cost, and present a stable matching based mapping strategy to improve the accuracy. At last, the experiments conducted on two real-world aligned networks demonstrate that our method has better performance on precision and recall.

With the volume of data grows rapidly, the cost of detecting duplication entities has increased significantly in data cleaning. However, some real-time applications only need to identify as many duplicate entities as possible in a limited time, rather than all of them. The existing works adopt the sorting method to divide similar records into blocks, and arrange the processing order of blocks to detect duplicate entity progressively. However, this method only works well when the attributes of records are suitable for sorting. Therefore, this paper proposes a novel progressive de-duplicate method for records that can't be sorted by their attributes. The method distributes records into different blocks based on their features and generates a modified bloom filter index for each block. Then it uses the bloom filter to predict the probability of duplicate entities in this block, which determines the processing order of blocks to detect the duplicate entities more quickly. The comprehensive experiment shows that the number of duplicate detection by this algorithm in the finite time is far more efficient than other algorithms involved in the related works.

The process of matching and integrating records that relate to the same entity from one or more datasets is known as record linkage, and it has become an increasingly important subject in many application areas, including business, government and health system. The data from these areas often contain sensitive information. To prevent privacy breaches, ideally records should be linked in a private way such that no information other than the matching result is leaked in the process, and this technique is called privacy-preserving record linkage (PPRL). With the increasing data, scalability becomes the main challenge of PPRL, and many private blocking techniques have been developed for PPRL. They are aimed at reducing the number of record pairs to be compared in the matching process by removing obvious non-matching pairs without compromising privacy. However, most of them are designed for two databases and they vary widely in their ability to balance competing goals of accuracy, efficiency and security. In this paper, we propose a novel private blocking approach for PPRL based on dynamic k -anonymous blocking and Paillier cryptosystem which can be applied on two or multiple databases. In dynamic k -anonymous blocking, our approach dynamically generates blocks satisfying k -anonymity and more accurate values to represent the blocks with varying k . We also propose a novel similarity measure method which performs on the numerical attributes and combines with Paillier cryptosystem to measure the similarity of two or more blocks in security, which provides strong privacy guarantees that none information reveals even collusion. Experiments conducted on a public dataset of voter registration records validate that our approach is scalable to large databases and keeps a high quality of blocking. We compare our method with other techniques and demonstrate the increases in security and accuracy.

With the development of keyword search over relational databases, how to improve the result quality is a popular problem. To solve it, existing work mainly are CN-based and graph-based. The CN-based approaches occupy little memory space and have high level of abstract. However, the defect of these approaches is not considering meaningful information in metadata of databases. In this paper, we propose a novel architecture. First, it provides richer semantics for keywords to generate more meaningful candidate networks. Second, it provides query templates to facilitate the query transforms of candidate networks, which contribute to generating more meaningful query results. Third, some properties of ranking are simply summarized. Finally, the experimental results demonstrate that the result quality is improved.

Determing matching schemas enables queries on heterogeneous data space to be formulated and facilitates data integration. Current schema matching techniques most focus on mining mappings using elements' own information. This paper proposes to introduce semantic and functional dependencies into matching process to achieve multilayer schema matching results. It calculates semantic similarity with the help of Word Net and generates candidate mapping sets. By introducing functional dependency to formulize structural information, it can get structural similarities between element pairs. A probabilistic factor is considered to select mapping pairs. Through experimental evaluation on real data, the superiority of our method is verified.

Nowadays, most popular methods for web data extraction (WDE) are top-down ones depending on structure. However, these techniques are not scalable enough when coming to complex pages. Consequently, we put forward a bottom-up approach for WDE based on entity recognition and integration to avoid over dependency to structure of web pages. The approach proposed focuses on primary text sequences labeling first and also gives consideration to repetitive patterns of them as well. We propose a Two-Level extraction model for entity recognition and repetitive pattern extraction algorithm for entity integration. Our approach can effectively reduce the attribute labeling mistakes. Also, we demonstrate our approach by scientifically experimental results. The conclusion is that our approach perform better than the traditional extraction techniques, especially on complex Web pages.

This paper proposes a relation extraction model based on semantic pattern matching in Web environment. It consists of frequent pattern extraction, pattern clustering based on density, and pattern matching based on semantic similarity. First, based on the entities with known relations in a limited training set, we extract relation patterns containing these named entities from the web page. Then the relations between entities from the web page in specific areas can be extracted based on these relation patterns extracted. Experiments show the affectivity and the self-adaptive of our method on extracting relations between entities from dynamic web environment.

Keyword search is a wildly popular way for querying XML document. However, the increasing volume of XML data poses new challenges to keyword search processing. Parallel database is an efficient solution for this problem. In this paper, we study the problem of effective keyword search for SLCA (Smallest lower common ancestor) in parallel XML databases. We propose two efficient algorithm SONB (Scan once with no buffer) and MSOP (Merge strategy based on ordered partition) to compute the SLCA efficiently in the parallel environment. We have performed an extensive experimental study and the results show that our proposed approach achieves high efficiency for the keyword search.

As Deep Web contains tremendous well-structured data sources, how to integrate data sources in Deep Web has become a hotspot in current research. Accurately discovering and identifying Deep Web data sources related to a specific domain become key issues. We propose a Domain-Oriented Deep Web data source Discovery method (DO-DWD) and a novel Domain Identification strategy of Deep Web data sources (DIDW). In the discovery stage, we use machine learning algorithms and some heuristic rules to find query interfaces of the data sources; In the identification stage, we identify Deep Web data sources associated with the domain by calculating the relevance between a query interface and the domain based on semantic similarity. Finally, we have extensive experiments on a real data set showing that DO-DWD and DIDW are of high correctness and accuracy.

Because the amount of information contained on the Deep Web is much larger than the surface web, how to use it well has become a popular problem to research. When a query is sent to a deep web resource and the data sources return few results or even no result, a proper query relaxation solution should be adopted to get more satisfactory results to users. In this paper, such a query relaxation solution is presented. First, it solves the problem of relaxing attributes which contain multiple key words by value. That is, such attributes are not simply removed in the relaxation, but the query values of the attributes are modified. Second, when a data source returns many result pages, instead of getting all the pages, it evaluates the quality of the results in the current page to decide whether to send another query to fetch the next page. Thus, the number of query times is reduced. Finally, the experimental results demonstrate that both the result quality and the query efficiency are improved.

Data Grids primarily deal with providing services and infrastructure for distributed data-intensive applications, in which schema matching is a key technology for supporting dynamic data integration. Against the limitations of existed schema matching methods and with the aim of reducing the amount of user effort as much as possible, a novel approach to schema matching called SMM is proposed based on schema structure information and known matching knowledge, in which neural network influence procedure is imitated to realize semantic matching and reasoning, known matching knowledge is reused to supplement the matching and reasoning. At last, the experiment results show that SMM is feasible.

With the rapid growth of Web databases, it's necessary to extract and integrate large-scale data available in deep Web automatically. But current Web search engines conduct page-level ranking, which are becoming inadequate for entity-oriented vertical search. In this paper, we present an entity-level ranking mechanism called LG-ERM for deep Web query based on local scoring and global aggregation. Unlike traditional approaches, LG-ERM considers more rank influencing factors including the uncertainty of entity extraction, the style information of entities and the importance of Web sources, as well as the entity relationship. By combining local scoring and global aggregation in ranking, the query result can be more accurate and effective to meet users' needs. The experiments demonstrate the feasibility and effectiveness of the key techniques of LG-ERM.

To access the large-scale data sources efficiently and automatically, it is necessary to classify these data sources into different domains and categories. In this paper, we propose a novel classification approach to classify data sources into detail domain subjects by query probing. In our approach, we train sample instances for each subject category and use them to probe the data scale of each source and category. And then we build a matrix to classify a data source into one or more subject categories and develop a decision algorithm based on probing iteration to rectify the classification result. Our experiments over real deep web sources show that our approach can achieve higher accuracy across a variety of data sources.

A database grid can provide a robust distributed environment for accessing and manipulating different database resources. While current challenges focus on managing database resources and ensuring the quality of data integration. This paper describes a service level agreement (SLA) based data integration model, which includes SLA-based resource description model, SLA-based query model, SLA-based matching algorithm and SLA-based evaluation model. The SLAs of a database resource is defined by SLA-based resource description model. The SLA-based query model is defined to normalize the various types of queries. The SLA-based matching algorithm has been proposed to match schemas of resources for each sub-query, and then the quality of database resources is evaluated by SLA-based evaluation model to obtain the final query solutions. Experimental results have shown that SLA-based data integration model can provide more stable database resources and save time cost in data integration applications as well.

The Web services composition plays a more and more important role in SOA environment nowadays. Composing Web services on user's demand proves to be essential for both B2B and B2C applications. However, existing composition approaches and services composition description languages, such as BPEL4WS, are insufficient for satisfying user requirements. In this paper, we present an approach for Web services composition on demand. Our approach defines a description language for describing user's demand and supporting dynamic services binding for flexible service composition, and applies SLA to service discovery that can automatically adapt the change of QoS constraints. The description language can be applied to any process-oriented composition language that supports executable business processes. Finally, our approach is applied to a service grid system where it provides a fully automatic, stable service composition on user's demand