Pairwise Relationships Research Articles

DHM-Net: Deep Hypergraph Modeling for Robust Feature Matching.

We present a novel deep hypergraph modeling architecture (called DHM-Net) for feature matching in this paper. Our network focuses on learning reliable correspondences between two sets of initial feature points by establishing a dynamic hypergraph structure that models group-wise relationships and assigns weights to each node. Compared to existing feature matching methods that only consider pair-wise relationships via a simple graph, our dynamic hypergraph is capable of modeling nonlinear higher-order group-wise relationships among correspondences in an interaction capturing and attention representation learning fashion. Specifically, we propose a novel Deep Hypergraph Modeling block, which initializes an overall hypergraph by utilizing neighbor information, and then adopts node-to-hyperedge and hyperedge-to-node strategies to propagate interaction information among correspondences while assigning weights based on hypergraph attention. In addition, we propose a Differentiation Correspondence-Aware Attention mechanism to optimize the hypergraph for promoting representation learning. The proposed mechanism is able to effectively locate the exact position of the object of importance via the correspondence aware encoding and simple feature gating mechanism to distinguish candidates of inliers. In short, we learn such a dynamic hypergraph format that embeds deep group-wise interactions to explicitly infer categories of correspondences. To demonstrate the effectiveness of DHM-Net, we perform extensive experiments on both real-world outdoor and indoor datasets. Particularly, experimental results show that DHM-Net surpasses the state-of-the-art method by a sizable margin. Our approach obtains an 11.65% improvement under error threshold of 5° for relative pose estimation task on YFCC100M dataset. Code will be released at https://github.com/CSX777/DHM-Net.

Bayesian graph convolutional network with partial observations.

As a widely studied model in the machine learning and data processing society, graph convolutional network reveals its advantage in non-grid data processing. However, existing graph convolutional networks generally assume that the node features can be fully observed. This may violate the fact that many real applications come with only the pairwise relationships and the corresponding node features are unavailable. In this paper, a novel graph convolutional network model based on Bayesian framework is proposed to handle the graph node classification task without relying on node features. First, we equip the graph node with the pseudo-features generated from the stochastic process. Then, a hidden space structure preservation term is proposed and embedded into the generation process to maintain the independent and identically distributed property between the training and testing dataset. Although the model inference is challenging, we derive an efficient training and predication algorithm using variational inference. Experiments on different datasets demonstrate the proposed graph convolutional networks can significantly outperform traditional methods, achieving an average performance improvement of 9%.

Tensor Learning Meets Dynamic Anchor Learning: From Complete to Incomplete Multiview Clustering.

Multiview clustering (MVC), which can dexterously uncover the underlying intrinsic clustering structures of the data, has been particularly attractive in recent years. However, previous methods are designed for either complete or incomplete multiview only, without a unified framework that handles both tasks simultaneously. To address this issue, we propose a unified framework to efficiently tackle both tasks in approximately linear complexity, which integrates tensor learning to explore the inter-view low-rankness and dynamic anchor learning to explore the intra-view low-rankness for scalable clustering (TDASC). Specifically, TDASC efficiently learns smaller view-specific graphs by anchor learning, which not only explores the diversity embedded in multiview data, but also yields approximately linear complexity. Meanwhile, unlike most current approaches that only focus on pair-wise relationships, the proposed TDASC incorporates multiple graphs into an inter-view low-rank tensor, which elegantly models the high-order correlations across views and further guides the anchor learning. Extensive experiments on both complete and incomplete multiview datasets clearly demonstrate the effectiveness and efficiency of TDASC compared with several state-of-the-art techniques.

Adaptive Feature Learning for Unbiased Scene Graph Generation.

Scene Graph Generation (SGG) aims to detect all objects and identify their pairwise relationships in the scene. Recently, tremendous progress has been made in exploring better context relationship representations. Previous work mainly focuses on contextual information aggregation and uses de-biasing strategies on samples to eliminate the preference for head predicates. However, there remain challenges caused by indeterminate feature training. Overlooking the label confusion problem in feature training easily results in a messy feature distribution among the confused categories, thereby affecting the prediction of predicates. To alleviate the aforementioned problem, in this paper, we focus on enhancing predicate representation learning. Firstly, we propose a novel Adaptive Message Passing (AMP) network to dynamically conduct information propagation among neighbors. AMP provides discriminating representations for neighbor nodes under the view of de-noising and adaptive aggregation. Furthermore, we construct a feature-assisted training paradigm alongside the predicate classification branch, guiding predicate feature learning to the corresponding feature space. Moreover, to alleviate biased prediction caused by the long-tailed class distribution and the interference of confused labels, we design a Bi-level Curriculum learning scheme (BiC). The BiC separately considers the training from the feature learning and de-biasing levels, preserving discriminating representations of different predicates while resisting biased predictions. Results on multiple SGG datasets show that our proposed method AMP-BiC has superior comprehensive performance, demonstrating its effectiveness.

Deep Supervised Multi-View Learning with Graph Priors.

This paper presents a novel method for supervised multi-view representation learning, which projects multiple views into a latent common space while preserving the discrimination and intrinsic structure of each view. Specifically, an apriori discriminant similarity graph is first constructed based on labels and pairwise relationships of multi-view inputs. Then, view-specific networks progressively map inputs to common representations whose affinity approximates the constructed graph. To achieve graph consistency, discrimination, and cross-view invariance, the similarity graph is enforced to meet the following constraints: 1) pairwise relationship should be consistent between the input space and common space for each view; 2) within-class similarity is larger than any between-class similarity for each view; 3) the inter-view samples from the same (or different) classes are mutually similar (or dissimilar). Consequently, the intrinsic structure and discrimination are preserved in the latent common space using an apriori approximation schema. Moreover, we present a sampling strategy to approach a sub-graph sampled from the whole similarity structure instead of approximating the graph of the whole dataset explicitly, thus benefiting lower space complexity and the capability of handling large-scale multi-view datasets. Extensive experiments show the promising performance of our method on five datasets by comparing it with 18 state-of-the-art methods.

Adaptive Neural Message Passing for Inductive Learning on Hypergraphs.

Graphs are the most ubiquitous data structures for representing relational datasets and performing inferences in them. They model, however, only pairwise relations between nodes and are not designed for encoding the higher-order relations. This drawback is mitigated by hypergraphs, in which an edge can connect an arbitrary number of nodes. Most hypergraph learning approaches convert the hypergraph structure to that of a graph and then deploy existing geometric deep learning methods. This transformation leads to information loss, and sub-optimal exploitation of the hypergraph's expressive power. We present HyperMSG, a novel hypergraph learning framework that uses a modular two-level neural message passing strategy to accurately and efficiently propagate information within each hyperedge and across the hyperedges. HyperMSG adapts to the data and task by learning an attention weight associated with each node's degree centrality. Such a mechanism quantifies both local and global importance of a node, capturing the structural properties of a hypergraph. HyperMSG is inductive, allowing inference on previously unseen nodes. Further, it is robust and outperforms state-of-the-art hypergraph learning methods on a wide range of tasks and datasets. Finally, we demonstrate the effectiveness of HyperMSG in learning multimodal relations through detailed experimentation on a challenging multimedia dataset.

Label Semantic Knowledge Distillation for Unbiased Scene Graph Generation

The Scene Graph Generation (SGG) task aims to detect all the objects and their pairwise visual relationships in a given image. Although SGG has achieved remarkable progress over the last few years, almost all existing SGG models follow the same training paradigm: they treat both object and predicate classification in SGG as a single-label classification problem, and the ground-truths are one-hot target labels. However, this prevalent training paradigm has overlooked two characteristics of current SGG datasets: 1) For positive samples, some specific subject-object instances may have multiple reasonable predicates. 2) For negative samples, there are numerous missing annotations. Regardless of the two characteristics, SGG models are easy to be confused and make wrong predictions. To this end, we propose a novel model-agnostic Label Semantic Knowledge Distillation (LS-KD) for unbiased SGG. Specifically, LS-KD dynamically generates a “soft" label for each subject-object instance by fusing a predicted Label Semantic Distribution (LSD) with its original one-hot target label. LSD reflects the correlations between this instance and multiple predicate categories. Meanwhile, we propose two different strategies to predict LSD: iterative self-KD and synchronous self-KD. Extensive ablations and results on three SGG tasks have attested to the superiority and generality of our proposed LS-KD, which can consistently achieve decent trade-off performance between different predicate categories.

GenURL: A General Framework for Unsupervised Representation Learning.

Unsupervised representation learning (URL) that learns compact embeddings of high-dimensional data without supervision has achieved remarkable progress recently. However, the development of URLs for different requirements is independent, which limits the generalization of the algorithms, especially prohibitive as the number of tasks grows. For example, dimension reduction (DR) methods, t-SNE and UMAP, optimize pairwise data relationships by preserving the global geometric structure, while self-supervised learning, SimCLR and BYOL, focuses on mining the local statistics of instances under specific augmentations. To address this dilemma, we summarize and propose a unified similarity-based URL framework, GenURL, which can adapt to various URL tasks smoothly. In this article, we regard URL tasks as different implicit constraints on the data geometric structure that help to seek optimal low-dimensional representations that boil down to data structural modeling (DSM) and low-dimensional transformation (LDT). Specifically, DSM provides a structure-based submodule to describe the global structures, and LDT learns compact low-dimensional embeddings with given pretext tasks. Moreover, an objective function, general Kullback-Leibler (GKL) divergence, is proposed to connect DSM and LDT naturally. Comprehensive experiments demonstrate that GenURL achieves consistent state-of-the-art performance in self-supervised visual learning, unsupervised knowledge distillation (KD), graph embeddings (GEs), and DR.

Three-Stage Semisupervised Cross-Modal Hashing With Pairwise Relations Exploitation.

Hashing methods have sparked a great revolution in cross-modal retrieval due to the low cost of storage and computation. Benefiting from the sufficient semantic information of labeled data, supervised hashing methods have shown better performance compared with unsupervised ones. Nevertheless, it is expensive and labor intensive to annotate the training samples, which restricts the feasibility of supervised methods in real applications. To deal with this limitation, a novel semisupervised hashing method, i.e., three-stage semisupervised hashing (TS3H) is proposed in this article, where both labeled and unlabeled data are seamlessly handled. Different from other semisupervised approaches that learn the pseudolabels, hash codes, and hash functions simultaneously, the new approach is decomposed into three stages as the name implies, in which all of the stages are conducted individually to make the optimization cost-effective and precise. Specifically, the classifiers of different modalities are learned via the provided supervised information to predict the labels of unlabeled data at first. Then, hash code learning is achieved with a simple but efficient scheme by unifying the provided and the newly predicted labels. To capture the discriminative information and preserve the semantic similarities, we leverage pairwise relations to supervise both classifier learning and hash code learning. Finally, the modality-specific hash functions are obtained by transforming the training samples to the generated hash codes. The new approach is compared with the state-of-the-art shallow and deep cross-modal hashing (DCMH) methods on several widely used benchmark databases, and the experiment results verify its efficiency and superiority.

STATISTICAL VALIDATION OF TRIPLE COLOCALIZATION ANALYSIS

Background: in the last decades, colocalization analysis of fluorescently tagged biomolecules has proven to be a powerful approach to studying functional relationships between these biomolecules. However, in many cases, to give this analysis a biological meaning, colocalization coefficients must be tested statistically, comparing them with the colocalization expected by chance. Aim: It addressed the statistical significance of triple colocalization to distinguish real triple colocalization and classify different triple signal scenarios. Methods: we use biological and generated images of triple signal scenarios to contrast seven independent statistical facts with independent statistical tests. Three of these tests correspond to pairwise relationships (double scrambling tests), and the others correspond to triple relationships: single scrambling tests (red, green, and blue scrambling) and the triple scrambling test. The analysis and methodology proposed can be reproduced using the application developed in our laboratory. Results: In the study approach, we found true triple relationships ignored by using traditional methods of computing the statistical significance, while we could reinterpret cases of not significant triple colocalization wrongly considered as significant by traditional methods. Discussion: single scrambling tests can reveal significant triple colocalization for low levels of triple co-occurrence, even when all pairwise relationships were exclusion relationships. Moreover, on the other hand, single scrambling tests can reveal the absence of a significant triple colocalization for high levels of triple co-occurrence, even when all pairwise relationships were significant colocalization. Conclusion: all scrambling tests are useful to classify a specific scenario of a triple relationship. Dynamics like mitosis can be distinguished into their phases by triple signal relationships using these 7 independent statistical tests.

H3GNN: Hybrid Hierarchical HyperGraph Neural Network for Personalized Session-based Recommendation

Personalized Session-based recommendation (PSBR) is a general and challenging task in the real world, aiming to recommend a session’s next clicked item based on the session’s item transition information and the corresponding user’s historical sessions. A session is defined as a sequence of interacted items during a short period. The PSBR problem has a natural hierarchical architecture in which each session consists of a series of items, and each user owns a series of sessions. However, the existing PSBR methods can merely capture the pairwise relation information within items and users. To effectively capture the hierarchical information, we propose a novel hierarchical hypergraph neural network to model the hierarchical architecture. Moreover, considering that the items in sessions are sequentially ordered, while the hypergraph can only model the set relation, we propose a directed graph aggregator (DGA) to aggregate the sequential information from the directed global item graph. By attentively combining the embeddings of the above two modules, we propose a framework dubbed H3GNN (Hybrid Hierarchical HyperGraph Neural Network). Extensive experiments on three benchmark datasets demonstrate the superiority of our proposed model compared to the state-of-the-art methods, and ablation experiment results validate the effectiveness of all the proposed components.

Лінійний регресійний аналіз впливу біоелементів на частоту гострих респіраторних інфекцій у дітей дошкільного віку

Purpose - to identify the bioelements having the most significant impact on the susceptibility of preschool children to frequent episodes of acute respiratory infections (ARI). Materials and methods. A total of 30 children (14 boys and 16 girls) aged 1-6 years, undergoing inpatient treatment on ARI, were involved in the clinical study. Two integral indicators of acute respiratory infections recurrence, i.e. the infection index and the resistance index, were taken into account for each patient. The children were tested by X-ray fluorescence analysis of 17 bioelements in their hair - Zn, Fe, Cu, Se, Mn, Cr, Co, Br, Ni, Rb, Sr, Sn, Pb, Ca, K, S, and Cl. The statistical processing of the obtained digital material was performed with IBM SPSS Statistics 28 licensed software. A linear regression analysis with stepwise involvement of predictors was applied. Results. In preschool children, there is a moderate negative correlation between hair Rb content and the calculated resistance index (ρ=-0.405; p=0.026; 95% CI: (-0.674)-(-0.042)), according to which lower concentrations of this bioelement are associated with more frequent episodes of ARI. Additionally, Rb has a statistically significant pairwise relationship with several other bioelements studied and the ratios between them. Rb was demonstrated to be directly and most closely correlated with K (ρ=0.842; p<0.001; 95% CI: 0.678-0.926). A prognostic model of the resistance index was obtained, using the linear regression analysis of independent factors. The formula of the prognostic model included only one of the factors studied - the ratio of Mn/Cr content in hair. The informativeness of the mentioned model was 24.9%, which is a quite significant value, taking into consideration a broad range of known predictors for recurrent respiratory infections. Conclusions. The findings are complementary to the available scientific data on the participation of the bioelements in providing resistance to frequent ARI in preschool children. It is planned to continue examining the status of particular bioelements in combination with other potential predictors of recurrent respiratory infections. The study was conducted in accordance with the principles of the Declaration of Helsinki. The study protocol was approved by the local ethics committees of the institutions mentioned in the paper. An informed parental consent was obtained for the study in children. No conflict of interests was declared by the authors.

A simplicial epidemic model for COVID-19 spread analysis.

Networks allow us to describe a wide range of interaction phenomena that occur in complex systems arising in such diverse fields of knowledge as neuroscience, engineering, ecology, finance, and social sciences. Until very recently, the primary focus of network models and tools has been on describing the pairwise relationships between system entities. However, increasingly more studies indicate that polyadic or higher-order group relationships among multiple network entities may be the key toward better understanding of the intrinsic mechanisms behind the functionality of complex systems. Such group interactions can be, in turn, described in a holistic manner by simplicial complexes of graphs. Inspired by these recently emerging results on the utility of the simplicial geometry of complex networks for contagion propagation and armed with a large-scale synthetic social contact network (also known as a digital twin) of the population in the U.S. state of Virginia, in this paper, we aim to glean insights into the role of higher-order social interactions and the associated varying social group determinants on COVID-19 propagation and mitigation measures.

Unsupervised Feature Selection with Latent Relationship Penalty Term

With the exponential growth of high dimensional unlabeled data, unsupervised feature selection (UFS) has attracted considerable attention due to its excellent performance in machine learning. Existing UFS methods implicitly assigned the same attribute score to each sample, which disregarded the distinctiveness of features and weakened the clustering performance of UFS methods to some extent. To alleviate these issues, a novel UFS method is proposed, named unsupervised feature selection with latent relationship penalty term (LRPFS). Firstly, latent learning is innovatively designed by assigning explicitly an attribute score to each sample according to its unique importance in clustering results. With this strategy, the inevitable noise interference can be removed effectively while retaining the intrinsic structure of data samples. Secondly, an appropriate sparse model is incorporated into the penalty term to further optimize its roles as follows: (1) It imposes potential constraints on the feature matrix to guarantee the uniqueness of the solution. (2) The interconnection between data instances is established by a pairwise relationship situation. Extensive experiments on benchmark datasets demonstrate that the proposed method is superior to relevant state-of-the-art algorithms with an average improvement of 10.17% in terms of accuracy.

Deep semi-supervised clustering based on pairwise constraints and sample similarity

Semi-supervised clustering methods enhance the performance of completely unsupervised clustering tasks by incorporating pairwise relationship information from a subset of samples. However, previous methods based on pairwise constraints have struggled to effectively leverage available prior knowledge and fully exploit the similarity relationships between samples. To address these issues, this paper proposes an advanced approach called Deep Semi-Supervised Clustering based on Pairwise Constraints and Sample Similarity (DSCPS). Specifically, DSCPS consists of two training stages: the coarse clustering stage and the fine clustering stage. In the coarse clustering stage, DSCPS assigns probabilities to each sample indicating its belongingness to each cluster by computing the distance to the cluster centers. In the fine clustering stage, DSCPS introduces a predictor network in the clustering space to predict the class labels of each sample. Simultaneously, the thresholds for similarity and dissimilarity between samples are determined based on pairwise constraints. Finally, the encoder and prediction network are further optimized using sample similarity relationships and pairwise constraints as loss conditions, resulting in the final clustering results. Extensive experiments demonstrate that DSCPS outperforms state-of-the-art methods, achieving the highest performance.

Machine learning–driven self-discovery of the robot body morphology

The morphology of a robot is typically assumed to be known, and data from external measuring devices are used mainly for its kinematic calibration. In contrast, we take an agent-centric perspective and ponder the vaguely explored question of whether a robot could learn elements of its morphology by itself, relying on minimal prior knowledge and depending only on unorganized proprioceptive signals. To answer this question, we propose a mutual information–based representation of the relationships between the proprioceptive signals of a robot, which we call proprioceptive information graphs (π-graphs). Leveraging the fact that the information structure of the sensorimotor apparatus is dependent on the embodiment of the robot, we use the π-graph to look for pairwise signal relationships that reflect the underlying kinematic first-order principles applicable to the robot’s structure. In our discussion, we show that analysis of the π-graph leads to the inference of two fundamental elements of the robot morphology: its mechanical topology and corresponding kinematic description, that is, the location and orientation of the robot’s joints. Results from a robot manipulator, a hexapod, and a humanoid robot show that the correct topology and kinematic description can be effectively inferred from their π-graph either offline or online, regardless of the number of links and body configuration.

NeuSyRE: Neuro-symbolic visual understanding and reasoning framework based on scene graph enrichment

Exploring the potential of neuro-symbolic hybrid approaches offers promising avenues for seamless high-level understanding and reasoning about visual scenes. Scene Graph Generation (SGG) is a symbolic image representation approach based on deep neural networks (DNN) that involves predicting objects, their attributes, and pairwise visual relationships in images to create scene graphs, which are utilized in downstream visual reasoning. The crowdsourced training datasets used in SGG are highly imbalanced, which results in biased SGG results. The vast number of possible triplets makes it challenging to collect sufficient training samples for every visual concept or relationship. To address these challenges, we propose augmenting the typical data-driven SGG approach with common sense knowledge to enhance the expressiveness and autonomy of visual understanding and reasoning. We present a loosely-coupled neuro-symbolic visual understanding and reasoning framework that employs a DNN-based pipeline for object detection and multi-modal pairwise relationship prediction for scene graph generation and leverages common sense knowledge in heterogenous knowledge graphs to enrich scene graphs for improved downstream reasoning. A comprehensive evaluation is performed on multiple standard datasets, including Visual Genome and Microsoft COCO, in which the proposed approach outperformed the state-of-the-art SGG methods in terms of relationship recall scores, i.e. Recall@K and mean Recall@K, as well as the state-of-the-art scene graph-based image captioning methods in terms of SPICE and CIDEr scores with comparable BLEU, ROGUE and METEOR scores. As a result of enrichment, the qualitative results showed improved expressiveness of scene graphs, resulting in more intuitive and meaningful caption generation using scene graphs. Our results validate the effectiveness of enriching scene graphs with common sense knowledge using heterogeneous knowledge graphs. This work provides a baseline for future research in knowledge-enhanced visual understanding and reasoning. The source code is available at https://github.com/jaleedkhan/neusire.

Side-constrained graph fusion for semi-supervised multi-view clustering

In these years, semi-supervised learning arouses ongoing attentions due to its appealing avail and economic expenditure of guiding model training. Semi-supervised multi-view clustering takes advantages of heterogeneous features and a small number of side constraints (i.e., must-link constraints and cannot-link constraints) to partition data points. However, most of existing approaches are very limited in absorbing available side constraints since it is difficult to optimize cannot-link constraints in a provable way, and thus greatly waste the value of prior information. To address it, we innovatively pose a side-constrained multi-view graph clustering method, where the pairwise constraints are flexibly incorporated into the multiple graph fusion framework. The technique definitely formulates the pairwise constraints in the graph clustering model by designing a semi-supervised graph regularization term. In this way, the structured optimal graph that satisfies multiple perspectives and specified pairwise relations is obtained. By virtue of graph fusion, the self-adaptive weight of each single-view is optimally determined without partiality. We demonstrate theoretical feasibility of the proposed method. Extensive experimental results in four multi-view data sets witness our superiority compared to the state-of-the-art approaches.

Asset Resource Optimization Solution for Smart Hospital Facilities and Energy Management through an Interpretive Structural Model

An increasing focus has been placed on clean energy, carbon neutrality, carbon footprint monitoring, and adaptation of building information modeling (BIM)-based facility management (FM). Hence, there is also a growing demand to evaluate and prioritize which BIM applications are the most relevant to FM and are the most beneficial in the asset lifecycle, particularly in the operations stage. To inform BIM-FM application on smart hospital management, this research introduces a one-systems method through an interpretive structural model (ISM) to establish a structural contextual interrelationship between BIM uses in the operations stages of the asset. Through a literature review, this research first summarizes facility management functionalities achievable by BIM-FM and establishes their pairwise contextual relationship. A structural self-interaction matrix (SSIM) is then established, followed by partitioning these functionalities into separate levels to form the ISM model, while using driving power and dependence to form a MICMAC analysis matrix. The finding that the BIM uses “Environmental Monitoring and Building Performance” is the foundation that enables the other functionalities whilst validating that ad-hoc operations and maintenance activities enablement has the highest driving power, and automation and robotics have the highest dependency. Among the applications, energy monitoring plays a pivotal and transitional role with a strong dependency between airflow monitoring and solar monitoring, while its performance would directly impact emergency responses.

Influencing factors of hotel reservation and prediction

Hotel reservation has been a concern for hotel managers. They can manage their rooms well and deal with emergencies through the booking status, so it is important to predict whether the customer will cancel the reservation or not. Different from the articles data set based on evaluation and satisfaction of the hotel, this article is going to use limited and basic information based on objective factors to analysis the most influential factor and do the prediction. According to the correlation coefficient, the pairwise relationship of lead_time and booking status have a moderate and positive relationship, which. Next, through the test of goodness of fit, the number of children has a significant effect on the booking status. Last, the distance discriminant analysis model has a good predictive ability. The meaning of the analysis is to find new correlations of the pairwise variables, which people naturally ignore, and build a relatively accurate prediction model to serve the hotel managers to develop better.