Pairwise Structures Research Articles

Mathematical Limitations of Gravity Model in Constructing Regional Association Networks: A Case Study

This study evaluates the limitations of gravity models in constructing regional association networks, using China’s interprovincial economic connections as a case study. Comparison between a gravity-model-based simulated network and an actual network reveals significant topological differences. The gravity model overestimates the influence of larger, inward-oriented provinces and fails to accurately represent external connections. Attempts to refine the model with additional variables proved ineffective. Further theoretical analysis attributes these deficiencies to measurement bias from the model’s simplified binary perspective and information loss due to dimensional mismatch between pairwise predictions and complex network structures. These findings underscore the need for cautious application of gravity models and the development of more comprehensive analytical frameworks in regional network analysis.

Semi-supervised clustering guided by pairwise constraints and local density structures

Clustering based on local density peaks and graph cut (LDP-SC) is one of the state-of-the-art algorithms in unsupervised clustering, which first divides the data set to be multiple local trees, and then aggregates these local trees to obtain the final clustering result. However, for complex data sets, there might exist data points from different classes in the same local tree. In this article, we use pairwise constraint information to resolve this issue and propose a semi-supervised local density peaks and graph cut based clustering algorithm (SLDPC). In particular, SLDPC proposes intra-cluster conflict resolution and inter-cluster conflict resolution steps to split the local trees which are inconsistent with the provided pairwise constraint information. Theoretically, we show that the two steps will finish in a finite number of operations and the split local trees will be consistent with the pairwise constraint information. Subsequently, root node redirection and noise filtering steps are designed to avoid the local trees becoming too fragmented. Finally, we exploit the E2CP algorithm to further improve the similarity matrix between local trees using the pairwise constraint information, and the spectral clustering algorithm is adopted to obtain the clustering result. Experiments on multiple widely used synthetic and real-world data sets show that SLDPC is superior to LDP-SC and several other semi-supervised prominent clustering algorithms for most of the cases.

Low-rank persistent probability representation for higher-order role discovery

Role discovery is an emerging research area in the analysis of social networks, biological networks, and neural networks. The fundamental idea of role discovery is partitioning the vertices based on their structural features in a graph. However, most existing studies construct the role representations by learning the pairwise connectivity structures, thus weak to represent the relations among multiple vertices, namely higher-order structures. To this effect, this paper proposes a novel approach termed Low-Rank Persistent Probability representation (LRPP) for higher-order role discovery. In detail, we define local Dowker filtration to compute the persistent homology of the neighbor subgraph, which models the connection patterns among vertices and their neighbors. Then, we propose the Persistent Probability (PP) based on Dirichlet equivalence to vectorize the obtained features. Since the persistent probability matrix is sparse, we finally construct the low-rank representation to cluster the higher-order roles by embedding PP vectors into a series of linear subspaces. We conduct experiments of role discovery on both labeled and unlabeled datasets. The experimental results show that the proposed LRPP outperforms the baseline methods in role discovery and demonstrate that LRPP can effectively represent the higher-order role in graphs.

Multi-hazard joint probability distribution model for wind speed, wind direction and rain intensity

Multiple disasters such as strong wind and torrential rain pose great threats to civil infrastructures. However, most existing studies ignored the dependence structure between them, as well as the effect of wind direction. From the dimension of the engineering sector, this paper introduces the vine copula to model the joint probability distribution (JPD) of wind speed, wind direction and rain intensity based on the field data in Yangjiang, China during 1971–2020. First, the profiles of wind and rain in the studied area are statistically analyzed, and the original rainfall amounts are converted into short-term rain intensity. Then, the marginal distributions of individual variables and their pairwise dependence structures are built, followed by the development of the trivariate joint distribution model. The results show that the constructed vine copula-based model can well characterize the dependence structure between wind speed, wind direction and rain intensity. Meanwhile, the JPD characteristics of wind speed and rain intensity show significant variations depending on wind direction, thus the effect of wind direction cannot be neglected. The proposed JPD model will be conducive for reasonable and precise performance assessment of structures subjected to multiple hazards of wind and rain actions.

Classification and prediction for multi-cancer data with ultrahigh-dimensional gene expressions.

Analysis of gene expression data is an attractive topic in the field of bioinformatics, and a typical application is to classify and predict individuals’ diseases or tumors by treating gene expression values as predictors. A primary challenge of this study comes from ultrahigh-dimensionality, which makes that (i) many predictors in the dataset might be non-informative, (ii) pairwise dependence structures possibly exist among high-dimensional predictors, yielding the network structure. While many supervised learning methods have been developed, it is expected that the prediction performance would be affected if impacts of ultrahigh-dimensionality were not carefully addressed. In this paper, we propose a new statistical learning algorithm to deal with multi-classification subject to ultrahigh-dimensional gene expressions. In the proposed algorithm, we employ the model-free feature screening method to retain informative gene expression values from ultrahigh-dimensional data, and then construct predictive models with network structures of selected gene expression accommodated. Different from existing supervised learning methods that build predictive models based on entire dataset, our approach is able to identify informative predictors and dependence structures for gene expression. Throughout analysis of a real dataset, we find that the proposed algorithm gives precise classification as well as accurate prediction, and outperforms some commonly used supervised learning methods.

Measuring dynamical systems on directed hypergraphs.

Networks and graphs provide a simple but effective model to a vast set of systems in which building blocks interact throughout pairwise interactions. Unfortunately, such models fail to describe all those systems in which building blocks interact at a higher order. Higher-order graphs provide us the right tools for the task, but introduce a higher computing complexity due to the interaction order. In this paper we analyze the interplay between the structure of a directed hypergraph and a linear dynamical system, a random walk, defined on it. How can one extend network measures, such as centrality or modularity, to this framework? Instead of redefining network measures through the hypergraph framework, with the consequent complexity boost, we will measure the dynamical system associated to it. This approach let us apply known measures to pairwise structures, such as the transition matrix, and determine a family of measures that are amenable to such a procedure.

Arousal impacts distributed hubs modulating the integration of brain functional connectivity

Even when subjects are at rest, it is thought that brain activity is organized into distinct brain states during which reproducible patterns are observable. Yet, it is unclear how to define or distinguish different brain states. A potential source of brain state variation is arousal, which may play a role in modulating functional interactions between brain regions. Here, we use simultaneous resting state functional magnetic resonance imaging (fMRI) and pupillometry to study the impact of arousal levels indexed by pupil area on the integration of large-scale brain networks. We employ a novel sparse dictionary learning-based method to identify hub regions participating in between-network integration stratified by arousal, by measuring k-hubness, the number (k) of functionally overlapping networks in each brain region. We show evidence of a brain-wide decrease in between-network integration and inter-subject variability at low relative to high arousal, with differences emerging across regions of the frontoparietal, default mode, motor, limbic, and cerebellum networks. State-dependent changes in k-hubness relate to the actual patterns of network integration within these hubs, suggesting a brain state transition from high to low arousal characterized by global synchronization and reduced network overlaps. We demonstrate that arousal is not limited to specific brain areas known to be directly associated with arousal regulation, but instead has a brain-wide impact that involves high-level between-network communications. Lastly, we show a systematic change in pairwise fMRI signal correlation structures in the arousal state-stratified data, and demonstrate that the choice of global signal regression could result in different conclusions in conventional graph theoretical analysis and in the analysis of k-hubness when studying arousal modulations. Together, our results suggest the presence of global and local effects of pupil-linked arousal modulations on resting state brain functional connectivity.

Building Cross-Sectional Systematic Strategies by Learning to Rank

The success of a cross-sectional systematic strategy depends critically on accurately ranking assets before portfolio construction. Contemporary techniques perform this ranking step either with simple heuristics or by sorting outputs from standard regression or classification models, which have been demonstrated to be suboptimal for ranking in other domains (e.g., information retrieval). To address this deficiency, the authors propose a framework to enhance cross-sectional portfolios by incorporating learning-to-rank algorithms, which lead to improvements in ranking accuracy by learning pairwise and listwise structures across instruments. Using cross-sectional momentum as a demonstrative case study, the authors show that the use of modern machine learning ranking algorithms can substantially improve the trading performance of cross-sectional strategies—providing approximately threefold boosting of Sharpe ratios compared with traditional approaches. <b>TOPICS:</b>Big data/machine learning, portfolio construction, performance measurement <b>Key Findings</b> ▪ Contemporary approaches (e.g., simple heuristics) used to score and rank assets in portfolio construction are sub optimal as they do not learn the broader pairwise and listwise relationships across instruments. ▪ Learning to rank algorithms can be used to address this shortcoming, learning the broader links across assets, which consequently allow them to be ranked more accurately. ▪ Using Cross-sectional Momentum as a demonstrative use-case, we show that more precise rankings produce long/short portfolios that significantly outperform traditional approaches across various financial and ranking-based measures.

Adaptive Spectral Rotation via Joint Cluster and Pairwise Structure

Density structure and pairwise structure serve as two different but complementary perspectives for clustering. Either side of road is frequently visited and explored by multiple clustering methods. However, there are seldom approaches, which could mutually exploit both structures for clustering. To address this problem, in this paper, we develop a novel adaptive joint clustering algorithm, which combines unsupervised discrete orthogonal least squares discriminant analysis (DOLSDA) and discrete spectral clustering (DSC) with adaptive neighbors and side information into a unified model. Firstly, we extend supervised OLSDA to a discrete kernel clustering problem. To further achieve a clear pairwise structure, a new similarity with adaptive neighbors is then derived to establish sparse Laplacian matrix. In addition, side information could be incorporated to formulate clearer graph by modifying the proposed similarity. Based on the constructed graph, DSC is embedded with the discrete kernel OLSDA (DKOLSDA) clustering to exploit both cluster and pairwise data structures. Equipped with the proposed framework regarding quadratic weighted optimization, adaptive weight can be obtained automatically to leverage both unsupervised DKOLSDA and DSC. Since the unified problem is still discrete, we develop an increment scheme to achieve the optimal spectral rotation for the approximate solution to the predicted indicator.

Building Cross-Sectional Systematic Strategies By Learning to Rank

The success of a cross-sectional systematic strategy depends critically on accurately ranking assets prior to portfolio construction. Contemporary techniques perform this ranking step either with simple heuristics or by sorting outputs from standard regression or classification models, which have been demonstrated to be sub-optimal for ranking in other domains (e.g. information retrieval). To address this deficiency, we propose a framework to enhance cross-sectional portfolios by incorporating learning-to-rank algorithms, which lead to improvements of ranking accuracy by learning pairwise and listwise structures across instruments. Using cross-sectional momentum as a demonstrative case study, we show that the use of modern machine learning ranking algorithms can substantially improve the trading performance of cross-sectional strategies -- providing approximately threefold boosting of Sharpe Ratios compared to traditional approaches.

Learning Multiple Network Embeddings for Social Influence Prediction

Abstract How to effectively predict social influence is an essential issue in social network analysis. Almost all reported methods for social influence prediction are mainly concerned with estimating influence probabilities for each linking edge. However, all of this past work cannot accurately predict influence probabilities for all edges due to the problem of data sparsity. Unlike conventional approaches, this work focuses on exploring a cross problem for multiple network embeddings and social influence prediction. This study developed a new end-to-end approach, Multi-Influor, that learns multiple influence vectors for each user in social networks, instead of estimating influence probabilities for each edge. The multiple network embeddings consider multi-dimensional influence factors that incorporate pairwise node interactions, network structures, and global similarity comparisons. Moreover, this study solves the problem of influence evaluation caused by sparse observations. Extensive comparisons based on large-scale datasets indicate that the Multi-Influor approach outperforms several state-of-the-art baselines, and the experimental results demonstrate that the Multi-Influor approach is more practical on real-world social networks.

MADOKA: an ultra-fast approach for large-scale protein structure similarity searching

BackgroundProtein comparative analysis and similarity searches play essential roles in structural bioinformatics. A couple of algorithms for protein structure alignments have been developed in recent years. However, facing the rapid growth of protein structure data, improving overall comparison performance and running efficiency with massive sequences is still challenging.ResultsHere, we propose MADOKA, an ultra-fast approach for massive structural neighbor searching using a novel two-phase algorithm. Initially, we apply a fast alignment between pairwise structures. Then, we employ a score to select pairs with more similarity to carry out a more accurate fragment-based residue-level alignment. MADOKA performs about 6–100 times faster than existing methods, including TM-align and SAL, in massive alignments. Moreover, the quality of structural alignment of MADOKA is better than the existing algorithms in terms of TM-score and number of aligned residues. We also develop a web server to search structural neighbors in PDB database (About 360,000 protein chains in total), as well as additional features such as 3D structure alignment visualization. The MADOKA web server is freely available at: http://madoka.denglab.org/ConclusionsMADOKA is an efficient approach to search for protein structure similarity. In addition, we provide a parallel implementation of MADOKA which exploits massive power of multi-core CPUs.

Semantics-enhanced supervised deep autoencoder for depth image-based 3D model retrieval

Increased accuracy and affordability of depth sensors such as Kinect has created a great depth-data source for various 3D oriented applications. Specifically, 3D model retrieval is attracting attention in the field of computer vision and pattern recognition due to its numerous applications. A cross-domain retrieval approach such as depth image based 3D model retrieval has the challenges of occlusion, noise and view variability present in both query and training data. In this paper, we propose a new supervised deep autoencoder approach followed by semantic modeling to retrieve 3D shapes based on depth images. The key novelty is the two-fold feature abstraction to cope with the incompleteness and ambiguity present in the depth images. First, we develop a supervised autoencoder to extract robust features from both real depth images and synthetic ones rendered from 3D models, which are intended to balance reconstruction and classification capabilities of mix-domain data. Then semantic modeling of the supervised autoencoder features offers the next level of abstraction to cope with the incompleteness and ambiguity of the depth data. It is interesting that unlike any other pairwise model structures, we argue that cross-domain retrieval is still possible using only one single deep network trained on real and synthetic data. The experimental results on the NYUD2 and ModelNet10 datasets demonstrate that the proposed supervised method outperforms the recent approaches for cross-modal 3D model retrieval.

Classifying the Built-Up Structure of Urban Blocks with Probabilistic Graphical Models and TerraSAR-X Spotlight Imagery

Up-to-date maps of a city’s urban structure types (USTs) are very important for effective planning, as well as for different studies and applications. We present an approach for the classification of USTs at the level of urban blocks based on high-resolution spaceborne radar imagery. Images obtained at the satellite’s ascending and descending orbits were used for extracting line and polygon features from each block. Most of the attributes considered in the classification concern the geometry of these features, as well as their spatial disposition inside the blocks. Furthermore, assuming the UST classes of neighboring blocks are probabilistically dependent, we explored the framework of probabilistic graphical models and propose different context-based classification models. These models differ with respect to (i) their type, i.e., Markov or conditional random fields, (ii) their parameterization and (iii) the criterion applied for establishing pairwise neighboring relationships between blocks. In our experiments, 1,695 blocks from the city of Munich (Germany) and five representative UST classes were considered. A standard classification performed with the Random Forest algorithm achieved an overall accuracy of nearly 70%. All context-based classifications achieved overall accuracies up to 7% higher than that. The results indicate that denser pairwise block-neighborhood structures lead to better results and that the accuracy improvement is higher when the strength of the contextual influences is proportional to the similarity of the neighboring blocks attributes.

Experimental characterization of pairwise correlations from triple quantum correlated beams generated by cascaded four-wave mixing processes

We theoretically and experimentally characterize the performance of the pairwise correlations from triple quantum correlated beams based on the cascaded four-wave mixing (FWM) processes. The pairwise correlations between any two of the beams are theoretically calculated and experimentally measured. The experimental and theoretical results are in good agreement. We find that two of the three pairwise correlations can be in the quantum regime. The other pairwise correlation is always in the classical regime. In addition, we also measure the triple-beam correlation which is always in the quantum regime. Such unbalanced and controllable pairwise correlation structures may be taken as advantages in practical quantum communications, for example, hierarchical quantum secret sharing. Our results also open the way for the classification and application of quantum states generated from the cascaded FWM processes.

Exotic Holomorphic Engel Structures on $$\mathbf {C}^4$$ C 4

A holomorphic Engel structure determines a flag of distributions $$\mathcal {W}\subset \mathcal {D}\subset {\mathcal {E}}$$ . We construct examples of Engel structures on $$\mathbf {C}^4$$ such that each of these distributions is hyperbolic in the sense that it has no tangent copies of $$\mathbf {C}$$ . We also construct two infinite families of pairwise non-isomorphic Engel structures on $$\mathbf {C}^4$$ by controlling the curves $$f{:}\mathbf {C}\rightarrow \mathbf {C}^4$$ tangent to $$\mathcal {W}$$ . The first is characterised by the topology of the set of points in $$\mathbf {C}^4$$ admitting $$\mathcal {W}$$ -lines and the second by a finer geometric property of this set. A consequence of the second construction is the existence of uncountably many non-isomorphic holomorphic Engel structures on $$\mathbf {C}^4$$ .

Hedging Oil and Market Price Risk for U.S. Oil and Gas Industry Investors after Using Copulas to Model Dependencies

Using copulas, we investigate the pairwise dependence structures between two risk factors, oil price and aggregate market index price, and the US oil and gas sub-sector indices. We also explore the out-of-sample hedging performance of a hedging strategy by minimizing the conditional Value-at-Risk of the hedged portfolios composed with sub-sector index and futures contract after estimating the time-varying parameters of copulas. We compare the hedging effectiveness of this strategy with the hedging strategy for minimizing the volatility of hedged portfolios using five hedging performance measures. Our results suggest that Integrated oil & gas and Pipelines sub-sectors have lower tail depen- dence coefficients with oil price and market index price compared with the other two sub-sectors. However, the results of the out-of-sample investigation suggests that the hedging strategy with using copulas and conditional Value-at-Risk underperforms in risk reduction compared with the hedging strategy with Ordinary Least Squares and volatility.

RNA-TVcurve: a Web server for RNA secondary structure comparison based on a multi-scale similarity of its triple vector curve representation

BackgroundRNAs have been found to carry diverse functionalities in nature. Inferring the similarity between two given RNAs is a fundamental step to understand and interpret their functional relationship. The majority of functional RNAs show conserved secondary structures, rather than sequence conservation. Those algorithms relying on sequence-based features usually have limitations in their prediction performance. Hence, integrating RNA structure features is very critical for RNA analysis. Existing algorithms mainly fall into two categories: alignment-based and alignment-free. The alignment-free algorithms of RNA comparison usually have lower time complexity than alignment-based algorithms.ResultsAn alignment-free RNA comparison algorithm was proposed, in which novel numerical representations RNA-TVcurve (triple vector curve representation) of RNA sequence and corresponding secondary structure features are provided. Then a multi-scale similarity score of two given RNAs was designed based on wavelet decomposition of their numerical representation. In support of RNA mutation and phylogenetic analysis, a web server (RNA-TVcurve) was designed based on this alignment-free RNA comparison algorithm. It provides three functional modules: 1) visualization of numerical representation of RNA secondary structure; 2) detection of single-point mutation based on secondary structure; and 3) comparison of pairwise and multiple RNA secondary structures. The inputs of the web server require RNA primary sequences, while corresponding secondary structures are optional. For the primary sequences alone, the web server can compute the secondary structures using free energy minimization algorithm in terms of RNAfold tool from Vienna RNA package.ConclusionRNA-TVcurve is the first integrated web server, based on an alignment-free method, to deliver a suite of RNA analysis functions, including visualization, mutation analysis and multiple RNAs structure comparison. The comparison results with two popular RNA comparison tools, RNApdist and RNAdistance, showcased that RNA-TVcurve can efficiently capture subtle relationships among RNAs for mutation detection and non-coding RNA classification. All the relevant results were shown in an intuitive graphical manner, and can be freely downloaded from this server. RNA-TVcurve, along with test examples and detailed documents, are available at: http://ml.jlu.edu.cn/tvcurve/.

Calix(4)arene sulfonic acid complexes with halogenated acetic acids

Effective proton conductors based on calix(4)arene sulfonic acid and CX3COOH (where X=H, F, Cl) with molar ratio 1:1 were obtained in crystalline form. It was demonstrated that the original calixarene sulfonic acid and its complex with CCl3COOH, and complexes with CH3COOH and CF3COOH have pairwise similar structures and similar proton transport patterns.

Modelling tourist flow association for tourism demand forecasting

The purpose of this study is to examine tourism demand for Singapore from 1995 to 2013 by six major origin countries which belong to three different regions. Unlike prior tourism research, we take into account the dependence relations among the different tourist flows via copula. Copula is a statistical model of dependence and measurement of association. Specifically, we investigate the association between two tourist flows in each region. Based on empirical copula estimation, the Frank function has been identified as the most appropriate to capture the pairwise dependence structures of tourist flows. The copula-based approach combined with econometric models is proposed for tourism demand analysis that can be used to predict tourist arrivals. We apply the copula-ARDL and copula-ECM frameworks to generate joint forecasts of tourist arrivals from three regions. The findings show that the forecast performance of the Frank copula-based model outperforms the benchmark model which corresponds to the independence structure (no association) of tourist flows.