Graph Data Structure Research Articles

Efficient generation of grids and traversal graphs in compositional spaces towards exploration and path planning

AbstractDiverse disciplines across science and engineering deal with problems related to compositions, which exist in non-Euclidean simplex spaces, rendering many standard tools inaccurate or inefficient. This work explores such spaces conceptually in the context of materials discovery, quantifies their computational feasibility, and implements several essential methods specific to simplex spaces through a new high-performance open-source library . Most significantly, we derive and implement an algorithm for constructing a novel n-dimensional simplex graph data structure, containing all discretized compositions and possible neighbor-to-neighbor transitions. Critically, no distance or neighborhood calculations are performed, instead leveraging pure combinatorics and order in procedurally generated simplex grids, keeping the algorithm $${\mathcal{O}}(N)$$ O ( N ) , with minimal memory, enabling rapid construction of graphs with billions of transitions in seconds. Additionally, we demonstrate how such graph representations can be combined to homogeneously express complex path-planning problems, while facilitating efficient deployment of existing high-performance gradient descent, graph traversal, and other optimization algorithms.

GPS Tracking and Indoor Navigation System

This project is an idea of developing an application based on a navigation system formed by Graph Data Structure. An indoor positioning system (IPS) can be thought of as a global positioning system (GPS) for indoor venues. While GPS is used outdoors, IPS can detect real-time locations to accurately determine the coordinates of people or assets inside a building. These coordinates are typically represented visually by a blue dot on a digital indoor map to provide additional context to users and features such as wayfinding. The project aims to have certain objectives such as a tracking system, navigation system that is inside a small area of a building. This idea aims to track the location of any particular device within a building and show a navigation to that device in an efficient manner. Not only tracking of devices but also solving a problem of finding a particular room in the building through data of different paths that is stored. This project comes under the intelligent system design and development domain and falls under the sector of analysing and designing hardware, software and operating systems for computers. The main objective of this system design is to navigate through the area and find places to reach with ease and as fast as possible, it is helpful for people who are new at that place and even finding a user in that particular vicinity by live tracking technique.

Interaction-knowledge semantic alignment for recommendation

In order to alleviate the issue of data sparsity, knowledge graphs are introduced into recommender systems because they contain diverse information about items. The existing knowledge graph enhanced recommender systems utilize both user–item interaction data and knowledge graph, but those methods ignore the semantic difference between interaction data and knowledge graph. On the other hand, for the item representations obtained from two kinds of graph structure data respectively, the existing methods of fusing representations only consider the item representations themselves, without considering the personalized preference of users. In order to overcome the limitations mentioned above, we present a recommendation method named Interaction-Knowledge Semantic Alignment for Recommendation (IKSAR). By introducing a semantic alignment module, the semantic difference between the interaction bipartite graph and the knowledge graph is reduced. The representation of user is integrated during the fusion of representations of item, which improves the quality of the fused representation of item. To validate the efficacy of the proposed approach, we perform comprehensive experiments on three datasets. The experimental results demonstrate that the IKSAR is superior to the existing methods, showcasing notable improvement.

A review of feature selection strategies utilizing graph data structures and Knowledge Graphs

Abstract Feature selection in Knowledge Graphs (KGs) is increasingly utilized in diverse domains, including biomedical research, Natural Language Processing (NLP), and personalized recommendation systems. This paper delves into the methodologies for feature selection (FS) within KGs, emphasizing their roles in enhancing machine learning (ML) model efficacy, hypothesis generation, and interpretability. Through this comprehensive review, we aim to catalyze further innovation in FS for KGs, paving the way for more insightful, efficient, and interpretable analytical models across various domains. Our exploration reveals the critical importance of scalability, accuracy, and interpretability in FS techniques, advocating for the integration of domain knowledge to refine the selection process. We highlight the burgeoning potential of multi-objective optimization and interdisciplinary collaboration in advancing KG FS, underscoring the transformative impact of such methodologies on precision medicine, among other fields. The paper concludes by charting future directions, including the development of scalable, dynamic FS algorithms and the integration of explainable AI principles to foster transparency and trust in KG-driven models.

Electric vehicle charging load prediction based on graph attention networks and autoformer

AbstractWith the widespread popularity of electric vehicles in the domestic market, large‐scale electric vehicle user data has been collected and stored. Highly accurate user‐level charging load prediction has a wide range of application scenarios and great business value. However, most existing EV load prediction methods are modelled from the charging station perspective, ignoring the user's travel habits and charging demand. Therefore, this paper proposes a temporal spatial neural network based on graph attention and Autoformer to predict electric vehicle charging load. Firstly, the urban map of Wuhan is rasterized. Then, driving and charging data from the user level are aggregated into the raster module according to the time sequence, and a spatio‐temporal graph data structure of user travel trajectory is constructed. Finally, the temporal spatial neural network is used to construct the EV charging load prediction model from the user's perspective. The experimental results show that, compared with other baseline prediction methods, the proposed method effectively improves the accuracy of the EV charging load prediction model by fully exploiting the distribution of EV user clusters in time and geographic space.

Network link prediction via deep learning method: A comparative analysis with traditional methods

In the domain of data-centric networks, Link Prediction (LP) is instrumental in discerning potential or absent connections among entities within complex networks. By employing graph data structures, LP techniques enable a detailed analysis of entity interactions across varied sectors, contributing significantly to overcoming challenges in data filtering and integrity restoration, primarily when the network does not provide embedded data. Although LP methods are widely applicable, especially in recommender systems, their efficacy in current social networks needs to be thoroughly investigated. This study introduces an innovative LP approach using Deep Neural Networks (DNNs). We compare our method against a comprehensive set of established techniques, including traditional score-based methods, classical baselines, and recent deep learning approaches like Graph Neural Networks (GNNs). Our DNN-based solution incorporates a robust feature extraction process and a binary classifier, optimized for accurate prediction of missing links within networks. We performed extensive experimental evaluations on diverse datasets, including co-authorship networks, e-commerce, and social media networks. The study encompasses a comparative analysis with traditional LP techniques, namely Common Neighbors, Resource Allocation Index, Jaccard’s Coefficient, and Adamic/Adar Index, as well as other selected baseline and deep-learning methods. Our findings demonstrate that the DNN-based approach significantly enhances predictive accuracy, outperforming the conventional baseline methods in link prediction.

Multi-Source Information Graph Embedding with Ensemble Learning for Link Prediction

Link prediction is a key technique for connecting entities and relationships in a graph reasoning field. It leverages known information about the graph structure data to predict missing factual information. Previous studies have either focused on the semantic representation of a single triplet or on the graph structure data built on triples. The former ignores the association between different triples, and the latter ignores the true meaning of the node itself. Furthermore, common graph-structured datasets inherently face challenges, such as missing information and incompleteness. In light of this challenge, we present a novel model called Multi-source Information Graph Embedding with Ensemble Learning for Link Prediction (EMGE), which can effectively improve the reasoning of link prediction. Ensemble learning is systematically applied throughout the model training process. At the data level, this approach enhances entity embeddings by integrating structured graph information and unstructured textual data as multi-source information inputs. The fusion of these inputs is effectively addressed by introducing an attention mechanism. During the training phase, the principle of ensemble learning is employed to extract semantic features from multiple neural network models, facilitating the interaction of enriched information. To ensure effective model learning, a novel loss function based on contrastive learning is devised, effectively minimizing the discrepancy between predicted values and the ground truth. Moreover, to enhance the semantic representation of graph nodes in link prediction, two rules are introduced during the aggregation of graph structure information. These rules incorporate the concept of spreading activation, enabling a more comprehensive understanding of the relationships between nodes and edges in the graph. During the testing phase, the EMGE model is validated on three datasets, including WN18RR, FB15k-237, and a private Chinese financial dataset. The experimental results demonstrate a reduction in the mean rank (MR) by 0.2 times, an improvement in the mean reciprocal rank (MRR) by 5.9%, and an increase in the Hit@1 by 12.9% compared to the baseline model.

Proximity Graph Networks: Predicting Ligand Affinity with Message Passing Neural Networks.

Message passing neural networks (MPNNs) on molecular graphs generate continuous and differentiable encodings of small molecules with state-of-the-art performance on protein-ligand complex scoring tasks. Here, we describe the proximity graph network (PGN) package, an open-source toolkit that constructs ligand-receptor graphs based on atom proximity and allows users to rapidly apply and evaluate MPNN architectures for a broad range of tasks. We demonstrate the utility of PGN by introducing benchmarks for affinity and docking score prediction tasks. Graph networks generalize better than fingerprint-based models and perform strongly for the docking score prediction task. Overall, MPNNs with proximity graph data structures augment the prediction of ligand-receptor complex properties when ligand-receptor data are available.

GraphSlimmer: Preserving Read Mappability with the Minimum Number of Variants.

Modern genomic datasets, like those generated under the 1000 Genome Project, contain millions of variants belonging to known haplotypes. Although these datasets are more representative than a single reference sequence and can alleviate issues like reference bias, they are significantly more computationally burdensome to work with, often involving large-indexed genome graph data structures for tasks such as read mapping. The construction, preprocessing, and mapping algorithms can require substantial computational resources depending on the size of these variant sets. Moreover, the accuracy of mapping algorithms has been shown to decrease when working with complete variant sets. Therefore, a drastically reduced set of variants that preserves important properties of the original set is desirable. This work provides a technique for finding a minimal subset of variants such that for given parameters α and δ, all substrings up to length α in the haplotypes are guaranteed to be still alignable to the appropriate locations with either Hamming or edit distance at most δ, using only . Our contributions include showing the NP-hardness and inapproximability of these optimization problems and providing Integer Linear Programming (ILP) formulations. Our edit distance ILP formulation carefully decomposes the problem according to variant locations, which allows it to scale to support all of chromosome 22's variants from the 1000 Genome Project. Our experiments also demonstrate a significant reduction in the number of variants. For example, for moderately long reads, e.g., α = 1000, over 75% of the variants can be removed while preserving read mappability with edit distance at most one.

EEG-based TSK fuzzy graph neural network for driver drowsiness estimation

With the development of brain-computer interface (BCI), electroencephalogram (EEG) is considered to be one of the best physiological signals to detect the fatigue state of drivers due to its advantages of extremely high time resolution and low use cost. However, since EEG is sensitive to noise/artifacts, and there is non-stationarity and low signal-to-noise ratio in inter-subject/intra-subject, the accurate estimation of driver drowsiness state remains challenging. Therefore, this paper proposes the EEG-based TSK fuzzy graph neural network (TSKG) to solve the regression problem of driver drowsiness estimation by combining transfer learning (TL), graph convolutional neural network (GCN), information theory, and TSK fuzzy neural network. TSKG extracts the relevant features in EEG through mutual information minimization and regards the fuzzy rules as graph structure data. The extracted relevant features and the original features are used to optimize the fuzzy rules through GCN. TSKG is tested on the fatigue driving dataset, and Root Mean Square Error (RMSE) and Correlation Coefficient (CC) are 0.1681 and 0.7118, respectively. Especially when dealing with difficult samples, TSKG has significantly better generalization performance.

Enhancing Signed Graph Attention Network by Graph Characteristics: An Analysis

A graph neural network (GNN) is one of successful methods for handling tasks on a graph data structure, e.g. node embedding, link prediction and node classification. GNNs focus on a graph data structure that must aggregate messages on nodes in the graph to retain a graph-structured information in new node’s message and proceed tasks on a graph. One of modifications on the propagation step in GNNs by adopting attention mechanism is a graph attention network (GAT). Applying this modification to signed graphs generated by sociological theories is called signed graph attention network (SiGAT). In this research, we utilize SiGAT and create novel graphs using graph characters to assess the performance of SiGAT models embedded in nodes across various characteristic graphs. The primary focus of our study was linked prediction, which aligns with the task employed in the previous research on SiGAT. We propose a method using graph characteristics to improve the time spent on the learning process in SiGAT.

Inference of gene regulatory networks based on directed graph convolutional networks.

Inferring gene regulatory network (GRN) is one of the important challenges in systems biology, and many outstanding computational methods have been proposed; however there remains some challenges especially in real datasets. In this study, we propose Directed Graph Convolutional neural network-based method for GRN inference (DGCGRN). To better understand and process the directed graph structure data of GRN, a directed graph convolutional neural network is conducted which retains the structural information of the directed graph while also making full use of neighbor node features. The local augmentation strategy is adopted in graph neural network to solve the problem of poor prediction accuracy caused by a large number of low-degree nodes in GRN. In addition, for real data such as E.coli, sequence features are obtained by extracting hidden features using Bi-GRU and calculating the statistical physicochemical characteristics of gene sequence. At the training stage, a dynamic update strategy is used to convert the obtained edge prediction scores into edge weights to guide the subsequent training process of the model. The results on synthetic benchmark datasets and real datasets show that the prediction performance of DGCGRN is significantly better than existing models. Furthermore, the case studies on bladder uroepithelial carcinoma and lung cancer cells also illustrate the performance of the proposed model.

Node classification in complex networks based on multi-view debiased contrastive learning

In complex networks, contrastive learning has emerged as a crucial technique for acquiring discriminative representations from graph data. Maximizing the similarity among relevant sample pairs while minimizing that among irrelevant pairs is pivotal in contrastive learning. Therefore, careful consideration must be given to the design of sample pairs in contrastive learning. However, existing node-level self-supervised contrastive learning often treats the enhanced representation of a central node as a positive sample, while considering representations of all other nodes as negative samples. This approach can lead to conflicts in downstream tasks on some graph data, as nodes of the same class are treated as negatives during learning. Precision in sample pair design is essential for enhancing the performance of contrastive learning. To address this issue, this paper introduces a negative sample debiased sampling contrastive learning (NDSCL), specifically tailored for node classification tasks. In particular, this method integrates contrastive learning with semi-supervised learning. A trained classifier assigns pseudo-labels to unlabeled data, and debiased sampling is applied to negative samples. Unlike other methods that focus on negative sample selection, NDSCL also addresses the imbalance in pseudo-label distribution by employing debiasing techniques. Finally, in conjunction with diffusion augmentation, the model is provided with diverse views as inputs to maximize the retention of underlying semantic information. Experimental results demonstrate that the proposed model significantly outperforms baseline models in node-level classification tasks across multiple network datasets. Moreover, the model not only enhances accuracy but also improves computational speed and memory requirements for handling large-scale graph data structures.

Deep graph layer information mining convolutional network

Graph convolution network is a powerful method of deep learning of graph structure data. Existing methods usually adjust the neighborhood information aggregation mode or optimize the graph topology layer by layer for improving the graph convolution network. However, these methods seldom consider the discriminative information about hierarchical characteristics nodes (some special nodes only can be correctly classified in one layer and are the misclassification nodes in the other layers of deep graph convolutional networks) in the different layers for complementing the neighborhood topology information. To further find these information, a deep graph layer information mining convolutional network (GLIM) can alternately measure the neighborhood ranking information on topology structure and update the residual identity mapping node information on the different layers for enhancing the model classification performance. Moreover, GLIM can construct a unified framework with the various hyper-parameters for the different graph learning method based on graph convolution network. Experiments show GLIM outperforms the state-of-the-art methods for semi-supervised node classification in three cite datasets (Cora, CiteSeer,and PubMed) and three image datasets (MNIST, Cifar10 and Cifar100).

Graph topological transformations in space-filling cell aggregates.

Cell rearrangements are fundamental mechanisms driving large-scale deformations of living tissues. In three-dimensional (3D) space-filling cell aggregates, cells rearrange through local topological transitions of the network of cell-cell interfaces, which is most conveniently described by the vertex model. Since these transitions are not yet mathematically properly formulated, the 3D vertex model is generally difficult to implement. The few existing implementations rely on highly customized and complex software-engineering solutions, which cannot be transparently delineated and are thus mostly non-reproducible. To solve this outstanding problem, we propose a reformulation of the vertex model. Our approach, called Graph Vertex Model (GVM), is based on storing the topology of the cell network into a knowledge graph with a particular data structure that allows performing cell-rearrangement events by simple graph transformations. Importantly, when these same transformations are applied to a two-dimensional (2D) polygonal cell aggregate, they reduce to a well-known T1 transition, thereby generalizing cell-rearrangements in 2D and 3D space-filling packings. This result suggests that the GVM's graph data structure may be the most natural representation of cell aggregates and tissues. We also develop a Python package that implements GVM, relying on a graph-database-management framework Neo4j. We use this package to characterize an order-disorder transition in 3D cell aggregates, driven by active noise and we find aggregates undergoing efficient ordering close to the transition point. In all, our work showcases knowledge graphs as particularly suitable data models for structured storage, analysis, and manipulation of tissue data.

Topology-Based Modularity and Modularity Density for Detecting Protein Complexes: A Comparative Study

Binary relations or interactions among bio-entities, such as proteins, set up the essential part of any living biological system. Protein-protein interactions are usually structured in a graph data structure called "protein-protein interaction networks" (PPINs). Analysis of PPINs into complexes tries to lay out the significant knowledge needed to answer many unresolved questions, including how cells are organized and how proteins work. However, complex detection problems fall under the category of non-deterministic polynomial-time hard (NP-Hard) problems due to their computational complexity. To accommodate such combinatorial explosions, evolutionary algorithms (EAs) are proven effective alternatives to heuristics in solving NP-hard problems. The main aim of this study is to make a close examination of the performance of the EAs where modularity and modularity density are selected as two different objective functions. Topology-based modularity and topology-based modularity density are designed to examine the detection ability of the EAs and to compare their performance. To conduct the experiments, two yeast Saccharomyces cerevisiae PPINs are used and evaluated under nine evaluation metrics. The results reveal the potential impact of the topology-based modularity density to outperform the counterpart modularity functions in almost all evaluation metrics.

The Use of Generative Adversarial Network and Graph Convolution Network for Neuroimaging-Based Diagnostic Classification.

Functional connectivity (FC) obtained from resting-state functional magnetic resonance imaging has been integrated with machine learning algorithms to deliver consistent and reliable brain disease classification outcomes. However, in classical learning procedures, custom-built specialized feature selection techniques are typically used to filter out uninformative features from FC patterns to generalize efficiently on the datasets. The ability of convolutional neural networks (CNN) and other deep learning models to extract informative features from data with grid structure (such as images) has led to the surge in popularity of these techniques. However, the designs of many existing CNN models still fail to exploit the relationships between entities of graph-structure data (such as networks). Therefore, graph convolution network (GCN) has been suggested as a means for uncovering the intricate structure of brain network data, which has the potential to substantially improve classification accuracy. Furthermore, overfitting in classifiers can be largely attributed to the limited number of available training samples. Recently, the generative adversarial network (GAN) has been widely used in the medical field for its generative aspect that can generate synthesis images to cope with the problems of data scarcity and patient privacy. In our previous work, GCN and GAN have been designed to investigate FC patterns to perform diagnosis tasks, and their effectiveness has been tested on the ABIDE-I dataset. In this paper, the models will be further applied to FC data derived from more public datasets (ADHD, ABIDE-II, and ADNI) and our in-house dataset (PTSD) to justify their generalization on all types of data. The results of a number of experiments show the powerful characteristic of GAN to mimic FC data to achieve high performance in disease prediction. When employing GAN for data augmentation, the diagnostic accuracy across ADHD-200, ABIDE-II, and ADNI datasets surpasses that of other machine learning models, including results achieved with BrainNetCNN. Specifically, in ADHD, the accuracy increased from 67.74% to 73.96% with GAN, in ABIDE-II from 70.36% to 77.40%, and in ADNI, reaching 52.84% and 88.56% for multiclass and binary classification, respectively. GCN also obtains decent results, with the best accuracy in ADHD datasets at 71.38% for multinomial and 75% for binary classification, respectively, and the second-best accuracy in the ABIDE-II dataset (72.28% and 75.16%, respectively). Both GAN and GCN achieved the highest accuracy for the PTSD dataset, reaching 97.76%. However, there are still some limitations that can be improved. Both methods have many opportunities for the prediction and diagnosis of diseases.

Public opinion bunching storage model for dense graph data in social networks1

Graph data storage has a promising prospect due to the surge of graph-structure data. Especially in social networks, it is widely used because hot public opinions trigger some network structures consisting of massively associated entities. However, the current storage model suffers from slow processing speed in this dense association graph data. Thus, we propose a new storage model for dense graph data in social networks to improve data processing efficiency. First, we identify the public opinion network formed by hot topics or events. Second, we design the germ elements and public opinion bunching mapping relationship based on equivalence partition. Finally, the Public Opinion Bunching Storage(POBS) model is constructed to implement dense graph data storage effectively. Extensive experiments on Twitter datasets demonstrate that the proposed POBS performs favorably against the state-of-the-art graph data models for storage and processing.

Intelligent extraction of medical entity relationship based on graph neural network and optimization strategy

Machine Learning technologies have obtained breakthrough in various fields, and medical information extraction has also successfully made great progress through deep learning methods. However, entity relationship overlap is a key issue and challenge in the field of medical entity relationship extraction. Hence, we propose an intelligent extraction method for Chinese medicine entity relationship through improving graph neural network and structure optimization strategy. We optimize model structure and introduce global pointer network. The sentence feature information is captured by attention mechanism and Bi-Long Short Term Memory (LSTM). Grammatical relations between entities are parsed using Graph Convolution Network (GCN) layer. Finally, multiple decoders are used for joint extraction of entity relations through the global pointer network. The model learns the graph structure data by GCN, while the challenge of entity relationship overlap is solved through using the pointer network. The experiments demonstrate that the model achieves 83.77% in terms of F1 value, which is better than other baseline models.

Learning Aligned Vertex Convolutional Networks for Graph Classification.

Graph convolutional networks (GCNs) are powerful tools for graph structure data analysis. One main drawback arising in most existing GCN models is that of the oversmoothing problem, i.e., the vertex features abstracted from the existing graph convolution operation have previously tended to be indistinguishable if the GCN model has many convolutional layers (e.g., more than two layers). To address this problem, in this article, we propose a family of aligned vertex convolutional network (AVCN) models that focus on learning multiscale features from local-level vertices for graph classification. This is done by adopting a transitive vertex alignment algorithm to transform arbitrary-sized graphs into fixed-size grid structures. Furthermore, we define a new aligned vertex convolution operation that can effectively learn multiscale vertex characteristics by gradually aggregating local-level neighboring aligned vertices residing on the original grid structures into a new packed aligned vertex. With the new vertex convolution operation to hand, we propose two architectures for the AVCN models to extract different hierarchical multiscale vertex feature representations for graph classification. We show that the proposed models can avoid iteratively propagating redundant information between specific neighboring vertices, restricting the notorious oversmoothing problem arising in most spatial-based GCN models. Experimental evaluations on benchmark datasets demonstrate the effectiveness.