Representation Of Relations Research Articles

On The Reasonable Effectiveness of Relational Diagrams: Explaining Relational Query Patterns and the Pattern Expressiveness of Relational Languages

Comparing relational languages by their logical expressiveness is well understood. Less well understood is how to compare relational languages by their ability to represent relational query patterns. Indeed, what are query patterns other than "a certain way of writing a query"? And how can query patterns be defined across procedural and declarative languages, irrespective of their syntax? To the best of our knowledge, we provide the first semantic definition of relational query patterns by using a variant of structure-preserving mappings between the relational tables of queries. This formalism allows us to analyze the relative pattern expressiveness of relational language fragments and create a hierarchy of languages with equal logical expressiveness yet different pattern expressiveness. Notably, for the non-disjunctive language fragment, we show that relational calculus can express a larger class of patterns than the basic operators of relational algebra. Our language-independent definition of query patterns opens novel paths for assisting database users. For example, these patterns could be leveraged to create visual query representations that faithfully represent query patterns, speed up interpretation, and provide visual feedback during query editing. As a concrete example, we propose Relational Diagrams, a complete and sound diagrammatic representation of safe relational calculus that is provably (i) unambiguous, (ii) relationally complete, and (iii) able to represent all query patterns for unions of non-disjunctive queries. Among all diagrammatic representations for relational queries that we are aware of, ours is the only one with these three properties. Furthermore, our anonymously preregistered user study shows that Relational Diagrams allow users to recognize patterns meaningfully faster and more accurately than SQL.

Vegetational and Structural Features of Forest Clearings in Plitvice Lakes National Park

The impact of various ecological factors, biogeographical position and both former and current anthropogenic activity in Plitvice Lakes National Park greatly influenced the development of different habitat types, including forest clearings. Due to the insufficient knowledge of this habitat type, based primarily on general descriptions within the National Habitat Classification of the Republic of Croatia (NN 27/2021, NN 101/2022), this paper deals with presenting their vegetational and structural characteristics in the national park area. The following taxonomic keys were used to determine plant species: Tutin et al. (1964-1980), Pignatti (1982), Javorka and Csapody (1991) and Martinčič et al. (1999). Furthermore, scientific nomenclature of plant species was conducted using Flora Croatica Database (Nikolić 2012), while threat status was aligned by the Red Book of Vascular Flora of Croatia (Nikolić and Topić 2005). Also, protection level was adjusted according to the Regulation on strictly protected species (NN 144/2013, NN 73/2016). Spectrum of life forms and chorological types were aligned according to Pignatti (2005). Vegetation was studied in accordance with the principles of the Braun-Blanquet approach (Braun-Blanquet 1964). Together with the basic parameters of the selected plots, the research also included the collection of structural parameters of forest clearings according to Medak et al. (2023). Based on conducted research, a total of 98 plots of forest clearing habitats were established with a total of five different forest clearing communities. The largest number of forest clearing communities belonged to Salicetum capreae, followed by Eupatorietum cannabini, Atropetum bella-donae, Telekium speciosae and Rubetum idaei. A total of 257 species of vascular plants were identified in the area and classified into 60 families. The most represented family was Asteraceae, while the highest relative representation of life-forms belonged to hemicryptophytes (H). Furthermore, the most represented chorologycal type in the area was Eurasian (20.6%). The habitat type contained a total of 11 strictly protected (SZ), 6 nearly threatened (NT), 3 vulnerable (VU), 2 data-deficient (DD) and 4 endemic species. In addition, the largest number of plots had an anthropogenic origin, irregular type (shape), occupied a small area (less than 1000 m2) and were located along the edges of both forests and forest roads. The results of this paper represent the first vegetational and structural data of forest clearings in the national park area which contribute to an expansion of our knowledge and understanding of this habitat type, and form a starting point for the necessary future research.

Student discourse’s paradoxes of representations of the concept “technological well-being of Russia”

Problem and aim. The relevance of presented study lies in understanding that it is impossible to be an independent government and implement its own policies without having technological leadership. In modern youth discourse, the attractive image of the creative engineer has disappeared, without which it is impossible to achieve a change in the «user» mentality in the field of technology. Accordingly, the purpose of the study is an applied communicative-semiotic analysis of the basic representations through which students describe concepts such as «Russia’s technological wellbeing», «technological leadership» and «technological imitation». Materials and research methods. The authors of the study used communicative-semiotic analysis to study free verbal associations of students (projective methodology), which made it possible to determine the symbolic constructs of youth discourse in the ratio of internal/external and individual/collective areas that integrate human consciousness and empirical phenomena into conversations about the technological well-being of Russia (concept of M. Conway). The applied research (questionnaire) was carried out in two stages. Data processing was carried out using the method of identifying keywords by Word Cloud Generator with the subsequent formation of a word cloud as a method of information compression. The identified associations were analyzed within the Porter stemmer word stemming tool. Research results. The results of the study showed that the formation of representations in relation to the concept of «technological well-being of Russia» is contradictory. However, this inconsistency is not associated with projection of the «technological leadership» and «technological imitation» vectors. The authors found that the projection of the image of the future of Russia in the trends of technological well-being is not associated by engineer students with the role of a man. The non-subjective nature of the concept of «technological well-being» emphasizes the gaps in the system of higher engineering education associated with the imposed practice of consumer behavior. The authors proposed educational technologies for leveling the non-subjective nature in the formation of the concept of «technological well-being of Russia» in the system of higher engineering education. Conclusion. The results of the study are significant for both the theoretical and practical research base in the field of higher engineering education. An empirical basis on representations of the image of the future associated with the concept of «technological well-being» will make it possible to understand what stereotypes and constructs are relevant for young people’s individual educational trajectory. In the future, this will make it possible to make changes curriculum for future engineers in terms of social and humanitarian knowledge.

I don't feel sick: Cognitive and affective processing of self-health associations using the Implicit Association Test.

Measuring implicit associations of self-concept with health or illness attributes may offer valuable insight into the mechanisms entailing the perception of one's own health, as explicit measures of self-reported health are usually influenced by social desirability or response bias. In this study, healthy participants performed a modified version of the implicit association test (IAT) investigating implicit associations between the self and either health or illness related representations. Behaviorally, implicit associations dominated for self-health pairing, and their strength was inversely correlated with depressive traits. Neurally, concomitant EEG recording showed significant modulations of the P1, LPP, and N4 components evoked by such pairings, suggesting a facilitation of sensory responses to self-related stimuli and differential emotional processes engaged to integrate health versus illness information into self-related representations. These data offer new clues to better understand the cognitive and affective mechanisms underlying unrealistic optimism and pathological awareness of health conditions in various clinical populations.

Influence of film thickness on structural, optical, and electrical properties of sputtered nickel oxide thin films.

Utilizing radio frequency magnetron sputtering, we successfully fabricated nickel oxide thin films with different thickness (from 80 to 270 nm), and conducted an in-depth examination of their structural, morphological, optical, and electrical properties. The crystal structure and surface roughness were determined using x-ray diffraction (XRD) and atomic force microscopy (AFM), respectively. The XRD analyses showed that the films were composed of cubic nickel oxide, exhibiting a notable orientation along the (200) direction. This crystal texture partially increased when the film thickness reached 270 nm. In addition, a direct correlation between film thickness and crystallite size was observed, with the latter increasing as the former did. AFM analysis provided insights into the surface morphology, revealing metrics like the bearing area, 3D surfaces intersections, and statistical properties of surface height. These insights underscore the relationship between film thickness and surface properties, which in turn influence the overall electrical, and prominently, optical properties of the films. Employing transmittance UV-visible spectroscopy, we characterized the optical behavior of these films, noting a proportional increase in refractive index with film thickness. Additionally, resistivity was observed to increase concomitantly with film thickness. In conclusion, the deposition process's film thickness acts as a pivotal parameter for fine-tuning the structural, morphological, and optical properties of nickel oxide thin films. This knowledge paves the way for optimizing nickel oxide-based devices across various applications. RESEARCH HIGHLIGHTS: We synthesized and characterized of p-type semiconducting NiO thin films sputtered on substrates by using RF magnetron sputtering with different thickness. Advanced crystalline structures and fractal features extracted from XRD and AFM analysis. The 2D and 3Dsurface analysis of the samples indicates a complex structure with an imperfect self-similarity that suggests a multifractal structure. We represented graphically the relative representation of higher geometric objects in the AFM image. We attributed the optical and electrical properties of the samples to the crystallite size, and the concurrent reduction in oxygen vacancies and crystalline defects within the films.

Diverse Structure-Aware Relation Representation in Cross-Lingual Entity Alignment

Cross-lingual entity alignment (CLEA) aims to find equivalent entity pairs between knowledge graphs (KGs) in different languages. It is an important way to connect heterogeneous KGs and facilitate knowledge completion. Existing methods have found that incorporating relations into entities can effectively improve KG representation and benefit entity alignment, and these methods learn relation representation depending on entities, which cannot capture the diverse structures of relations. However, multiple relations in KG form diverse structures, such as adjacency structure and ring structure. This diversity of relation structures makes the relation representation challenging. Therefore, we propose to construct the weighted line graphs to model the diverse structures of relations and learn relation representation independently from entities. Especially, owing to the diversity of adjacency structures and ring structures, we propose to construct adjacency line graph and ring line graph, respectively, to model the structures of relations and to further improve entity representation. In addition, to alleviate the hubness problem in alignment, we introduce the optimal transport into alignment and compute the distance matrix in a different way. From a global perspective, we calculate the optimal 1-to-1 alignment bi-directionally to improve the alignment accuracy. Experimental results on two benchmark datasets show that our proposed method significantly outperforms state-of-the-art CLEA methods in both supervised and unsupervised manners.

Measurable multiresolution systems, endomorphisms, and representations of Cuntz relations

Measurable multiresolution systems, endomorphisms, and representations of Cuntz relations

Knowledge Graph Embedding via Triplet Component Interactions

In knowledge graph embedding, multidimensional representations of entities and relations are learned in vector space. Although distance-based graph embedding methods have shown promise in link prediction, they neglect context information among the triplet components, i.e., the head_entity, relation, and tail_entity, limiting their ability to describe multivariate relation patterns and mapping properties. Such context information denotes the entity structural association inside the same triplet and implies the correlation between entities that are not directly connected. In this work, we propose a novel knowledge graph embedding model that explicitly considers context information in graph embedding via triplet component interactions (TCIE). To build connections between components and incorporate contextual information, entities and relations are represented as vectors comprised of two specialized parts, enabling comprehensive interaction. By simultaneously interacting with one-hop related head and tail entities, TCIE strengthens the connections between distant entities and enables contextual information to be transmitted across the knowledge graph. Mathematical proofs and experiments are performed to analyse the modelling ability of TCIE in knowledge graph embedding. TCIE shows a strong capacity for modelling four relation patterns (i.e., symmetry, antisymmetry, inverse, and composition) and four mapping properties (i.e., one-to-one, one-to-many, many-to-one, and many-to-many). The experimental evaluation of ogbl-wikikg2, ogbl-biokg, FB15k, and FB15k-237 shows that TCIE achieves state-of-the-art results in link prediction.

Semantic-Enhanced Knowledge Graph Completion

Knowledge graphs (KGs) serve as structured representations of knowledge, comprising entities and relations. KGs are inherently incomplete, sparse, and have a strong need for completion. Although many knowledge graph embedding models have been designed for knowledge graph completion, they predominantly focus on capturing observable correlations between entities. Due to the sparsity of KGs, potential semantic correlations are challenging to capture. To tackle this problem, we propose a model entitled semantic-enhanced knowledge graph completion (SE-KGC). SE-KGC effectively addresses the issue by incorporating predefined semantic patterns, enabling the capture of semantic correlations between entities and enhancing features for representation learning. To implement this approach, we employ a multi-relational graph convolution network encoder, which effectively encodes the KG. Subsequently, we utilize a scoring decoder to evaluate triplets. Experimental results demonstrate that our SE-KGC model outperforms other state-of-the-art methods in link-prediction tasks across three datasets. Specifically, compared to the baselines, SE-KGC achieved improvements of 11.7%, 1.05%, and 2.30% in terms of MRR on these three datasets. Furthermore, we present a comprehensive analysis of the contributions of different semantic patterns, and find that entities with higher connectivity play a pivotal role in effectively capturing and characterizing semantic information.

Ayurvedic protocols of chronic pain management: spatiotemporality as present moment awareness and embodied time.

Temporality is understood as the subjective perception of the flow of chronological time and is a central component of contemporary and integrative medicine approaches. Although temporal dynamics are recognized as central to the processes associated with chronic pain (CP), the temporal management of CP is inadequately understood in pain research. How is temporality conceptualized in Ayurvedic protocols of CP management?. Ayurvedic physicians (N = 10) from India were recruited through purposive and snowball sampling. A semi-structured interview protocol was employed to gather qualitative data focusing on the Ayurvedic protocol employed to treat CP patients. The interviews were audio-recorded, professionally transcribed, and thematically analyzed. Member validation, participant voice, and researcher self-awareness were employed to strengthen reliability and validity. An ontologically grounded thematic exploration of Ayurvedic protocols illustrates that temporality is conceptualized in CP as spatiotemporal present moment awareness (PMA) and embodied time (ET). Spatiotemporality as PMA references an awareness of the relationality of cognitive temporal movement, dosha operations, and their pathophysiological expression in the body. Spatiotemporality as ET is conceptualized as awareness of the expression of time in embodied emotional and psychosocial processes as in the movement of the breath through the body, the movement of body sensations over time, and in their intersection with consciousness. The study findings present an experiential and relational framework situating spatiotemporality ontologically as an organizing principle in CP management. While temporality focuses on the representation of experiences and relations over time, spatiotemporality foregrounds a constructionist approach by centering the embodied spatial cognitive expression of time, consciousness, and subjective experience.

Weighted and Choquet $$L^p$$ distance representation of comparative dissimilarity relations on fuzzy description profiles

AbstractWe consider comparative dissimilarity relations on pairs on fuzzy description profiles, the latter providing a fuzzy set-based representation of pairs of objects. Such a relation expresses the idea of “no more dissimilar than” and is used by a decision maker when performing a case-based decision task under vague information. We first limit ourselves to those relations admitting a weighted $$\varvec{L}^p$$ L p distance representation, for which we provide an axiomatic characterization in case the relation is complete, transitive and defined on the entire space of pairs of fuzzy description profiles. Next, we switch to the more general class of comparative dissimilarity relations representable by a Choquet $$\varvec{L}^p$$ L p distance, parameterized by a completely alternating normalized capacity.

Exploring Visual Relationships via Transformer-based Graphs for Enhanced Image Captioning

Image captioning (IC), bringing vision to language, has drawn extensive attention. A crucial aspect of IC is the accurate depiction of visual relations among image objects. Visual relations encompass two primary facets: content relations and structural relations. Content relations, which comprise geometric positions content (i.e., distances and sizes) and semantic interactions content (i.e., actions and possessives), unveil the mutual correlations between objects. In contrast, structural relations pertain to the topological connectivity of object regions. Existing Transformer-based methods typically resort to geometric positions to enhance the visual relations, yet only using the shallow geometric content is unable to precisely cover actional content correlations and structural connection relations. In this article, we adopt a comprehensive perspective to examine the correlations between objects, incorporating both content relations (i.e., geometric and semantic relations) and structural relations, with the aim of generating plausible captions. To achieve this, first, we construct a geometric graph from bounding box features and a semantic graph from the scene graph parser to model the content relations. Innovatively, we construct a topology graph that amalgamates the sparsity characteristics of the geometric and semantic graphs, enabling the representation of image structural relations. Second, we propose a novel unified approach to enrich image relation representations by integrating semantic, geometric, and structural relations into self-attention. Finally, in the language decoding stage, we further leverage the semantic relation as prior knowledge to generate accurate words. Extensive experiments on MS-COCO dataset demonstrate the effectiveness of our model, with improvements of CIDEr from 128.6% to 136.6%. Codes have been released at https://github.com/CrossmodalGroup/ER-SAN/tree/main/VG-Cap .

Knowledge graph embedding based on dynamic adaptive atrous convolution and attention mechanism for link prediction

Knowledge graph embedding (KGE) is essential for various applications, particularly in link prediction and other downstream tasks. While existing convolutional neural network (CNN)-based methods have been effective, they face challenges in comprehensively capturing local and global contextual information from triplets. To address this challenge, we propose a KGE method based on a dynamic adaptive atrous convolution and attention mechanism (DTAE). In this study, we innovatively construct adaptive convolutional kernels derived from relation representations. Employing a parallel strategy, we apply a multidimensional attention mechanism across kernel space. This configuration allows our kernels to dynamically adapt and learn from different entity representations, ensuring more nuanced feature extraction. Moreover, a dynamic adaptive atrous convolutional network has been developed. This network leverages atrous convolution, efficiently broadening the receptive field to encompass global information while preserving essential details during the aggregation process. In addition, we enhance feature information by integrating a channel attention mechanism, further refining our model’s ability to discern and process relevant data. Via comprehensive experiments on five standard link prediction benchmark datasets, DTAE demonstrates superior performance over existing models. Compared to the best recent state-of-the-art models over the last three years, we achieve improvements across various metrics ranging from 0.4% to 14.4%.

Linear integral operators on Lp\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$L_p$$\\end{document} spaces representing polynomial covariance type commutation relations

In this work, we present methods for constructing representations of polynomial covariance type commutation relations AB=BF(A)\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$AB=BF(A)$$\\end{document} by linear integral operators in Banach spaces Lp\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$L_p$$\\end{document}. We derive necessary and sufficient conditions on the kernel functions for the integral operators to satisfy the covariance type commutation relation for general polynomials F, as well as for important cases, when F is arbitrary affine or quadratic polynomial, or arbitrary monomial of any degree. Using the obtained general conditions on the kernels, we construct concrete examples of representations of the covariance type commutation relations by integral operators on Lp\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$L_p$$\\end{document}. Also, we derive useful general reordering formulas for the integral operators representing the covariance type commutation relations, in terms of the kernel functions.

Semantic Interaction Matching Network for Few-Shot Knowledge Graph Completion

The prosperity of knowledge graphs, as well as related downstream applications, has raised the urgent need for knowledge graph completion techniques that fully support knowledge graph reasoning tasks, especially under the circumstance of training data scarcity. Although large efforts have been made on solving this challenge via few-shot learning tools, they mainly focus on simply aggregating entity neighbors to represent few-shot references, whereas the enhancement from latent semantic correlation within neighbors has been largely ignored. To that end, in this article, we propose a novel few-shot learning solution named SIM, a S emantic I nteraction M atching network that applies a Transformer framework to enhance the entity representation with capturing semantic interaction between entity neighbors. Specifically, we first design an entity-relation fusion module to adaptively encode neighbors with incorporating relation representation. Along this line, Transformer layers are integrated to capture latent correlation within neighbors, as well as the semantic diversification of the support set. Finally, a similarity score is attentively estimated with the attention mechanism. Extensive experiments on two public benchmark datasets demonstrate that our model outperforms a variety of state-of-the-art methods by a significant margin.

Food and childhood pathologies and social representations among the ewondo of Cameroon

In the Third World, childhood pathologies are associated with malnutrition and, above all, environmental conditions. However, there are pathological foci that are not linked to these two entities. We have a range of morbidities which are the result of the diet of either the mother or the child. These are morbidities considered to be endo-cultural. An approach to pathology that finds meaning and a solution in the perspective of a particular cultural entity, and for which it has its foundation. This is reflected in dietary prohibitions. The relationship between diet and morbidity makes perfect sense here. In fact, we have childhood pathologies that are the result of parents' failure to respect social and dietary prohibitions. In the light of a few examples, we can see how these two particularities of human and child life are linked. Using an ethnographic approach to the issue of food, we relate the childhood morbidities that Ewondo socioculture includes in its childhood nosology to the related perceptions and representations. Childhood illnesses are not caused by the environment or malnutrition, but rather by the culture and its vision of the world and of things.

Relative molecule self-attention transformer

The prediction of molecular properties is a crucial aspect in drug discovery that can save a lot of money and time during the drug design process. The use of machine learning methods to predict molecular properties has become increasingly popular in recent years. Despite advancements in the field, several challenges remain that need to be addressed, like finding an optimal pre-training procedure to improve performance on small datasets, which are common in drug discovery. In our paper, we tackle these problems by introducing Relative Molecule Self-Attention Transformer for molecular representation learning. It is a novel architecture that uses relative self-attention and 3D molecular representation to capture the interactions between atoms and bonds that enrich the backbone model with domain-specific inductive biases. Furthermore, our two-step pretraining procedure allows us to tune only a few hyperparameter values to achieve good performance comparable with state-of-the-art models on a wide selection of downstream tasks.

Gut microbiota at different stages of cardiovascular disease continuum

Aim. To study the relationship of gut microbiota (GM) composition with clinical and paraclinical characteristics of patients with coronary artery disease (CAD) and heart failure with reduced ejection fraction (HFrEF).Material and methods. The study included 64 patients (men, 71,9%) with CAD, 33 (men, 87,9%) with HFrEF and 38 (men, 63,2%) with various cardiovascular risk factors (control group). GM composition was assessed using real-time polymerase chain reaction and next- generation sequencing. To identify correlations of GM composition with clinical and paraclinical characteristics, the Spearman rank correlation coefficient (ρ) was calculated. Generalized linear models (QuasiPoisson, overdispersion) with covariates (age, body mass index) were used to compare groups by phylotype.Results. The relative abundance of Bacillota phylotypes is significantly higher in patients with CAD and HFrEF compared to controls (p<0,001). The Bacillota/Bacteroidota dysbiosis ratio was also significantly higher in patients with CAD and HFrEF than in the control group (p<0,001). According to correlation analysis, the relative representation of methanogenic archaea Methanomassiliicoccaceae, Methanomethylophilaceae (ρ=0,49, p<0,0003) directly correlated with ventricular arrhythmias in patients with HFrEF.Conclusion. Patients with CAD and HFrEF differ significantly from the control group in GM composition at the phylotype level. In the study groups, Bacillota/Bacteroidota dysbiosis ratio was also significantly higher than in the control group. The relative abundance of the archaea Methanomassiliicoccaceae and Methanomethylophilaceae is associated with episodes of ventricular tachycardia/ventricular fibrillation.

A Unified and Biologically Plausible Relational Graph Representation of Vision Transformers.

Vision transformer (ViT) and its variants have achieved remarkable success in various tasks. The key characteristic of these ViT models is to adopt different aggregation strategies of spatial patch information within the artificial neural networks (ANNs). However, there is still a key lack of unified representation of different ViT architectures for systematic understanding and assessment of model representation performance. Moreover, how those well-performing ViT ANNs are similar to real biological neural networks (BNNs) is largely unexplored. To answer these fundamental questions, we, for the first time, propose a unified and biologically plausible relational graph representation of ViT models. Specifically, the proposed relational graph representation consists of two key subgraphs: an aggregation graph and an affine graph. The former considers ViT tokens as nodes and describes their spatial interaction, while the latter regards network channels as nodes and reflects the information communication between channels. Using this unified relational graph representation, we found that: 1) model performance was closely related to graph measures; 2) the proposed relational graph representation of ViT has high similarity with real BNNs; and 3) there was a further improvement in model performance when training with a superior model to constrain the aggregation graph.

High-Order Neighbors Aware Representation Learning for Knowledge Graph Completion.

As a building block of knowledge acquisition, knowledge graph completion (KGC) aims at inferring missing facts in knowledge graphs (KGs) automatically. Previous studies mainly focus on graph convolutional network (GCN)-based KG embedding (KGE) to determine the representations of entities and relations, accordingly predicting missing triplets. However, most existing KGE methods suffer from limitations in predicting tail entities that are far away or even unreachable in KGs. This limitation can be attributed to the related high-order information being largely ignored. In this work, we focus on learning the information from the related high-order neighbors in KGs to improve the performance of prediction. Specifically, we first introduce a set of new nodes called pedal nodes to augment the KGs for facilitating message passing between related high-order entities, effectively injecting the information of high-order neighbors into entity representation. Additionally, we propose strength-guided graph neural networks to aggregate neighboring entity representations. To address the issue of transmitting irrelevant higher order information to entities through pedal nodes, which can potentially hurt entity representation, we further propose to dynamically integrate the aggregated representation of each node with its corresponding self-representation. Extensive experiments have been conducted on three benchmark datasets and the results demonstrate the superiority of our method compared to strong baseline models.