Pairwise Model Research Articles

Joint group and pairwise localities embedding for feature extraction

Many practical applications generate high-dimensional data, which poses challenges in terms of computational time and storage. To address this issue, feature extraction has become a popular research topic. Learning by way of graph embedding is useful for discovering potential intrinsic low-dimensional structures and has thus gained wide attention. However, traditional embedding models typically utilize only one graph or one type of multiple graphs to capture local relationships, which may be insufficient for high-dimensional data that may exhibit different kinds of local relationships. To overcome this drawback, we developed a joint embedding framework that incorporates multiple types of graphs. Under this framework, a novel joint group and pairwise locality embedding model (GPE) is proposed. The GPE model has the following distinctive merits: (1) it simultaneously incorporates simple graphs, hypergraphs, and probabilistic hypergraphs, enabling the use of not only one type of multiple graphs but also multiple types of multiple graphs; (2) it can leverage both group relationships and pairwise graphs to discover local information during feature extraction; and (3) its objective function can be solved using an alternating optimization strategy, which involves solving eigenvalue problems and quadratic programming problems, resulting in very fast convergence. Finally, we arranged classification tasks and clustering tasks on several high-dimensional real-world datasets, and the experimental results prove that the identification capability of GPE is encouraging.

Microwave sintering of Ti(C,N)-based cermets: Study of the magnetic effect on metal phase

For microwave heating of Ti(C,N)-based cermets, this paper presents a microwave heating simulation study of pure Ti(C,N) ceramics and Ti(C,N)-based cermets using Comsol software. S-parameter inversion is employed to determine the equivalent relative permittivity of Ti(C,N)-based cermets with varying metal contents. The pairwise Ni metal plate model is utilized to investigate the law of mutual coupling voltage between metal plates. It was found that vigorous electric field intensity is generated around the metal particles of Ti(C,N)-based cermets, and high electric field intensity is generated between the metal particles. Model slice analysis and mechanism analysis are combined to reveal the following phenomena: (1)The surface of metal particles in Ti(C,N)-based cermets excites induced electromagnetic fields; (2)High mutual coupling voltages are generated between metal particles; (3)The reflection effect of metal particles on microwaves can increase the electric field intensity between metal particles. By statistically analyzing the temperature data of pure Ti(C,N) ceramics and Ti(C,N)-based cermets during the initial 30-min microwave sintering period, the temperature difference changing law can be concluded: (1)During the initial 30 min of microwave sintering, the temperature difference between the two gradually increased with time; (2)At 30 min, the temperature difference between the two reached 111 °C.

Friendship transmission and cooperation evolution in highly clustering interactions

“Friends of friends are friends, and enemies of friends are enemies” is a well-known friendship transmission effect. In interpersonal interactions, friendship transmission may prompt individuals to imitate one partner’s attitude toward another. Real human interactive networks often show a high degree of clustering and are filled with triangles. In this context, friendship-transmission-based imitation (FI) may be very frequent and play a crucial role in the flourishing of cooperation. Here, we develop an evolutionary pairwise game model and conduct simulations on small-world networks with the aim of revealing exactly how FI affects cooperation. Specifically, we add four forms of FI to a strategy update framework with interactive diversity, using two sets of parameters to control the frequency of each update method. The results show that the different FIs play very different roles. Two of them even conditionally outperform the targeted imitation with reciprocal features. Furthermore, appropriate coexistence of multiple FIs may catalyze more cooperation. This work captures potential factors influencing the evolution of cooperation in real human societies, and contributes to understanding the drivers and the barriers to human cooperation in highly clustering interactions.

The incomplete analytic hierarchy process and Bradley–Terry model: (In)consistency and information retrieval

Several methods of preference modeling, ranking, voting and multi-criteria decision-making include pairwise comparisons. It is usually simpler to compare two objects at a time, furthermore, some relations (e.g., the outcome of sports matches) are naturally known for pairs. This paper investigates and compares pairwise comparison models and the stochastic Bradley–Terry model. It is proved that they provide the same priority vectors for consistent (complete or incomplete) comparisons. For incomplete comparisons, all filling in levels are considered. Recent results identified the optimal subsets and sequences of multiplicative/additive/reciprocal pairwise comparisons for small sizes of items (up to n=6). Simulations of this paper show that the same subsets and sequences are optimal in the case of the Bradley–Terry and the Thurstone models as well. This somehow surprising coincidence suggests the existence of a more general result. Further models of information and preference theory are subject to future investigation to identify optimal subsets of input data.

An Efficient Transfer Learning Based Configuration Adviser for Database Tuning

In recent years, a wide spectrum of database tuning systems have emerged to automatically optimize database performance. However, these systems require a significant number of workload runs to deliver a satisfactory level of database performance, which is time-consuming and resource-intensive. While many attempts have been made to address this issue by using advanced search optimizers, empirical studies have shown that no single optimizer can dominate the rest across tuning tasks with different characteristics. Choosing an inferior optimizer may significantly increase the tuning cost. Unfortunately, current practices typically adopt a single optimizer or follow simple heuristics without considering the task characteristics. Consequently, they fail to choose the most suitable optimizer for a specific task. Furthermore, constructing a compact search space can significantly improve the tuning efficiency. However, current practices neglect the setting of the value range for each knob and rely on a large number of workload runs to select important knobs, resulting in a considerable amount of unnecessary exploration in ineffective regions. To pursue efficient database tuning, in this paper, we argue that it is imperative to have an approach that can judiciously determine a precise space and search optimizer for an arbitrary tuning task. To this end, we propose OpAdviser, which exploits the information learned from historical tuning tasks to guide the search space construction and search optimizer selection. Our design can greatly accelerate the tuning process and further reduce the required workload runs. Given a tuning task, OpAdviser learns the geometries of search space, including important knobs and their effective regions, from relevant previous tasks. It then constructs the target search space from the geometries according to the on-the-fly task similarity, which allows for adaptive adjustment of the target space. OpAdviser also employs a pairwise ranking model to capture the relationship from task characteristics to optimizer rankings. This ranking model is invoked during tuning and predicts the best optimizer to be used for the current iteration. We conduct extensive evaluations across a diverse set of workloads, where OpAdviser achieves 9.2% higher throughput and significantly reduces the number of workload runs with an average speedup of ~3.4x compared to state-of-the-art tuning systems.

A pairwise radiomics algorithm-lesion pair relation estimation model for distinguishing multiple primary lung cancer from intrapulmonary metastasis.

Distinguishing multiple primary lung cancer (MPLC) from intrapulmonary metastasis (IPM) is critical for their disparate treatment strategy and prognosis. This study aimed to establish a non-invasive model to make the differentiation pre-operatively. We retrospectively studied 168 patients with multiple lung cancers (307 pairs of lesions) including 118 cases for modeling and internal validation, and 50 cases for independent external validation. Radiomic features on computed tomography (CT) were extracted to calculate the absolute deviation of paired lesions. Features were then selected by correlation coefficients and random forest classifier 5-fold cross-validation, based on which the lesion pair relation estimation (PRE) model was developed. A major voting strategy was used to decide diagnosis for cases with multiple pairs of lesions. Cases from another institute were included as the external validation set for the PRE model to compete with two experienced clinicians. Seven radiomic features were selected for the PRE model construction. With major voting strategy, the mean area under receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity of the training versus internal validation versus external validation cohort to distinguish MPLC were 0.983 versus 0.844 versus 0.793, 0.942 versus 0.846 versus 0.760, 0.905 versus 0.728 versus 0.727, and 0.962 versus 0.910 versus 0.769, respectively. AUCs of the two clinicians were 0.619 and 0.580. The CT radiomic feature-based lesion PRE model is potentially an accurate diagnostic tool for the differentiation of MPLC and IPM, which could help with clinical decision making.

Assessment of Lymphovascular Invasion in Breast Cancer Using a Combined MRI Morphological Features, Radiomics, and Deep Learning Approach Based on Dynamic Contrast-Enhanced MRI.

Assessment of lymphovascular invasion (LVI) in breast cancer (BC) primarily relies on preoperative needle biopsy. There is an urgent need to develop a non-invasive assessment method. To develop an effective model to assess the LVI status in patients with BC using magnetic resonance imaging morphological features (MRI-MF), Radiomics, and deep learning (DL) approaches based on dynamic contrast-enhanced MRI (DCE-MRI). Cross-sectional retrospective cohort study. The study included 206 BC patients, with 136 in the training set [97 LVI(-) and 39 LVI(+) cases; median age: 51.5 years] and 70 in the test set [52 LVI(-) and 18 LVI(+) cases; median age: 48 years]. 1.5 T/T1-weighted images, fat-suppressed T2-weighted images, diffusion-weighted imaging (DWI), and DCE-MRI. The MRI-MF model was developed with conventional MR features using logistic analyses. The Radiomic feature extraction process involved collecting data from categorized DCE-MRI datasets, specifically the first and second post-contrast images (A1 and A2). Next, a DL model was implemented to determine LVI. Finally, we established a joint diagnosis model by combining the MRI-MF, Radiomics, and DL approaches. Diagnostic performance was compared using receiver operating characteristic curve analysis, confusion matrix, and decision curve analysis. Rim sign and peritumoral edema features were used to develop the MRI-MF model, while six Radiomics signature from the A1 and A2 images were used for the Radiomics model. The joint model (MRI-MF + Radiomics + DL models) achieved the highest accuracy (area under the curve [AUC] = 0.857), being significantly superior to the MRI-MF (AUC = 0.724), Radiomics (AUC = 0.736), or DL (AUC = 0.740) model. Furthermore, it also outperformed the pairwise combination models: Radiomics + MRI-MF (AUC = 0.796), DL + MRI-MF (AUC = 0.796), or DL + Radiomics (AUC = 0.826). The joint model incorporating MRI-MF, Radiomics, and DL approaches can effectively determine the LVI status in patients with BC before surgery. 4 TECHNICAL EFFICACY: Stage 2.

Pairwise Regression Weight Contrasts: Models for Allocating Psychological Resources

Researchers examine contrasts between analysis of variance (ANOVA) effects but seldom contrasts between regression coefficients even though such coefficients are an ANOVA generalization. Regression weight contrasts can be analyzed by reparameterizing the linear model. Two pairwise contrast models are developed for the study of qualitative differences among predictors. One leads to tests of null hypotheses that the regression weight for a reference predictor equals each of the other weights. The second involves ordered predictors and null hypotheses that the weight for a predictor equals that for the variables just above or below in the ordering. As illustration, qualitative differences in high school math course content are related to math achievement. The models facilitate the study of qualitative differences among predictors and the allocation of resources. They also readily generalize to moderated, hierarchical, and generalized linear forms.

Fragmentation from group interactions: A higher-order adaptive voter model

The adaptive voter model allows for studying the interplay between homophily, the tendency of like-minded individuals to attract each other, and social influence, the tendency for connected individuals to influence each other. However, it relies on graphs, and thus, it only considers pairwise interactions. We develop a minimal extension of the adaptive voter model to hypergraphs to study the interactions of groups of arbitrary sizes using a threshold parameter. We study S-uniform hypergraphs as initial configurations. With numerical simulations, we find new phenomena not found in the counterpart pairwise models, such as the formation of bands in the magnetization and the lack of an equilibrium state. Finally, we develop an analytical model using a sparse hypergraph approximation that accurately predicts the bands’ boundaries and height.

Inference for the Optimum Using Linear Regression Models with Discrete Inputs

We present a multiple-comparison-with-the-best procedure to provide inference for the optimum from regression models with discrete inputs. Two applications are given to illustrate the methodology: two-level factorial designs to identify the best drug combination and order-of-addition experiments where the primary objective is to identify the sequence with the largest mean response. The methods easily accommodate restrictions limiting the inference set of conditions. We use simulation to determine the critical values. While the methods apply to any linear regression model, we identify cases that require just a single critical value, and we also show where approximations and upper bounds mitigate the need for intensive computation. We tabulate the required critical values for a variety of common applications: the main-effect model and two-factor interaction model estimated by certain two-level factorial designs, and the pairwise order model and several component-position models for estimation based on optimal order-of-addition designs. Our work greatly simplifies the problem of rigorous inference for the optimum from regression models with discrete inputs.

Relative importance of speech and voice features in the classification of schizophrenia and depression

Speech is a promising biomarker for schizophrenia spectrum disorder (SSD) and major depressive disorder (MDD). This proof of principle study investigates previously studied speech acoustics in combination with a novel application of voice pathology features as objective and reproducible classifiers for depression, schizophrenia, and healthy controls (HC). Speech and voice features for classification were calculated from recordings of picture descriptions from 240 speech samples (20 participants with SSD, 20 with MDD, and 20 HC each with 4 samples). Binary classification support vector machine (SVM) models classified the disorder groups and HC. For each feature, the permutation feature importance was calculated, and the top 25% most important features were used to compare differences between the disorder groups and HC including correlations between the important features and symptom severity scores. Multiple kernels for SVM were tested and the pairwise models with the best performing kernel (3-degree polynomial) were highly accurate for each classification: 0.947 for HC vs. SSD, 0.920 for HC vs. MDD, and 0.932 for SSD vs. MDD. The relatively most important features were measures of articulation coordination, number of pauses per minute, and speech variability. There were moderate correlations between important features and positive symptoms for SSD. The important features suggest that speech characteristics relating to psychomotor slowing, alogia, and flat affect differ between HC, SSD, and MDD.

Improving AlphaFold2-based protein tertiary structure prediction with MULTICOM in CASP15

Since the 14th Critical Assessment of Techniques for Protein Structure Prediction (CASP14), AlphaFold2 has become the standard method for protein tertiary structure prediction. One remaining challenge is to further improve its prediction. We developed a new version of the MULTICOM system to sample diverse multiple sequence alignments (MSAs) and structural templates to improve the input for AlphaFold2 to generate structural models. The models are then ranked by both the pairwise model similarity and AlphaFold2 self-reported model quality score. The top ranked models are refined by a novel structure alignment-based refinement method powered by Foldseek. Moreover, for a monomer target that is a subunit of a protein assembly (complex), MULTICOM integrates tertiary and quaternary structure predictions to account for tertiary structural changes induced by protein-protein interaction. The system participated in the tertiary structure prediction in 2022 CASP15 experiment. Our server predictor MULTICOM_refine ranked 3rd among 47 CASP15 server predictors and our human predictor MULTICOM ranked 7th among all 132 human and server predictors. The average GDT-TS score and TM-score of the first structural models that MULTICOM_refine predicted for 94 CASP15 domains are ~0.80 and ~0.92, 9.6% and 8.2% higher than ~0.73 and 0.85 of the standard AlphaFold2 predictor respectively.

Priced risk in corporate bonds

Recent studies document strong empirical support for multifactor models that aim to explain the cross-sectional variation in corporate bond expected excess returns. We revisit these findings and provide evidence that common factor pricing in corporate bonds is exceedingly difficult to establish. Based on portfolio- and bond-level analyses, we demonstrate that previously proposed bond risk factors, with traded liquidity as the only marginal exception, do not have any incremental explanatory power over the corporate bond market factor. Consequently, this implies that the bond CAPM is not dominated by either traded- or nontraded-factor models in pairwise and multiple model comparison tests.

How to analyze continuous and discrete repeated measures in small-sample cross-over trials?

To optimize the use of data from a small number of subjects in rare disease trials, an at first sight advantageous design is the repeated measures cross-over design. However, it is unclear how these within-treatment period and within-subject clustered data are best analyzed in small-sample trials. In a real-data simulation study based upon a recent epidermolysis bullosa simplex trial using this design, we compare non-parametric marginal models, generalized pairwise comparison models, GEE-type models and parametric model averaging for both repeated binary and count data. The recommendation of which methodology to use in rare disease trials with a repeated measures cross-over design depends on the type of outcome and the number of time points the treatment has an effect on. The non-parametric marginal model testing the treatment-time-interaction effect is suitable for detecting between group differences in the shapes of the longitudinal profiles. For binary outcomes with the treatment effect on a single time point, the parametric model averaging method is recommended, while in the other cases the unmatched generalized pairwise comparison methodology is recommended. Both provide an easily interpretable effect size measure, and do not require exclusion of periods or subjects due toincompleteness.

Mixed modifier effect in Na2O·K2O·CaO aluminosilicate glasses: Pairwise and ternary interactions

AbstractThe mixed modifier effect (MME) is one of the most challenging puzzles in the field of oxide glasses, as there exists no universal quantitative theoretical model for accurately describing and predicting the nonlinear deviation of property values. In this paper, pairwise and ternary interactions are examined experimentally to understand the MME in a series of aluminosilicate glasses. By keeping the glass network former concentration constant and adjusting the molar ratios of three network modifiers (Na2O, K2O, and CaO), the MMEs in glass transition temperature (Tg), Vickers hardness (Hv), and activation energy (Ea) for aqueous dissolution for each modifier cation are investigated. We examine whether a pairwise interaction model is sufficient, or if ternary interactions also need to be included to predict the MME in these aluminosilicate glass systems. This work reveals that the pairwise model can be used to predict the MME for Tg in complex multiple‐modifier glass systems using only two‐body interaction factors. However, ternary mixed‐modifier interactions are present in other properties such as Hv and Ea.

Necessary and sufficient conditions for exact closures of epidemic equations on configuration model networks

We prove that it is possible to obtain the exact closure of SIR pairwise epidemic equations on a configuration model network if and only if the degree distribution follows a Poisson, binomial, or negative binomial distribution. The proof relies on establishing the equivalence, for these specific degree distributions, between the closed pairwise model and a dynamical survival analysis (DSA) model that was previously shown to be exact. Specifically, we demonstrate that the DSA model is equivalent to the well-known edge-based Volz model. Using this result, we also provide reductions of the closed pairwise and Volz models to a single equation that involves only susceptibles. This equation has a useful statistical interpretation in terms of times to infection. We provide some numerical examples to illustrate our results.

Δ-Learning applied to coarse-grained homogeneous liquids.

Coarse-grained molecular dynamics (CGMD) simulations address lengthscales and timescales that are critical to many chemical and material applications. Nevertheless, contemporary CGMD modeling is relatively bespoke and there are no black-box CGMD methodologies available that could play a comparable role in discovery applications that density functional theory plays for electronic structure. This gap might be filled by machine learning (ML)-based CGMD potentials that simplify model development, but these methods are still in their early stages and have yet to demonstrate a significant advantage over existing physics-based CGMD methods. Here, we explore the potential of Δ-learning models to leverage the advantages of these two approaches. This is implemented by using ML-based potentials to learn the difference between the target CGMD variable and the predictions of physics-based potentials. The Δ-models are benchmarked against the baseline models in reproducing on-target and off-target atomistic properties as a function of CG resolution, mapping operator, and system topology. The Δ-models outperform the reference ML-only CGMD models in nearly all scenarios. In several cases, the ML-only models manage to minimize training errors while still producing qualitatively incorrect dynamics, which is corrected by the Δ-models. Given their negligible added cost, Δ-models provide essentially free gains over their ML-only counterparts. Nevertheless, an unexpected finding is that neither the Δ-learning models nor the ML-only models significantly outperform the elementary pairwise models in reproducing atomistic properties. This fundamental failure is attributed to the relatively large irreducible force errors associated with coarse-graining that produces little benefit from using more complex potentials.

Comparative evidence of different surgical techniques for the management of vertical alveolar ridge defects in terms of complications and efficacy: A systematic review and network meta-analysis.

To systematically appraise the available evidence on vertical ridge augmentation (VRA) techniques and estimate a treatment-based ranking on the incidence of complications as well as their clinical effectiveness. Searches were conducted in six databases to identify randomized clinical trials comparing VRA techniques up to November 2022. The incidence of complications (primary) and of early, major, surgical and intra-operative complications, vertical bone gain (VBG), marginal bone loss, need for additional grafting, implant success/survival, and patient-reported outcome measures (secondary) were chosen as outcomes. Direct and indirect effects and treatment ranking were estimated using Bayesian pair-wise and network meta-analysis (NMA) models. Thirty-two trials (761 participants and 943 defects) were included. Five NMA models involving nine treatment groups were created: onlay, inlay, dense-polytetrafluoroethylene, expanded-polytetrafluoroethylene, titanium, resorbable membranes, distraction osteogenesis, tissue expansion and short implants. Compared with short implants, statistically significant higher odds ratios of healing complications were confirmed for all groups except those with resorbable membranes (odds ratio 5.4, 95% credible interval 0.92-29.14). The latter group, however, ranked last in clinical VBG. VRA techniques achieving greater VBG are also associated with higher incidence of healing complications. Guided bone regeneration techniques using non-resorbable membranes yield the most favourable results in relation to VBG and complications.

Mid-term clinical and echocardiographic results of the INSPIRIS RESILIA aortic valve: a retrospective comparison to the Magna Ease.

The INSPIRIS aortic valve combines the RESILIA proprietary tissue preservation process and an expandable stent frame to benefit future transcatheter valve-in-valve procedures. As the INSPIRIS valve became commercially available in 2017, mid-term outcome reports are scarce. We aimed to evaluate mid-term safety and echocardiographic performance of the INSPIRIS valve in comparison to its predecessor, the Carpentier Edwards Perimount Magna Ease (ME). This study was a retrospective single-centre study. Clinical results included early postoperative outcomes, mid-term mortality and readmission for cardiovascular cause or stroke. Echocardiographic follow-up (FU) was performed at discharge and 1-3, 6, 12 and 24 months. Clinical end point analyses were accomplished with a propensity score matching analysis and FU echocardiographic data comparisons using pairwise analyses and linear mixed-effect models. We included 953 patients who received an INSPIRIS (n = 488) or ME (n = 463) bioprosthesis between January 2018 and July 2021. In the matched population (n = 217 per group), no significant difference in short-term outcomes was observed, survival was similar at 30 months (INSPIRIS: 94% vs ME: 91%, P = 0.89), but freedom from readmission was higher in the INSPIRIS group (94% vs 86%, P = 0.014). INSPIRIS valves had a lower gradient at discharge (∼10 vs 14 mmHg, P < 0.001), 1-3 months (∼10 vs 12 mmHg, P < 0.001) and 24 months (∼11 vs 17 mmHg, P < 0.001) in paired analyses and significantly lower evolution of mean transvalvular gradients compared to ME. This study represents the largest comparative evaluation of the INSPIRIS to the ME valves, which demonstrated safe clinical outcomes and favourable haemodynamic performance at 2 years. Long-term FU is underway.

Dynamic surface chemistry and interparticle interactions mediating chemically fueled dissipative assembly of colloids

HypothesisDissipative assembly of colloids involves using a chemical fuel to temporarily activate organic colloid surface ligands to an assembly prone state. Colloids assemble into transient aggregates that disintegrate after the fuel is consumed. The underlying colloidal interactions controlling dissipative assembly have not been rigorously identified or quantified. We expect that fuel concentration dependent dissipative assembly behavior can be reconciled with measurements of dynamic colloid surface chemistry and colloidal interactions. ExperimentsCarbodiimide chemistry was utilized to induce dissipative assembly of carboxylic acid functionalized polystyrene colloids. We measured aggregation kinetics, colloid surface hydrophobicity, and zeta potential as a function of time, which established that colloids underwent dissipative assembly for fuel concentrations between 5 and 12.5 mM and irreversible aggregation at higher fuel concentrations due to transient changes in surface chemistry. FindingsWe formulated a pairwise colloidal interaction potential model including hydrophobic interactions quantified by fluorescence binding experiments. Fuel concentrations causing dissipative assembly displayed a transient increase in secondary minimum depth and a primary maximum much larger than the thermal potential. Fuel concentrations leading to irreversible aggregation displayed a primary maximum smaller than the thermal potential. This is the first study to quantify surface chemistry and interparticle interactions during dissipative colloid assembly and represents a foundational step in rationally designing more complex dissipative assembly systems.