The increasing scale of graph datasets has significantly improved the performance of graph representation learning methods, but it has also introduced substantial training challenges. Graph dataset condensation techniques have emerged to compress large datasets into smaller yet information-rich datasets, while maintaining similar test performance. However, these methods strictly require downstream applications to match the original dataset and task, which often fails in cross-task and cross-domain scenarios. To address these challenges, we propose a novel causal-invariance-based and transferable graph dataset condensation method, named TGCC, providing effective and transferable condensed datasets. Specifically, to preserve domain-invariant knowledge, we first extract domain causal-invariant features from the spatial domain of the graph using causal interventions. Then, to fully capture the structural and feature information of the original graph, we perform enhanced condensation operations. Finally, through spectral-domain Enhanced contrastive learning, we inject the causal-invariant features into the condensed graph, ensuring that the compressed graph retains the causal information of the original graph. Experimental results on five public datasets and our novel FinReport dataset demonstrate that TGCC achieves up to a 13.41% improvement in cross-task and cross-domain complex scenarios compared to existing methods, and achieves state-of-the-art performance on 5 out of 6 datasets in the single dataset and task scenario.

Explainability plays a critical role in understanding the workings of Graph Neural Networks (GNNs). While recent methods have introduced causal inference into GNN explanation, they predominantly rely on individual-level interventions and lack rigorous statistical causality testing, resulting in unfaithful and unreliable explanations. To address these challenges, we propose CastX that integrates cohort-level causal analysis with statistical causality testing for GNN explanations. Specifically, CastX formulates the discovery of explanatory subgraphs as a dynamic edge pruning task guided by Conditional Average Treatment Effect (CATE) estimation. A reinforcement learning agent is employed to iteratively eliminate spurious edges and identify causally informative substructures. To further enhance reliability, we introduce an i.i.d.-agnostic non-parametric permutation test that assesses the statistical significance of each target edge. Extensive experiments on real-world datasets demonstrate that our CastX outperforms existing methods in yielding explanatory subgraphs that are concise, faithful, reliable, and statistically supported.

Revealing the underlying causal mechanisms in the real world is crucial for scientific and technological progress. Despite notable advances in recent decades, the lack of high-quality data and the reliance of traditional causal discovery algorithms (TCDA) on the assumption of no latent confounders, as well as their tendency to overlook the precise semantics of latent variables, have long been major obstacles to the broader application of causal discovery. To address this issue, we propose a novel causal modeling framework, TLVD, which integrates the metadata-based reasoning capabilities of large language models (LLMs) with the data-driven modeling capabilities of TCDA for inferring latent variables and their semantics. Specifically, we first employ a data-driven approach to construct a causal graph that incorporates latent variables. Then, we employ multi-LLM collaboration for latent variable inference, modeling this process as a game with incomplete information and seeking its Bayesian Nash Equilibrium (BNE) to infer the possible specific latent variables. Finally, to validate the inferred latent variables across multiple real-world web-based data sources, we leverage LLMs for evidence exploration to ensure traceability. We comprehensively evaluate TLVD on three de-identified real patient datasets provided by a hospital and two benchmark datasets. Extensive experimental results confirm the effectiveness and reliability of TLVD, with average improvements of 32.67% in Acc, 62.21% in CAcc, and 26.72% in ECit across the five datasets.

Risk disclosures play a crucial role in the investment decision‐making processes for investors. However, extracting relevant variables from unstructured financial text poses a nontrivial challenge. In this paper, we propose RiskBERT, a large language model (LLM) trained on financial texts and risk knowledge graphs, specifically designed for risk factors extraction. By incorporating both finance and risk knowledge, RiskBERT significantly improves the extraction of risk factors in financial texts. We evaluate RiskBERT’s performance on a labeled risk factors dataset comprising 119,153 sentences from 2400 Chinese A‐listed companies and compare it against other LLMs and automated text analysis algorithms for risk types’ classification. Our findings demonstrate that RiskBERT outperforms alternative models, particularly when the training sample size is limited. Moreover, we uncover that RiskBERT provides risk informativeness estimates in annual reports that are at least 4.5% higher than those derived from other models. These results highlight the value of RiskBERT as a powerful tool for extracting risk factors and enhancing risk analysis in finance and accounting domains.

Information theory has inspired numerous advancements in multi-view learning. Most multi-view methods incorporating information-theoretic principles rely an assumption called multi-view redundancy which states that common information between views is necessary and sufficient for down-stream tasks. This assumption emphasizes the importance of common information for prediction, but inherently ignores the potential of unique information in each view that could be predictive to the task. In this paper, we propose a comprehensive information-theoretic multi-view learning framework named CIML, which discards the assumption of multi-view redundancy. Specifically, CIML considers the potential predictive capabilities of both common and unique information based on information theory. First, the common representation learning maximizes Gács-Körner common information to extract shared features and then compresses this information to learn task-relevant representations based on the Information Bottleneck (IB). For unique representation learning, IB is employed to achieve the most compressed unique representation for each view while simultaneously minimizing the mutual information between unique and common representations, as well as among different unique representations. Importantly, we theoretically prove that the learned joint representation is predictively sufficient for the downstream task. Extensive experimental results have demonstrated the superiority of our model over several state-of-art methods. The code is released on CIML.

Sequential federated learning (SFL) trains models collaboratively across clients in a chain manner. This order shows communication efficiency compared to traditional FL in a parallel manner with a star topology. However, SFL can fail to produce stable training results when clients have significant statistical heterogeneity among their local data distributions. To address these challenges, we propose a novel element-wise model decoupling framework namedSeqFedEDTthat accelerates SFL training by separating model parameters of each client into a shared subset for global knowledge collaboration and a personalized subset for migrating data heterogeneity. We explore three types of parameter contribution scoring metrics based on gradient, Fisher information, and parameter importance (PI) for personalized parameter selection. In addition, we propose a quantile-based thresholding mechanism to separate shared and personalized subsets and explore the best performance quantile selection in numerical studies. Extensive experiments demonstrate thatSeqFedEDToutperforms eight state-of-the-art methods across diverse datasets and heterogeneity scenarios. All code and results are available athttps://github.com/tian0920/SeqFedEDT.

Revealing the underlying causal mechanisms in the real world is critical for scientific and technical progress. Despite advancements over the past decades, the lack of high-quality data and the inability of traditional causal discovery algorithms (TCDA) to fully comprehend the exact semantics of variables have long been major obstacles to the broader application of causal discovery. To address this issue, this paper proposes a novel causal modeling framework, LLM-CD, which integrates the metadata-based reasoning capabilities of large language models (LLMs) with the data-driven modeling abilities of TCDA for causal discovery. LLM-CD deeply couples the reasoning abilities of LLMs at various stages of TCDA, and enhances causal discovery through an iterative process. Due to the issues of overconfidence and hallucination in LLMs, LLM-CD quantifies and analyzes its uncertainty by incorporating evidence-based deep learning theory with the assumptions of TCDA. We utilize a large-scale de-identified real patient dataset provided by a hospital, a new dataset extracted from MIMIC-IV about the same disease (lung cancer), and two benchmark datasets to comprehensively evaluate LLM-CD. Extensive experimental results confirm the effectiveness and reliability of LLM-CD, with the highest improvement of 403.93% in the Recall and 25.77% in the Ratio metric across four datasets.

The highly volatile nature of the stock market makes predicting data patterns challenging. Significant efforts have been dedicated to modeling complex stock correlations to improve stock return forecasting and support better investor decision-making. Although various predefined intrinsic associations and learned implicit graph structures have been discovered, they have limitations in fully exploring and leveraging both types of graph information. In this paper, we proposed a Hybrid Structure-aware Graph Neural Network (HSGNN) framework. Unlike models that rely solely on predefined or learned graphs, HSGNN utilizes money-flow graphs to complementarily learn implicit graph structures and applies sparse supply-chain graphs to jointly enhance stock return forecasting. Extensive experiments on real stock benchmarks demonstrate our proposed HSGNN outperforms various state-of-the-art forecasting methods, offering a robust decision-support system for financial stakeholders.

In credit evaluation, feature selection and grouping effect analysis are used to identify the most relevant credit risk features. Most feature selection and grouping effect analysis are implemented via regularizing linear models. Nevertheless, substantial evidence shows that credit data are linearly inseparable due to heterogeneous credit customers and various risk sources. Although many nonlinear models have been proposed in the last two decades, the majority of them required recombination of the original features, which made it difficult to interpret the results of the models. To cope with this dilemma, we propose a diagonal distance metric learning model that improves distance metrics by rescaling the features. Meanwhile, feature selection and grouping effect analysis are realized by adding regularizations to the model. The main merit of the proposed model is that it avoids the limitation of the linear models by not pursuing linear separability, yet guaranteeing the interpretability. We also prove and explain why feature selection and grouping effect can be achieved and decompose the optimization problem into parallel linear programming problems, plus a small quadratic consensus-reaching problem, such that the optimization can be efficiently solved. Experiments using a real credit data set of 96,000 instances show that the proposed model improves the area under the receiver operating characteristic curve (AUC) of the distance-based classifier k-nearest neighbors by 14% in two-class credit evaluation and surpasses linear models in terms of accuracy, true positive rate, and AUC. The proposed regularized diagonal distance metric learning approach also has the potential to be applied to other fields where data are linearly inseparable. History: Accepted by Ram Ramesh, Area Editor for Data Science & Machine Learning. Funding: Financial support from the National Social Science Fund of China [Grant 23BTJ040] and the National Natural Science Foundation of China [Grants 72471047 and 71910107002] is gratefully acknowledged. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information ( https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2023.0322 ) as well as from the IJOC GitHub software repository ( https://github.com/INFORMSJoC/2023.0322 ). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/ .

Federated learning, as a promising distributed learning paradigm, enables collaborative training of a global model across multiple network edge clients without the need for central data collecting. However, the heterogeneity of edge data distribution drags the model towards the local minima, which can be distant from the global optimum. Such heterogeneity often leads to slow convergence and substantial communication overhead. To address these issues, we propose a novel federated learning framework calledFedCMD, a model decoupling tailored to the Cloud-edge supported federated learning that separates deep neural networks into a body for capturing shared representations in Cloud and a personalized head for migrating data heterogeneity. Our motivation is that, by the deep investigation of the performance of selecting different neural network layers as the personalized head, we found rigidly assigning the last layer as the personalized head in current studies is not always optimal. Instead, it is necessary to dynamically select the personalized layer that maximizes the training performance by taking the representation difference between neighbor layers into account. To find the optimal personalized layer, we utilize the low-dimensional representation of each layer to contrast feature distribution transfer and introduce a Wasserstein-based layer selection method, aimed at identifying the best-match layer for personalization. Additionally, a weighted global aggregation algorithm is proposed based on the selected personalized layer for the practical application ofFedCMD. Extensive experiments on ten benchmarks demonstrate the efficiency and superior performance of our solution compared with nine state-of-the-art solutions. All code and results are available athttps://github.com/elegy112138/FedCMD.

The graph contrastive learning (GCL) has garnered significant interest due to its strong capability to capture both graph structure and node attribute information through self-supervised learning. However, current GCL frameworks primarily construct final contrastive views based on local structure view, neglecting the valuable complementary information provided by the attribute view. In this article, we aim to effectively incorporate the attribute view into GCL while leveraging multiscale structure views. We identify that directly contrasting the attribute view with the local structure view results in impaired performance, primarily due to the excessively low level of mutual information (MI) between these two contrastive views. To overcome this inherent limitation, we propose a novel Attribute and Structure-Preserving GCL framework, named attribute and structure-preserving graph contrastive learning (ASP). ASP adopts an innovative contrastive view generation process that aggregates different graph views as the final contrastive view. The framework has two main modules: the attribute-preserving contrastive learning module and the structure-preserving contrastive learning module. These modules capture attribute and long-range global structure information of the input graphs. We further extend ASP to ASP-adaptive which can flexibly generate contrastive views with adaptive aggregation mechanisms. Extensive experiments on real-world graph benchmarks demonstrate the superiority of ASP and ASP-adaptive over several representative baselines on both node classification and link prediction tasks. The source code is available at: https://github.com/JialuChenChina/ASP-adaptive.

Learning from label proportions (LLPs), which aims to learn an instance-level classifier using proportion-based grouped training data, has garnered increasing attention in the field of machine learning. Existing deep learning-based LLP methods employ end-to-end pipelines to derive proportional loss functions via the Kullback-Leibler (KL) divergence between bag-level prior and posterior class distributions. However, the optimal solutions of these methods often struggle to conform to the given proportions, inevitably leading to degradation in the final classification performance. In this article, we address this issue by proposing a novel progressive training method for LLP, termed PT-LLP, which strives to meet the proportion constraints from the bag level to the instance level. Specifically, we first train a model by using the existing KL-divergence-based LLP methods that are consistent with bag-level proportion information. Then, we impose additional constraints on strict proportion consistency to the classifier to further move toward a more ideal solution by reformulating it as a constrained optimization problem, which can be efficiently solved using optimal transport (OT) algorithms. In particular, the knowledge distillation is employed as a transition stage to transfer the bag-level information to the instance level using a teacher-student framework. Finally, our framework is model-agnostic and demonstrates significant performance improvements through extensive experiments on different datasets when incorporated into other deep LLP methods as the first training stage.

In the past decade, the sensor and surveillance technology have been widely used in condition monitoring. The hidden states of systems can be inferred from collected sensor data. However, the maintenance decision problem becomes more challenging when ordering decision of the spare parts must be considered jointly. In this article, we consider a multistate deteriorating system whose states are hidden but partially observable, and determine the optimal maintenance and spare parts inventory ordering policy. We use the partially observable Markov decision process to model the problem of interest and adopt the state-of-the-art heuristic search value iteration algorithm to solve the optimization problem. The proposed policy is illustrated and compared with$( {{\bm{s}},{\bm{S}}} )$inventory policy through a series of numerical examples. The numerical results indicate that our proposed policy is cost effective. Further, the model of multicomponent system is formulated, highlighting the adaptability of our framework. This research shows that considering the system component conditions and spare parts ordering jointly can result a lower operation and maintenance cost.

Temporal graph representation learning has drawn considerable attention in recent years. Most existing works mainly focus on modeling local structural dependencies of temporal graphs. However, underestimating the inherent global structural role information in many real-world temporal graphs inevitably leads to sub-optimal graph representations. To overcome this shortcoming, we propose a novel Role-based Temporal Graph Convolution Network (RTGCN) that fully leverages the global structural role information in temporal graphs. Specifically, RTGCN can effectively capture the static global structural roles by using hypergraph convolution neural networks. To capture the evolution of nodes' structural roles, we further design structural role-based gated recurrent units. Finally, we integrate structural role proximity in our objective function to preserve global structural similarity, further promoting temporal graph representation learning. Experimental results on multiple real-world datasets demonstrate that RTGCN consistently outperforms state-of-the-art temporal graph representation learning methods by significant margins in various temporal link prediction and node classification tasks. Specifically, RTGCN achieves AUC improvement of up to 5.1% for link prediction and F1 improvement of up to 6.2% for new link prediction. In addition, RTGCN achieves AUC improvement up to 4.6% for node classification and 2.7% for structural role classification.

Semiconductor materials play a crucial role in the development of optoelectronics and power devices. However, their evaluation and selection pose a multi-attribute decision-making problem. This problem encompasses various considerations, such as multiple evaluation criteria, data variation, and the importance of criteria multiplicity. Therefore, this study proposes an integrated fuzzy multi-measurement decision-making model (IFMMDMM) to evaluate and select optimization techniques for semi-polar III-V semiconductor materials. The research methodology is designed based on three sequential phases. Firstly, four optimization techniques for semi-polar III-V semiconductor materials and four evaluation criteria are identified to construct the evaluation decision matrix. Secondly, the fuzzy-weighted zero-inconsistency method is developed to evaluate and assign weights to the defined multi-measurement criteria. Thirdly, the fuzzy decision by opinion score method is developed to select the optimization techniques for semi-polar III-V semiconductor materials. The weighting results reveal that the highest weight value was assigned to ‘root mean square under surface morphology’ ( 0.1382 ), while ‘peak-to-valley under surface morphology’ received the lowest weight value ( 0.1074 ). The selection results indicated that ‘different flux with fixed cycle NH3 treatment (D)’ ranked first, whereas ‘NH3 flux at changing V/III (A)’ had the lowest performance order. Systematic and sensitivity ranking assessments were performed to verify the efficiency of the proposed model.

This paper introduces a novel Integrated Interval Rough Pivot Pairwise Relative Criteria Importance Assessment (IRN PIPRECIA) model combined with Interval Rough Combined Compromise Solution (IRN CoCoSo), marking a significant advancement in sustainable traffic flow management for commercial vehicles. This innovative merger is a first in literature, methodologically enhancing the evaluation of road sections based on critical parameters including passenger car equivalent (PCE) 85%, AADT, road conditions, and accident data. Our model systematically fills the research gap in holistic traffic performance analysis, providing a unique tool for prioritizing road safety and efficiency. The key scientific contribution is the model’s ability to integrate causal and consequential traffic factors into a single framework, offering a novel multi-criteria decision-making (MCDM) approach. Results, validated through various verification models, show the integrated model’s effectiveness in real-world scenarios, confirming its robustness and stability. With strong engineering application potential, our work supports urban planners and traffic managers in making informed, sustainable decisions. The model extends beyond traditional traffic analysis, promising a shift towards more adaptive, data-driven infrastructure management. Future research will aim to refine the criteria basis and explore real-time decision-making through advanced MCDM applications.

Choosing the right projects in renewable energy investments is very significant. Due to this issue, necessary improvements to the performance indicators of these projects should be made. However, every improvement made also leads to an increase in costs. There is a need for a priority analysis to find the most important factors affecting the selection of the right renewable energy projects. Accordingly, this study aims to evaluate critical determinants of renewable energy project selection and provide effective investment strategies for this situation with a new fuzzy decision-making model. First, the indicators of renewable energy project selection are analyzed by perception and expression-based quantum Spherical fuzzy M-SWARA. The weights of these determinants are also calculated by DEMATEL to check the reliability of the results. Secondly, the priorities of renewable energy project selection are ranked by considering perception and expression-based quantum Spherical fuzzy ELECTRE. This calculation is also made by TOPSIS methodology to measure the reliability of the findings. The main contribution of this manuscript is that perception and expression-based evaluation can be carried out in the proposed model. In this process, the facial expressions and emotions of the decision makers are considered so that the hesitancy of these people while answering these questions can be included in the evaluation process. Another important novelty is that a new decision-making model (M-SWARA) is also proposed. This new technique provides an opportunity to consider causality relationship between the criteria to reach the most significant ones. The weighting results are the same for both M-SWARA and DEMATEL approaches. This situation gives information that the findings are coherent and valid. Market analysis has the greatest value in both perception-based (0.272) and expression-based (0.259) evaluations. Owing to this analysis, it is possible to clearly understand the supply-demand balance in the market. The ranking results indicate that technical adequacy is the most significant priority alternative for the selection of the appropriate renewable energy alternatives.

Network embedding is a fundamental part of many network analysis tasks, including node classification and link prediction. The existing random walk-based embedding methods aim to learn node embedding that preserves information on either node proximity or structural similarity. However, the information on both role and community is important to network nodes. To address the shortcomings of the existing methods, this paper proposes a novel method for network embedding called the RARE, which can be used for the analysis of different types of networks and even disconnected networks. The proposed method uses the role and community information of nodes to preserve both node proximity and structural similarity in the learned node embeddings. The walks generated through the role-aware random walk can capture the role and community information of nodes. The obtained walks are input to the Skip-gram model to learn the final embedding of nodes. In addition, the RARE is extended to the CRARE that adds the sampling of high-order community members to the customized random walk so that the node’s representation can preserve more structural information of the network. The performances of the proposed methods are evaluated on multi-class node classification, link prediction, and network visualization tasks. Experimental results on different domain datasets indicate that the proposed methods outperform the baseline methods. The proposed methods can be further accelerated using parallelization in the random walk generation process.

Many production systems undergo a multistate deterioration process before failure, during which inspection and repair are used to detect and remove the defects. Given the limitations of technology and random noise, inspection and repair are always imperfect. This study considered imperfect inspection and repair for a system subject to a three-stage degradation process. The concepts of virtual age and the improvement factor were adopted to characterize the imperfect repair effect. To verify the effectiveness of the proposed model, we applied it to the case of a steel converter plant and used the genetic algorithm to search for the optimal solution. The numerical results indicated that an optimal arrangement of inspection policy could significantly reduce maintenance costs.

Graph Contrastive Learning (GCL) has drawn much research interest due to its strong ability to capture both graph structure and node attribute information in a self-supervised manner. Current GCL methods usually adopt Graph Neural Networks (GNNs) as the base encoder, which typically relies on the homophily assumption of networks and overlooks node similarity in the attribute space. There are many scenarios where such assumption cannot be satisfied, or node similarity plays a crucial role. In order to design a more robust mechanism, we develop a novel attribute and structure preserving graph contrastive learning framework, named ASP, which comprehensively and efficiently preserves node attributes while exploiting graph structure. Specifically, we consider three different graph views in our framework, i.e., original view, attribute view, and global structure view. Then, we perform contrastive learning across three views in a joint fashion, mining comprehensive graph information. We validate the effectiveness of the proposed framework on various real-world networks with different levels of homophily. The results demonstrate the superior performance of our model over the representative baselines.

Interval-valued Fermatean fuzzy sets play a significant role in modelling decision-making problems with incomplete information more accurately than intuitionistic fuzzy sets. Various decision-making methods have been introduced for the different classes IFSs. In this study, we aim to introduce a novel two-phase interval-valued Fermatean fuzzy dominance method which suits the decision-making problems modelled under the IVFFS environment well and study its applications in the adoption of energy consumption in Urban mobility considering digital carbon footprint. The proposed method considers the importance and performance of one alternative with respect to all others, which is not the case with many available decision-making algorithms introduced in the literature. Transportation is one of the most significant sources of global greenhouse gas (GHG) emissions. Numerous potential remedies are proposed to reduce the quantity of GHG generated by transportation activities, including regulatory measures and public transit digitalization initiatives. Decision-makers, however, should consider the digital carbon footprint of such projects. This study proposes three alternatives for reducing GHG emissions from transportation activities: incremental adoption of digital technologies to reduce energy consumption and greenhouse gases, disruptive digitalization technologies in urban mobility, and redesign of urban mobility using regulatory approaches and economic instruments. The proposed novel two-phase interval-valued Fermatean fuzzy dominance method will be utilized to rank these alternative projects in order of advantage. First, the problem is converted into a multi-criterion group decision-making problem. Then a novel two-phase interval-valued Fermatean fuzzy dominance method is designed and developed to rank the alternatives. The importance and advantage of the proposed two-phase method over other existing methods are discussed by using sensitivity and comparative analysis. The results indicate that rethinking urban mobility through governmental policies and economic tools is the least advantageous choice, while incremental adoption of digital technologies is the most advantageous.

As a novel architecture of a fuzzy decision tree constructed on fuzzy rules, the fuzzy rule-based decision tree (FRDT) achieved better performance in terms of both classification accuracy and the size of the resulted decision tree than other classical decision trees such as C4.5, LADtree, BFtree, SimpleCart and NBTree. The concept of Z-number extends the classical fuzzy number to model both uncertain and partial reliable information. Z-numbers have significant potential in rule-based systems due to their strong representation capability. This paper designs a Z-number-valued rule-based decision tree (ZRDT) and provides the learning algorithm. Firstly, the information gain is used to replace the fuzzy confidence in FRDT to select features in each rule. Additionally, we use the negative samples to generate the second fuzzy numbers that adjust the first fuzzy numbers and improve the model's fit to the training data. The proposed ZRDT is compared with the FRDT with three different parameter values and two classical decision trees, PUBLIC and C4.5, and a decision tree ensemble method, AdaBoost.NC, in terms of classification effect and size of decision trees. Based on statistical tests, the proposed ZRDT has the highest classification performance with the smallest size for the produced decision tree.

Representation learning has an important impact on the performance of machine learning methods and has been used to solve many distribution problems for numerous graphical and sequential mining tasks. While the distributions of credit data are very complex, the representations of such data are less studied. This study proposes a new representation learning approach based on a neural network called NyströmNet, which represents the credit data to benefit credit evaluation and sub-pattern analysis. The NyströmNet is developed to utilize the advantages of the Nyström method – a kernel approximation method in credit evaluation, yet overcomes its two limitations: distance distortions in kernel functions, and parameter tuning. The two main modules contained in NyströmNet, i.e., the Distance Metric Learning module and the Nyström module, can benefit each other and yield an overall optimum. Experiments using six real-life large-scale credit data showed that the AUC of the distance-based classifiers and the linear classifiers were improved by 2–11% and 2–14% with the newly generated distributions. The proposed approach also has certain practical advantages over traditional approaches because it is free from complex parameter tuning, consumes fewer memories, and is easy to utilize automatic differential frameworks such as PyTorch. The proposed approach is highly suitable for large-scale credit evaluation.

Stock Movement Prediction (SMP) aims at predicting listed companies' stock future price trend, which is a challenging task due to the volatile nature of financial markets. Recent financial studies show that the momentum spillover effect plays a significant role in stock fluctuation. However, previous studies typically only learn the simple connection information among related companies, which inevitably fail to model complex relations of listed companies in real financial market. To address this issue, we first construct a more comprehensive Market Knowledge Graph (MKG) which contains bi-typed entities including listed companies and their associated executives, and hybrid-relations including the explicit relations and implicit relations. Afterward, we proposeDanSmp, a novel Dual Attention Networks to learn the momentum spillover signals based upon the constructed MKG for stock prediction. The empirical experiments on our constructed datasets against nine SOTA baselines demonstrate that the proposedDanSmpis capable of improving stock prediction with the constructed MKG.

Bi-typed multi-relational heterogeneous graph (BMHG) is one of the most common graphs in practice, for example, academic networks, e-commerce user behavior graph and enterprise knowledge graph. It is a critical and challenge problem on how to learn the numerical representation for each node to characterize subtle structures. However, most previous studies treat all node relations in BMHG as the same class of relation without distinguishing the different characteristics between the intra-type relations and inter-type relations of the bi-typed nodes, causing the loss of significant structure information. To address this issue, we propose a novelDualHierarchicalAttentionNetworks (DHAN) based on the bi-typed multi-relational heterogeneous graphs to learn comprehensive node representations with the intra-type and inter-type attention-based encoder under a hierarchical mechanism. Specifically, the former encoder aggregates information from the same type of nodes, while the latter aggregates node representations from its different types of neighbors. Moreover, to sufficiently model node multi-relational information in BMHG, we adopt a newly proposed hierarchical mechanism. By doing so, the proposed dual hierarchical attention operations enable our model to fully capture the complex structures of the bi-typed multi-relational heterogeneous graphs. Experimental results on various tasks against the state-of-the-arts sufficiently confirm the capability of DHAN in learning node representations on the BMHGs.

Inspection is usually carried out periodically to update a system state such that the optimal maintenance policy can be determined. In order to obtain the best inspection and maintenance policy, existing research is focused on improving the modeling accuracy of the system failure process. Little work has been devoted to making full use of the system idle time, which is known as the production wait in production systems. In this research, the failure process of a single-unit system is modeled in three stages with consideration of its production wait time. The objective of minimizing the long-run average maintenance cost per unit time is achieved by finding the optimal length of the periodic inspection interval and renewal age for this single-unit system. By comparing this model with two two-stage inspection models, the numerical study of a real steelmaking converter confirms both the accuracy and effectiveness of the proposed inspection and maintenance model. Furthermore, the sensitivity analysis of different parameters is conducted to explore the optimal choice of maintenance strategy for different cost parameters and degradation parameters. The analysis provides useful management insights for decision-makers.

With the emergence of the industrial internet of things, distributed data storage systems have become widely used to store the monitoring data of power generation systems. Malicious hackers often try to destroy or steal these confidential data by illegally invading the systems. In addition to hackers’ illegal intrusions, the availability of the data stored is also affected by the internal failures of the system.In this research, two reliability models are formulated to study the reliability of a phased-mission distributed data storage system considering internal failures and illegal intrusion. The first model considers internal failures and data destruction, whereas the second model further considers data theft. Furthermore, the allocation of the data partitions is optimized so that system reliability can be maximized. Numerical experiments demonstrate the effectiveness of the proposed models and algorithms.

In many real production systems, a system may be stopped due to a lack of demand or exhaustion of raw materials. This is known as production wait and provides a good opportunity for maintenance. Meanwhile, the increased complexity of the modern machines brings new challenges for modeling and analyzing their failure behaviors. To address these real-world problems, this article considers a single-unit system that may fail due to either hard failures or soft failures. The wait time of a system is utilized to conduct inspections and maintenance. The system is replaced when a defect is found during an inspection, a failure occurred or a prespecified age threshold is reached, whichever comes first. The cost model, which is the long-run maintenance cost per unit of time, is derived. The optimal periodical inspection interval and the threshold age to minimize the long run maintenance cost per unit of time is then obtained. A case study is conducted to demonstrate the proposed maintenance model. The study shows using the proposed maintenance model can reduce the cost. Sensitivity analysis illustrates how each cost parameter affects the optimal inspection interval and the optimal age threshold.

In traditional social network analysis-based large-scale group decision making (LSGDM), decision makers (DMs) often trust others based on social prestige/status without sufficient information to understand others’ credibility. Notably, this ignores the inherent risks of trust, resulting in the LSGDM process being subject to trust risk behaviors (blind trust/lack of trust), which ultimately causes unreasonable aggregation weights allocation and unreliable decision results. Therefore, this article develops a trust risk analysis-based social network LSGDM model to mine and manage trust risk behaviors, reasonably assign aggregation weights and reach consensus. In this model, DMs are divided into different communities by a clustering method. The performances of DMs in each community are observed during the decision-making process and their credibility is evaluated. Community’s credibility is modeled by a multicriteria credibility assessment matrix (MCAM). Combined with external network structure information, community’s synthetical trust assessment matrix (STAM) is constructed. Furthermore, group’s MCAM and STAM are obtained by information collection from all communities. The aggregation weights of communities and DMs are dynamically derived from STAMs of group and communities, respectively. Afterward, a trust risk behaviors mining and detection method is presented to mine communities’ different behaviors and determine the trust risk degree of the group. When the group is deemed too risky, the trust risk behaviors management mechanism allows to compensate or punish the weights of communities with different behaviors, and give recommendations for information modification. Sensitivity analysis and comparative analysis, as well as a case study, verify the feasibility and superiority of the proposed methods.

Consensus reaching process (CRP), as an essential part of group decision making (GDM), can facilitate more effective consensus by taking human behaviors into account. Extending the established research on uncertain minimum cost consensus models (MCCMs), this article continues to adopt linear uncertainty distributions (LUDs) to represent decision-maker’s (DM’s) preference, but considers asymmetric costs into a new framework of CRP, where DM’s preference and weight are both adjusted according to democratic consensus. Moreover, in light of the uncertain distance measure, two novel optimization-based consensus models are built in this article: one is to obtain a minimum cost consensus by simultaneously considering asymmetric costs, aggregation function, and consensus measure; while the other provides a more flexible way to address GDM problems without presetting a specific consensus level (CL) threshold. Some 0–1 binary variables are further introduced to reduce the calculation complexity resulted from piecewise functions in the new multicoefficient goal programming models. Finally, an illustrative example and further discussion reveal the feasibility and superiority of our new method.

Group decision making (GDM) is normally resource consuming and requires a moderator to lead a group of experts to achieve consensus. A moderator’s preference on consensus level affects the cost of GDM and has important impacts on the consensus results. However, no previous research has considered the moderator’s preference in consensus. The objective of this article is to analyze the effect of the moderator’s preference on consensus result in GDM. We develop a set of optimization models and propose a bilateral compromise consensus-reaching framework, which provides a flexible way to reach an agreement. We apply the models to a loan consensus problem under a peer-to-peer lending environment. The results show that a moderator with a radical preference on consensus levels presents a lower initial group consensus level and requires more resources than the other two preference types. A moderator with a mixed preference presents the highest initial group consensus level and requires the lowest resources among the three types of preferences.

In recent years, multiplex network embedding has received great attention from researchers. However, existing multiplex network embedding methods neglect structural role information, which can be used to determine the structural similarity between nodes. To overcome this shortcoming, this work proposes a simple, effective, role-based embedding method for multiplex networks, called RMNE. The RMNE uses the structural role information of nodes to preserve the structural similarity between nodes in the entire multiplex network. Specifically, a role-modified random walk is designed to generate node sequences of each node, which can capture both the within-layer neighbors, structural role members, and cross-layer structural role members of a node. Additionally, the variant of RMNE extends the existing collaborative embedding method by unifying the structural role information into our method to obtain the role-based node representations. Finally, the proposed methods were evaluated on the network reconstruction, node classification, link prediction, and multi-class edge classification tasks. The experimental results on eight public, real-world multiplex networks demonstrate that the proposed methods outperform state-of-the-art baseline methods.

Balancing the accuracy rates of the majority and minority classes is challenging in imbalanced classification. Furthermore, data characteristics have a significant impact on the performance of imbalanced classifiers, which are generally neglected by existing evaluation methods. The objective of this study is to introduce a new criterion to comprehensively evaluate imbalanced classifiers. Specifically, we introduce an efficiency curve that is established using data envelopment analysis without explicit inputs (DEA-WEI), to determine the trade-off between the benefits of improved minority class accuracy and the cost of reduced majority class accuracy. In sequence, we analyze the impact of the imbalanced ratio and typical imbalanced data characteristics on the efficiency of the classifiers. Empirical analyses using 68 imbalanced data reveal that traditional classifiers such as C4.5 and the k-nearest neighbor are more effective on disjunct data, whereas ensemble and undersampling techniques are more effective for overlapping and noisy data. The efficiency of cost-sensitive classifiers decreases dramatically when the imbalanced ratio increases. Finally, we investigate the reasons for the different efficiencies of classifiers on imbalanced data and recommend steps to select appropriate classifiers for imbalanced data based on data characteristics.

Coupled information diffusion in complex networks has been widely studied in recent years. Nevertheless, current research mainly focuses on the interaction between each information pair. In this study, we investigate the interaction of multiple types of information on multiplex networks by considering both the competition and the cooperation among them. To study the dynamic characteristics theoretically, a microscopic Markov chain approach is used to reveal the co-evolution of multiple information. Through extensive simulations, the outbreak threshold is analyzed theoretically. The results reveal that the pairwise interaction between each information pair has an obvious impact on its final outbreak scale and the diffusion threshold. Interestingly, even information that has no direct impact on the target information can affect the diffusion of the target information through indirect effects. In addition, the inhibitory effect of the competitive information and the promotion effect of the cooperative information on the target information will reach equilibrium under specific parameter space conditions. We also conduct numerical simulations on three real multiplex social networks, including two large-scale networks. Current results are beneficial for us to further understand the coupled diffusion of multiple information on multiplex social networks.

In many financial applications, such as fraud detection, reject inference, and credit evaluation, detecting clusters automatically is critical because it helps to understand the subpatterns of the data that can be used to infer user's behaviors and identify potential risks. Due to the complexity of human behaviors and changing social environments, the distributions of financial data are usually complex and it is challenging to find clusters and give reasonable interpretations. The goal of this study is to develop an integrated approach to detect clusters in financial data, and optimize the scope of the clusters such that the clusters can be easily interpreted. Specifically, we first proposed a new cluster quality evaluation criterion, which is free from large-scale computation and can guide base clustering algorithms such as k -Means to detect hyperellipsoidal clusters adaptively. Then, we designed a new solver for a revised support vector data description model, which efficiently refines the centroids and scopes of the detected clusters to make the clusters tighter such that the data in the clusters share greater similarities, and thus, the clusters can be easily interpreted with eigenvectors. Using ten financial datasets, the experiments showed that the proposed algorithm can efficiently find reasonable number of clusters. The proposed approach is suitable for large-scale financial datasets whose features are meaningful, and also applicable to financial mining tasks, such as data distribution interpretation and anomaly detection.

Classic portfolio selection problems mainly focus on high-risk financial markets with tradeoffs between returns and risk. However, more risk-averse investors pursue long-term portfolio planning with the objectives of maximizing final returns and maximizing flexibility. This article addresses a new type of the portfolio problem, called periodic investment portfolio selection problems (PIPSPs), in which investors periodically allocate resources to financial products with different periods. A multiobjective model for PIPSPs is first presented. With a mechanism for utilizing the data generated during the implementation of multiobjective evolutionary algorithms (MOEAs), a data-assisted MOEA (DA-MOEA) is proposed to solve PIPSPs. The main idea of a DA-MOEA is to combine a MOEA with a data-assisted process that consists of three components: 1) feature construction; 2) data fusion model development; and 3) obtained information utilization. To solve the addressed PIPSPs, two versions of DA-MOEAs with baselines of nondominated sorting and decomposition-based mechanisms are implemented, namely, the data-assisted NSGA-II (DA-NSGA-II) and data-assisted MOEA/D (DA-MOEA/D). In the developed DA-MOEAs for PIPSPs, a feature construction process and a data fusion model are well designed for mining data with different formats. To validate the algorithms, two sets of test instances are generated. The experimental results demonstrate the efficacy of the data-assisted process. Furthermore, the effects of the algorithm components, such as the data source sizes, information types, and information utilization strategies, are investigated.

Inspired by the continuous opinion and discrete action (CODA) model, bounded confidence and social networks, the bounded confidence evolution of opinions and actions in social networks is investigated and a social network opinions and actions evolutions (SNOAEs) model is proposed. In the SNOAE model, it is assumed that each agent has a CODA for a certain issue. Agents' opinions are private and invisible, that is, an individual agent only knows its own opinion and cannot obtain other agents' opinions unless there is a social network connection edge that allows their communication; agents' actions are public and visible to all agents and impact other agents' actions. Opinions and actions evolve in a directed social network. In the limitation of the bounded confidence, other agents' actions or agents' opinions noticed or obtained by network communication, respectively, are used by agents to update their opinions. Based on the SNOAE model, the evolution of the opinions and actions with bounded confidence is investigated in social networks both theoretically and experimentally with a detailed simulation analysis. Theoretical research results show that discrete actions can attract agents who trust the discrete action, and make agents to express extreme opinions. Simulation experiments results show that social network connection probability, bounded confidence, and the opinion threshold of action choice parameters have strong impacts on the evolution of opinions and actions. However, the number of agents in the social network has no obvious influence on the evolution of opinions and actions.

Consensus reaching process (CRP) is important and present in a wide range of application areas. In practical CRP, the managers (e.g., enterprise) often hire some informed individuals (e.g., persuaders) to promote the efficiency of consensus reaching. This article proposes a CRP with minimum cost of informed individuals and time constraint in large-scale group decision-making (LSGDM) with bounded confidence effects. The consensus model with bounded confidence effects (CBC model) is formulated. Then, desirable properties of the CBC model are discussed to facilitate its resolution. Next, an extended particle swarm optimization algorithm is designed to solve the CBC model. Finally, a numerical analysis, a comparison analysis, and a simulation analysis are provided to illustrate the feasibility and effectiveness of the proposed approach.

Existing research has been concentrated on improving the reliability of a distributed computing system through optimizing tasks allocation, providing software redundancy and providing hardware redundancy. None of these works considered the performance sharing mechanism in a distributed computing system. Different from other performance sharing systems whose reliability can be calculated directly, the reliability evaluation of a distributed computing system with performance sharing is more challenging since the reliability depends on the task execution time of each processor after performance sharing. This research considers a distributed computing system with performance sharing mechanism such that the computing power can be redistributed among different processors in the system. A reliability model is proposed to evaluate the distributed computing system with performance sharing. An optimization model is formulated to derive the optimal performance sharing policy such that the system reliability can be maximized. Both analytic examples and numerical examples are carried out to illustrate the proposed model and algorithm.

As the number of people involved in a decision-making problem increases, the complexity of the group decision-making (GDM) process increases accordingly. The size of participants and the heterogeneous information have important effects on the consensus reaching process in GDM. To deal with these two issues, traditional methods divide large groups into smaller ones to reduce the scale of GDM and translate heterogeneous information into a uniform format to handle the heterogeneity problem. These methods face two challenges: 1) how to determine the appropriate group size? and 2) how to avoid or reduce loss of information during the transformation process? To address these two challenges, this article uses fuzzy cluster analysis to integrate heterogeneous information for large-scale GDM problems. First, a large group is divided into smaller ones using fuzzy cluster analysis and the F-statistic is applied to determine the satisfactory number of clusters. The original information is retained based on the similarity degree. Then, a consensus reaching process is conducted within these small groups to form a unified opinion. A feedback mechanism is developed to adjust the small GDM matrix when any group cannot reach a consensus, and the heterogeneous technique for order preference by similarity to an ideal solution (TOPSIS) is used to select the best alternative. To validate the proposed approach, an experiment study is conducted using a practical example of selecting the best rescue plan in an emergency situation. The result shows that the proposed approach helps to choose the best rescue plan faster.

Pairwise comparison matrix (PCM) is an important tool to rank items by deriving priorities and has been used in various applications. Though large-scale sparse PCMs appear frequently in today’s big data environment, it is hard for existing prioritization methods to handle large-scale sparse PCMs efficiently due to the curse of dimensionality. The goal of this article is to propose a new algorithm, bipartite graph iterative method (BGIM), to derive priorities from large-scale sparse PCMs. We first extended graph representations of PCMs to bipartite graphs. A transition matrix was induced by resource allocation on the bipartite graph. Finally, an iterative algorithm was designed to calculate priorities. The theoretical properties of the BGIM were analyzed to show its ability to derive priorities from large-scale sparse PCMs. Two experiments were conducted to validate the proposed approach. The numerical examples indicated that the BGIM can deal with traditional decision problems and derive reliable priorities with minimum Euclidean distance (ED) and minimum violation (MV) among the tested methods. The simulation examples suggested that the BGIM can not only derive reliable priorities from large-scale sparse PCMs but also require the least computation time compared with eight prioritization approaches. To demonstrate its applicability to real-world large-scale problems, we applied the BGIM to rank movies using MovieLens dataset with more than 100 000 ratings for 9125 movies. The results showed that the BGIM was the fastest approach and obtained the best ranking among the average ratings and the five prioritization methods.

Many bankruptcy prediction models for small and medium-sized enterprises (SMEs) are built using accounting-based financial ratios. This study proposes a bankruptcy prediction model for SMEs that uses transactional data and payment network–based variables under a scenario where no financial (accounting) data are required. Offline and online test results both confirmed the predictive capability and economic benefit of transactional data–based variables. However, incorporating those features in predictive models produces high dimensional problems, which deteriorates model interpretability and increases feature acquisition costs. Thus, we propose a two-stage multiobjective feature-selection method that optimizes the number of features as well as model classification performance. The results showed that the proposed model achieved similar classification performance while greatly reducing the cardinality of the feature subset. Finally, the feature importance evaluation for features in the optimal subset confirmed the importance of transactional data and payment network-based variables for bankruptcy prediction.

The benchmarking of smart e-tourism data management applications falls under the problem of multicriteria decision-making (MCDM). This claim is supported by three issues: 12 smart key concepts need to be considered in the evaluation, criteria importance, and data variation among these criteria. Thus, an MCDM solution is essential to overcome problem complexity. To end this, this study presents a decision-making framework on the basis of the extension of interval type 2 trapezoidal-fuzzy weighted with zero inconsistency (IT2TR-FWZIC) integrated with the Vlsekriterijumska Optimizcija I Kaompromisno Resenje (VIKOR) method for evaluating and benchmarking the smart e-tourism data management applications. Our methodology comprises two consecutive phases. In the first phase, a decision matrix is constructed using the intersection between the 12 key concepts and smart e-tourism data management applications of each category and subcategory in smart e-tourism. In the second phase, the integration of the IT2TR-FWZIC formulation and VIKOR is presented to compute the weights for the 12 key concepts and benchmark the smart e-tourism data management applications for each category. The results are as follows: (1) A clear difference is found among the criteria weights (12 smart key concepts). Specifically, the real-time criterion achieves the highest importance weight (0.098), whereas augmented reality obtains the lowest weight (0.068). The context-awareness and recommender systems have the same weight value (0.087), and the other eight criteria are distributed in between. (2) The smart e-tourism data management applications are evaluated and benchmarked effectively per category and subcategories. (3) Benchmarked applications in each category are subjected to a systematic ranking in the evaluation process. The sensitivity analysis has shown high correlation outcomes to the systematic ranking results over the 31 scenarios of criteria weight changing. Moreover, a comparative analysis of the proposed work with other existing studies is also discussed.

Urban resettlement projects involve a large number of stakeholders and impose tremendous cost. Developing resettlement plans and reaching an agreement amongst stakeholders about resettlement plans at a reasonable cost are some of the key issues in urban resettlement. From this perspective, urban resettlement is a typical large-scale group decision-making (GDM) problem, which is challenging because of the scale of participants and the requirement of high consensus levels. Observing that residents who are affected by a resettlement project often have tight social connections, this study proposes a framework to improve the consensus reaching and uses the minimum consensus cost to reduce the total cost for urban resettlement projects with more than 1000 participants. Firstly, we construct a network topology that consists of two layers to deal with incomplete social relationships amongst large-scale participants. An inner layer consists of participants whose preference similarities and trust relations are known. Meanwhile, an outside layer includes participants whose trust relations cannot be determined. Secondly, we develop a classification method to classify participants into small subgroups based on their preference similarities. We can then connect the participants whose trust relations are unknown (the outside layer) with the ones in the inner layer using the classification results. To facilitate effective consensus reaching in large-scale social network GDM, we develop a three-step approach to reconcile conflicting preferences and accelerate the consensus process at the minimum cost. A real-life urban resettlement example is used to validate the proposed approach. Results show that the proposed approach can reduce the total consensus cost compared with the other two practices used in the actual urban resettlement operations.

Distance metric learning (DML) aims to learn distance metrics that reflect the interactions between features and labels. Due to the high computational complexity, existing DML models are unsuitable for large-scale datasets. This study proposes a DML approach for large-scale problems by reducing the number of variables, utilizing sparse structures of the optimization problems, and taking advantage of large-scale computation platforms. The proposed approach treats DML as a linear space transformation problem and suggests that a full DML matrix can be approximated by a diagonal matrix in many cases. We solve the diagonal DML problem along with its ℓ1 and ℓ2 regularizations via linear and quadratic programming. To facilitate large-scale learning problems, we design a MapReduce framework to build triplets, which are encapsulations of triple data points used for the optimization problem, and develop a weighting mechanism for triplets according to their contributions to the whole distance distortion. Experiments show that the proposed approach is fast in large-scale DML applications with comparable accuracy to much more time-consuming full-matrix models. Since the approach is implemented with the Scala language based on the Spark platform, it can be used directly by productive Java applications, which makes it highly practical for large-scale datasets.

Recent multi-criteria group decision making methods focus their analysis on the experts preferences. They do not take into account the reasons why each expert has provided a specific set of preferences. In this paper, a method that introduces novel measures capable of explaining the reasons behind experts decisions is presented. A novel concept, the arguments are presented. They represent the experts have for maintaining a certain position in the debate. Several measures related to the arguments are proposed. These new argumentation measures, along with consensus measures, help us to get a clear idea about how and why a specific resolution has been reached. They help us to determine which is the most influential expert, that is, the expert whose contributions to the debate have inspired the rest. Also, the proposed method allows us to determine which are the arguments that most of the experts have followed. A clear overview about how the debate is evolving in terms of arguments is also provided. The novel presented analysis indicate how the experts change their opinions in every round and what was the reason for it, which changes have occurred between rounds and they also provide global analysis results.

The problem of deriving the priority vector from a pairwise comparison matrix is at the heart of multiple-criteria decision-making problems. Existing prioritization methods mostly model the inconsistency in relative preference–the ratio of two preference weights–by allowing for a small deviation, either additively or multiplicatively. In this study, we alternatively allow for a deviation in each of the two preference weights, which we refer to as the relative deviation interconnection. Under this framework, we consider both relative additive and multiplicative deviation cases and define two types of norms capturing the magnitudes of the deviations, which gives rise to four conic programming models for minimizing the norms of the deviations. Through the model structures, we analyze the signs of the deviations. This further allows us to establish the expressiveness of our framework, which covers the logarithmic least-squares method and the goal-programming method. Using numerical examples, we show that our models perform comparably against existing prioritization methods, efficiently identify unusual and false observations, and provide further suggestions for reducing inconsistency.

There has been significant research into reject inference, with several statistical methods and machine learning techniques having been employed to infer the possible repayment behavior of rejected credit applicants. This study proposes a novel three-stage reject inference learning framework using unsupervised transfer learning and three-way decision theory that integrates: (1) the rejected credit sample selection using three-way decision theory, (2) higher-level representations to transfer learning from both accepted and selected rejected credit samples; and (3) credit scoring using the reconstructed accepted credit samples. This method was found to both perform well for reject inference and handle negative transfer learning problems. The numerical results were validated on Chinese credit data, the results from which demonstrated the superiority of the proposed reject inference method for credit risk management applications.

In malicious URLs detection, traditional classifiers are challenged because the data volume is huge, patterns are changing over time, and the correlations among features are complicated. Feature engineering plays an important role in addressing these problems. To better represent the underlying problem and improve the performances of classifiers in identifying malicious URLs, this paper proposed a combination of linear and non-linear space transformation methods. For linear transformation, a two-stage distance metric learning approach was developed: first, singular value decomposition was performed to get an orthogonal space, and then a linear programming was used to solve an optimal distance metric. For nonlinear transformation, we introduced Nyström method for kernel approximation and used the revised distance metric for its radial basis function such that the merits of both linear and non-linear transformations can be utilized. 33,1622 URLs with 62 features were collected to validate the proposed feature engineering methods. The results showed that the proposed methods significantly improved the efficiency and performance of certain classifiers, such as k-Nearest Neighbor, Support Vector Machine, and neural networks. The malicious URLs’ identification rate of k-Nearest Neighbor was increased from 68% to 86%, the rate of linear Support Vector Machine was increased from 58% to 81%, and the rate of Multi-Layer Perceptron was increased from 63% to 82%. We also developed a website to demonstrate a malicious URLs detection system which uses the methods proposed in this paper. The system can be accessed at: http://url.jspfans.com.

Nowadays, datasets are always dynamic and patterns in them are changing. Instances with different labels are intertwined and often linearly inseparable, which bring new challenges to traditional learning algorithms. This paper proposes adaptive hyper-sphere (AdaHS), an adaptive incremental classifier, and its kernelized version: Nys-AdaHS. The classifier incorporates competitive training with a border zone. With adaptive hidden layer and tunable radii of hyper-spheres, AdaHS has strong capability of local learning like instance-based algorithms, but free from slow searching speed and excessive memory consumption. The experiments showed that AdaHS is robust, adaptive, and highly accurate. It is especially suitable for dynamic data in which patterns are changing, decision borders are complicated, and instances with the same label can be spherically clustered.

Internet is full of opinions that users provide about almost anything. These opinions are quite useful since they contain the knowledge of a high amount of people. Nevertheless, on their current state, they are disorganized and difficult to use. Therefore, there is a need of methods, like the one that we present, that take all this information and store it in an organized way. In this paper, a novel method that uses sentiment analysis procedures and fuzzy ontologies to organize opinion information obtained from the Web is presented. Sentiment analysis allows us to understand what people is feeling in their comments while fuzzy ontologies provide an organized way of storing and consulting the information.

Nowadays, in the social network–based decision-making processes, like the ones involved in e-commerce and e-democracy, multiple users with different backgrounds may take part and diverse alternatives might be involved. This diversity enriches the process, but at the same time, increases the uncertainty of opinions. This uncertainty can be considered from two different perspectives: (i) the uncertainty in the meaning of the words given as preferences, that is, motivated by the heterogeneity of the decision makers; and (ii) the uncertainty inherent to any decision-making process that may lead to an expert not being able to provide all their judgments. The main objective of this study is to address these two types of uncertainty. To do so, the following approaches are proposed: First, to capture, process, and keep the uncertainty in the meaning of the linguistic assumption, the Interval Type-2 Fuzzy Sets are introduced as a way to model the experts' linguistic judgments. Second, a measure of the coherence of the information provided by each decision maker is proposed. Finally, a consistency-based completion approach is introduced to deal with the uncertainty presented in the expert judgments. The proposed approach is tested in an e-democracy decision-making scenario.

On-line platforms foster the communication capabilities of the Internet to develop large-scale influence networks in which the quality of the interactions can be evaluated based on trust and reputation. So far, this technology is well known for building trust and harnessing cooperation in on-line marketplaces, such as Amazon (www.amazon.com) and eBay (www.ebay.es). However, these mechanisms are poised to have a broader impact on a wide range of scenarios, from large scale decision making procedures, such as the ones implied in e-democracy, to trust based recommendations on e-health context or influence and performance assessment in e-marketing and e-learning systems. This contribution surveys the progress in understanding the new possibilities and challenges that trust and reputation systems pose. To do so, it discusses trust, reputation and influence which are important measures in networked based communication mechanisms to support the worthiness of information, products, services opinions and recommendations. The existent mechanisms to estimate and propagate trust and reputation, in distributed networked scenarios, and how these measures can be integrated in decision making to reach consensus among the agents are analysed. Furthermore, it also provides an overview of the relevant work in opinion dynamics and influence assessment, as part of social networks. Finally, it identifies challenges and research opportunities on how the so called trust based network can be leveraged as an influence measure to foster decision making processes and recommendation mechanisms in complex social networks scenarios with uncertain knowledge, like the mentioned in e-health and e-marketing frameworks.

Social networks are the most preferred mean for the people to communicate. Therefore, it is quite usual that experts use them to carry out Group Decision Making processes. One disadvantage that recent Group Decision Making methods have is that they do not allow the experts to use free text to express themselves. On the contrary, they force them to follow a specific user–computer communication structure. This is against social network nature where experts are free to express themselves using their preferred text structure. This paper presents a novel model for experts to carry out Group Decision Making processes using free text and alternatives pairwise comparisons. The main advantage of this method is that it is designed to work using social networks. Sentiment analysis procedures are used to analyze free texts and extract the preferences that the experts provide about the alternatives. Also, our method introduces two ways of applying consensus measures over the Group Decision Making process. They can be used to determine if the experts agree among them or if there are different postures. This way, it is possible to promote the debate in those cases where consensus is low.

Different feedback mechanisms have been developed in large-scale group decision-making (GDM) to provide the decision-makers with advices for preference adjustment with the aim of improving the group consensus level. However, the willingness of the decision-makers to accept these advices is rarely considered in the extant feedback mechanisms. In the field of opinion dynamics, this issue is studied by the bounded confidence model, which shows that the decision-makers only consider the preferences that differ from their own preferences not more than a certain confidence level. Following this idea, this article proposes a large-scale consensus model with a bounded confidence-based feedback mechanism to promote the consensus level among decision-makers with bounded confidences. Specifically, this feedback mechanism classifies the decision-makers into different clusters and provides the corresponding clusters with more acceptable advices based on a bounded confidence-based optimization approach. Finally, through the numerical example and the simulation analysis, the use of the model is introduced, and the effectiveness of the model is justified.

When people express their opinions about a certain issue, they often give uncertain opinions rather than exact opinions. Particularly, these uncertain opinions will evolve in social networks. Therefore, in this paper, we focus on investigating uncertain opinion formation with social networks under bounded confidence. Specifically, we define the uncertain opinions by numerical interval opinions, whose ranges are between zero and one, and the larger width of numerical interval opinions means the more uncertainty of the opinions. Meanwhile, we describe social network structures by ER random graphs with different agents' scales and network connected probabilities. Then, we present the detailed simulation experiments to reveal the strong impact of social network structures on uncertain opinion formation. Simulation results show that: 1) larger agents' scales will yield the smaller ratios of agents expressing the uncertain opinions and larger average widths of uncertain opinions; 2) the average stable time starts increasing and then decreases with the increase in the network connected probabilities; and 3) larger network connected probabilities will yield less opinion clusters and the smaller ratios of the extremely small clusters in all clusters. The obtained results are helpful for the government and public opinion management departments to understand and manage uncertain public opinion evolution effectively.

The high amount of information that modern multi-criteria group decision making environments must handle requires the development of novel methods. These methods should be able to work with high amounts of alternatives while providing the experts a comfortable framework that they can use to carry out this complex decisions. In this paper, a novel method that tries to solve this issue is presented. Our method makes use of fuzzy ontologies in order to allow the experts to focus on what is more important: the weight that should be given to each criteria. This way, they do deal directly with the high amount of alternatives. Experts decide the importance of each criteria and the alternatives ranking is calculated automatically using the fuzzy ontology.

In this paper, from the perspective of opinion dynamics theory, we investigate the interaction mechanism of a group of autonomous agents in an e-commerce community (or social network), and the influence power of opinion leaders during the formation of group opinion. According to the opinion's update manner and influence, this paper divides social agents within a social network into two subgroups: opinion leaders and opinion followers. Then, we establish a new bounded confidence-based dynamic model for opinion leaders and followers to simulate the opinion evolution of the group of agents. Through numerical simulations, we further investigate the evolution mechanism of group opinion, and the relationship between the influence power of opinion leaders and three factors: the proportion of the opinion leader subgroups, the confidence levels of opinion followers, and the degrees of trust toward opinion leaders. The simulation results show that, in order to maximize the influence power in e-commerce, enhancing opinion leaders’ credibility is crucial.

In social network group decision making (SNGDM), the consensus reaching process (CRP) is used to help decision makers with social relationships reach consensus. Many CRP studies have been conducted in SNGDM until now. This paper provides a review of CRPs in SNGDM, and as a result it classifies them into two paradigms: (i) the CRP paradigm based on trust relationships, and (ii) the CRP paradigm based on opinion evolution. Furthermore, identified research challenges are put forward to advance this area of research.

This paper proposes a group decision-making (GDM) method for integrating heterogeneous information. To avoid information loss, instead of transforming heterogeneous information into a single form, the proposed method integrates heterogeneous information using a weighted-power average operator. The consensus degree between the individual-decision matrix and the group-decision matrix is then calculated based on the deviation degree. In addition, the feedback mechanism with the iterative algorithm is used to adjust the individual decision matrix, which does not reach the consensus. Furthermore, a ranking formula with heterogeneous technique for order preference by similarity to an ideal solution is adopted to select the best alternative. A numerical example of supplier selection is introduced to validate the proposed model and compare it with other similar GDM models. The results illustrate that the proposed method cannot only avoid information loss, but also effectively integrate heterogeneous information in heterogeneous GDM environment.

Identification of intrinsic characteristics and structure of high-dimensional data is an important task for financial analysis. This paper presents a kernel entropy manifold learning algorithm, which employs the information metric to measure the relationships between two financial data points and yields a reasonable low-dimensional representation of high-dimensional financial data. The proposed algorithm can also be used to describe the characteristics of a financial system by deriving the dynamical properties of the original data space. The experiment shows that the proposed algorithm cannot only improve the accuracy of financial early warning, but also provide objective criteria for explaining and predicting the stock market volatility.