Graph Topology Research Articles

Multi-Knowledge Graph and Multi-View Entity Feature Learning for Predicting Drug-Related Side Effects.

Computational prediction of potential drug side effects plays a crucial role in reducing health risks for clinical patients and accelerating drug development. Recent methods have constructed heterogeneous graphs that represent drugs and their side effects, utilizing graph learning strategies such as graph convolutional networks to predict associations between them. However, existing approaches fail to fully exploit the diverse topologies and semantics present in multiple knowledge graphs. We propose MVDSA, a novel multi-view drug-side effect association prediction model. Our approach integrates multiple relationship semantics, local topologies of knowledge graphs, and multi-view features of drug-side effect entity pairs. First, we constructed two knowledge graphs based on drug functional and structural similarity, side effect similarity, and drug-side effect associations. These knowledge graphs capture the topological and semantic connections between drug and side effect entities from diverse perspectives. Second, considering the diverse similarities and associations between entities, we designed a space-sensitive learning strategy where a relation-gated semantic encoder is constructed for each type of relationship. This encoder adaptively adjusts the contribution of each entity feature to the relational semantic representation, facilitating the learning of entity-specific semantic features within each relational space. Third, for the two knowledge graphs, given the multiple types of connections between head and tail entities, we propose a connection-sensitive tail entity attention mechanism to integrate these diverse semantic relationships. To capture the contribution of different knowledge graphs to entity feature learning, we designed a knowledge graph-level attention mechanism to adaptively fuse the enhanced features from multiple knowledge graphs. Finally, we propose a multi-view enhanced multi-layer perceptron (MLP) strategy to encode the features of drug-side effect pairs from three perspectives and capture the potential associations between entities. Extensive experiments demonstrate that MVDSA outperforms 10 state-of-the-art methods in predicting drug-side effect associations. Ablation studies validate the contributions of the proposed innovations to improved prediction performance. Additionally, case studies on candidate side effects for five drugs highlight MVDSA's capability to discover potential drug-side effect associations.

Scalable edge clustering of dynamic graphs via weighted line graphs

Abstract Timestamped relational datasets consisting of records (or connections) between pairs of entities are ubiquitous in network science. For applications like peer-to-peer communication, email, various social network interactions, and computer network security, it is useful to organize these records into groups based on how and when they are occurring. Weighted line graphs offer a natural way to model how records are related in such datasets but for large real-world graph topologies, building and utilizing the line graph is prohibitively expensive. We present the framework to cluster the edges of a dynamic graph via the associated line graph that contains two major contributions. The first is a method to work with the line graph implicitly and the second is a distributed scale implementation of an agglomerative hierarchical graph clustering algorithm. We outline a novel hierarchical dynamic graph edge clustering approach that efficiently breaks massive relational datasets into small sets of edges containing events at various timescales. This is in stark contrast to traditional graph clustering algorithms that prioritize highly connected (clique-like) community structures. Our approach relies on constructing a sufficient subgraph of a weighted line graph and applying a hierarchical agglomerative clustering. This approach is related to scalable techniques from spatial clustering, nonlinear-dimension reduction, topological data analysis, and draws particular inspiration from HDBSCAN. As an edge clustering, this method yields an overlapping node clustering. Our algorithm is parallelizable and we demonstrate efficient clustering of a billion-scale, real-world dynamic graph into small edge sets that correlate in topology and time. The entire clustering process for a graph with tens of billions of edges takes just a few minutes of run time on 256 nodes of a distributed compute environment. We argue how the output of the edge clustering is useful for a multitude of data visualization and powerful machine learning tasks, both involving the original massive dynamic graph data and metadata associated with the nodes and edges. Finally, we describe how this approach can be extended to dynamic hypergraphs and dynamic graphs/hypergraphs with unstructured data living on vertices and edges.

Energy and Degree Sum Energy of Non-coprime Graphs on Dihedral Groups

Research on graphs has increasingly garnered attention in recent years.This research focuses on graph representations, with particular emphasis on non-coprime graphs within the dihedral group D_{2n} with n = p^k, prime numbers, $k \in \mathbb{Z}^+$. The non-coprime graph of a group G is defined as a graph in which the vertex set is G \{e}, and two distinct vertices r and s are connected by an edge if gcd(|r|,|s|) =\= 1. Specifically, this research examines the adjacency matrix energy and the degree sum energy of non-coprime graphs on dihedral groups. With the extensive application of chemical topological graphs in the field of chemistry, it is hoped that they can assist in the numerical analysis of chemical compounds used in healthcare, such as the analysis of vaccines for the COVID-19 epidemic.

Consensus-Based Optimal Operation of Multi-Agent Renewable Energy Hubs Considering Various Graph Topologies

Consensus-Based Optimal Operation of Multi-Agent Renewable Energy Hubs Considering Various Graph Topologies

A temporal-spatial multi-order weighted graph convolution network with refined feature topology graph for imbalance fault diagnosis of rotating machinery

A temporal-spatial multi-order weighted graph convolution network with refined feature topology graph for imbalance fault diagnosis of rotating machinery

Topological Graph Simplification Solutions to the Street Intersection Miscount Problem

ABSTRACTStreet intersection counts and densities are ubiquitous measures in transport geography and planning. However, typical street network data and typical street network analysis tools can substantially overcount them. This article explains the three main reasons why this happens and presents solutions to each. It contributes algorithms to automatically simplify spatial graphs of urban street networks—via edge simplification and node consolidation—resulting in faster parsimonious models and more accurate network measures like intersection counts and densities, street segment lengths, and node degrees. These algorithms' information compression improves downstream graph analytics' memory and runtime efficiency, boosting analytical tractability without loss of model fidelity. Finally, this article validates these algorithms and empirically assesses intersection count biases worldwide to demonstrate the problem's widespread prevalence. Without consolidation, traditional methods would overestimate the median urban area intersection count by 14%. However, this bias varies drastically across regions, underscoring these algorithms' importance for consistent comparative empirical analyses.

QSPR analysis of amino acids for the family of Gourava indices.

Amino acids are chemical molecules that act as the building blocks of proteins and perform critical functions in biological processes. Their two main functional groups, an amino group (-NH2) and a carboxyl group (-COOH) as well as a changeable side chain (R group) that controls the unique characteristics of each amino acid are what define them. Because they can serve as building blocks for a variety of macromolecules and support biological activities in a variety of ways, amino acids have a wide range of uses in biology, medicine, industry and nutrition. Quantitative Structure-Activity/Property Relationships employ graph invariants to model physicochemical properties of substances. Topological indices are a reliable and computationally efficient technique to express molecular structures and properties, making them indispensable in theoretical and applied chemistry. Gourava indices are valuable mathematical tools that provide deeper insights into the topology and structure of networks and molecular graphs, resulting in improved decision-making and efficiency in research and applications. In this article, Gourva, hyper Gourava, alpha Gourava and gamma Gourava indices are presented and calculated. Curvilinear and multilinear regression models for predicting physicochemical characteristics of amino acids are analyzed.

An edge enhancement graph neural network model with node discrimination for knowledge graph representation learning

The vectorized representation of a knowledge graph is essential for effectively utilizing its implicit knowledge. Graph neural networks (GNNs) are particularly adept at learning graph representations due to their ability to handle graph topologies. However, GNN-based approaches face two main challenges: first, they fail to differentiate between the types of adjacent nodes during the information aggregation process; second, the edge representations lack relational semantic information and fail to capture the characteristics of adjacent nodes. Conventional methods typically treat source and destination nodes as identical, ignoring the distinct information that arises from different node types. This results in a failure to accurately capture the various semantic features, leading to feature redundancy. Additionally, many existing methods derive edge representations through random initialization or linear transformations, which do not adequately reflect relational semantics and adjacent node information, resulting in ineffective edge representations.To address these limitations, we propose the Edge Enhancement GNN model with Node Discrimination (NDEE-GNN). This model establishes node discrimination information aggregation mechanisms for source and destination nodes, allowing for a deeper investigation into the impact of various adjacent node types. It also employs a specially designed information aggregation mechanism for each edge, incorporating relation and adjacent node features. Experimental results across multiple real-world datasets demonstrate that by discriminating node types and enhancing edge representations, NDEE-GNN can accurately capture and represent complex associations between entities and relations, significantly improving link prediction performance and outpacing other baseline models.

Interval-Shared Information Integration and False-Negative Association Reduction in Multi-Source MiRNA-Disease Association Prediction.

Numerous studies have demonstrated that microRNAs (miRNAs) play crucial roles in the development and progression of various diseases, making the identification of miRNA-disease associations (MDAs) essential for understanding human disease etiology. While several computational models have been developed to predict MDAs, challenges persist-particularly the limited consideration of information interactions among multi-source similarities and the presence of "false-negative" associations in the original topology. To address these issues, we propose ISFNMDA, a model designed to infer potential MDAs by leveraging multi-view collaborative learning for feature extraction and optimizing association topology through graph structure momentum contrastive learning. Specifically, multi-source similarities of miRNAs and diseases are mapped into a unified feature space via encoders. The Pearson correlation coefficient is employed to derive pairwise constraints between nodes, facilitating information interactions and constructing interval-shared information constraints. Subsequently, an inference graph learner models the representations to generate an inferred graph topology. By maximizing mutual information between the inferred topology and the original "false-negative" associations through momentum contrastive learning, the model effectively reduces spurious correlations. The final comprehensive representations and optimized graph structure are then used to predict potential MDAs. Experimental results demonstrate that ISFNMDA outperforms existing methods, and case studies further validate its predictive capability. The complete code and related materials for ISFNMDA is available at https://github.com/WDNokl/ISFNMDA.

Graph Contrastive Learning with Joint Spectral Augmentation of Attribute and Topology

As an essential technique for Graph Contrastive Learning (GCL), Graph Augmentation (GA) improves the generalization capability of the GCLs by introducing different forms of the same graph. To ensure information integrity, existing GA strategies have been designed to simultaneously process the two types of information available in graphs: node attributes and graph topology. Nonetheless, these strategies tend to augment the two types of graph information separately, ignoring their correlation, resulting in limited representation ability. To overcome this drawback, this paper proposes a novel GCL framework with a Joint spectrAl augMentation, named GCL-JAM. Motivated the equivalence between the graph learning objective on an attribute graph and the spectral clustering objective on the attribute-interpolated graph, the node attributes are first abstracted as another type of node to harmonize the node attributes and graph topology. The newly constructed graph is then utilized to perform spectral augmentation to capture the correlation during augmentation. Theoretically, the proposed joint spectral augmentation is proved to perturb more inter-class edges and noise attributes compared to separate augmentation methods. Extensive experiments on homophily and heterophily graphs validate the effectiveness and universality of GCL-JAM.

Highly Imperceptible Black-Box Graph Injection Attacks with Reinforcement Learning

Recent studies have revealed the vulnerability of graph neural networks (GNNs) to adversarial attacks. In practice, effectively attacking GNNs is not easy. Existing attack methods primarily focus on modifying the topology of the graph data. In many scenarios, attackers do not have the authority to manipulate the graph's topology, making such attacks challenging to execute. Although node injection attacks are more feasible than modifying the topology, current injection attacks rely on knowledge of the victim model's architecture. This dependency significantly degrades attack quality when there is inconsistency in the victim models. Moreover, the generation of injected nodes often lacks precise control over features, making it difficult to balance attack effectiveness and stealthiness. In this paper, we investigate a node injection attack under model-agnostic conditions and propose Targeted Evasion Attack via Node Injection (TEANI). Specifically, TEANI models the generation of adversarial nodes as a Markov process. Without considering the target model's structure, it guides the agent to select features that maximize attack effectiveness within a budget, based solely on the results of queries to a black-box model. Extensive experiments on real-world datasets and mainstream GNN models demonstrate that the proposed TEANI poses more effective and imperceptible threats than state-of-the-art attack methods.

Individually Stable Dynamics in Coalition Formation over Graphs

Coalition formation over graphs is a well studied class of games whose players are vertices and feasible coalitions must be connected subgraphs. In this setting, the existence and computation of equilibria, under various notions of stability, has attracted a lot of attention. However, the natural process by which players, starting from any feasible state, strive to reach an equilibrium after a series of unilateral improving deviations, has been less studied. We investigate the convergence of dynamics towards individually stable outcomes under the following perspective: what are the most general classes of preferences and graph topologies guaranteeing convergence? To this aim, on the one hand, we cover a hierarchy of preferences, ranging from the most general to a subcase of additively separable preferences, including individually rational and monotone cases. On the other hand, given that convergence may fail in graphs admitting a cycle even in our most restrictive preference class, we analyze acyclic graph topologies such as trees, paths, and stars.

THGNets: Constrained Temporal Hypergraphs and Graph Neural Networks in Hyperbolic Space for Information Diffusion Prediction

Information diffusion prediction aims to predict the next infected user in the information diffusion, which is a critical task to understand how information spreads on social platforms. Existing methods mainly focus on the sequences or topology structure in euclidean space. However, they fail to sufficiently consider the hierarchical structure or power-law structure of the underlying topology of information cascade graphs and social networks, resulting in distortion of user features. To tackle above issue, we propose an innovative Constrained Temporal Hypergraphs and Graph Neural Networks (THGNets) framework that is tailored for information diffusion prediction. Specifically, we introduce hyperbolic temporal hypergraphs neural network to alleviate the distortion of user features by hyperbolic hierarchical learning in information cascades. Additionally, it also captures high-order dynamic interaction patterns between users and further integrates the time-consistency constraint mechanism to mitigate the instability and non-smoothness of user features in latent space. In parallel, we apply the hyperbolic graph neural network to investigate the hierarchical structure and user homogeneity on social networks, enhancing our understanding of social relationships. Moreover, hyperbolic gated recurrent units are employed to capture the potential dependency relationships between contextual users. Experiments conducted on four public datasets demonstrate that the proposed THGNets significantly outperform the existing methods, thereby validating the superiority and rationality of our approach.

GNN-Transformer Cooperative Architecture for Trustworthy Graph Contrastive Learning

Graph contrastive learning (GCL) has become a hot topic in the field of graph representaion learning. In contrast to traditional supervised learning relying on a large number of labels, GCL exploits augmentation techniques to generate multiple views and positive/negative pairs, both of which greatly influence the performance. Unfortunately, commonly used random augmentations may disturb the underlying semantics of graphs. Moreover, traditional GNNs, a type of widely employed encoders in GCL, are inevitably confronted with over-smoothing and over-squashing problems. To address these issues, we propose GNN-Transformer Cooperative Architecture for Trustworthy Graph Contrastive Learning (GTCA), which inherits the advantages of both GNN and Transformer, incorporating graph topology to obtain comprehensive graph representations. Theoretical analysis verifies the trustworthiness of the proposed method. Extensive experiments on benchmark datasets demonstrate state-of-the-art empirical performance.

TRACI: A Data-centric Approach for Multi-Domain Generalization on Graphs

Graph neural networks (GNNs) have gained superior performance in graph-based prediction tasks with a variety of applications such as social analysis and drug discovery. Despite the remarkable progress, their performance often degrades on test graphs with distribution shifts. Existing domain adaptation methods rely on unlabeled test graphs during optimization, limiting their applicability to graphs in the wild. Towards this end, this paper studies the problem of multi-domain generalization on graphs, which utilizes multiple source graphs to learn a GNN with high performance on unseen target graphs. We propose a new approach named Topological Adversarial Learning with Prototypical Mixup (TRACI) to solve the problem. The fundamental principle behind our TRACI is to produce virtual adversarial and mixed graph samples from a data-centric view. In particular, TRACI enhances GNN generalization by employing a gradient-ascent strategy that considers both label prediction entropy and graph topology to craft challenging adversarial samples. Additionally, it generates domain-agnostic node representations by characterizing class-graph pair prototypes through latent distributions and applying multi-sample prototypical Mixup for distribution alignment across graphs. We further provide theoretical analysis showing that TRACI reduces the model's excess risk. Extensive experiments on various benchmark datasets demonstrate that TRACI outperforms state-of-the-art baselines, validating its effectiveness.

ST-FiT: Inductive Spatial-Temporal Forecasting with Limited Training Data

Spatial-temporal graphs are widely used in a variety of real-world applications. Spatial-Temporal Graph Neural Networks (STGNNs) have emerged as a powerful tool to extract meaningful insights from this data. However, in real-world applications, most nodes may not possess any available temporal data during training. For example, the pandemic dynamics of most cities on a geographical graph may not be available due to the asynchronous nature of outbreaks. Such a phenomenon disagrees with the training requirements of most existing spatial-temporal forecasting methods, which jeopardizes their effectiveness and thus blocks broader deployment. In this paper, we propose to formulate a novel problem of inductive forecasting with limited training data. In particular, given a spatial-temporal graph, we aim to learn a spatial-temporal forecasting model that can be easily generalized onto those nodes without any available temporal training data. To handle this problem, we propose a principled framework named ST-FiT. ST-FiT consists of two key learning components: temporal data augmentation and spatial graph topology learning. With such a design, ST-FiT can be used on top of any existing STGNNs to achieve superior performance on the nodes without training data. Extensive experiments verify the effectiveness of ST-FiT in multiple key perspectives.

Visualization of physicochemical parameters' behavior in leachate, baseliner, and surface water during dry and rainy seasons at a sanitary landfill.

Landfill leachate, a major environmental contaminant, is influenced by multiple factors and can migrate through landfill systems, spreading over considerable distances and polluting surrounding ecosystems. This study utilized Ball Mapper, a topological data analysis tool, to qualitatively explore hidden relationships between physicochemical parameters in leachate, surface water, and the baseliner, which can aid in pollution monitoring. The resulting Ball Mapper topological graphs uncovered behavioral similarities and relationships among parameters across different seasonal conditions. The analysis effectively revealed underlying patterns and interconnections by clustering parameters with similar behavior into the same nodes and linking those with hidden similarities. Additionally, Spearman correlation was used to validate the Ball Mapper output, the analysis showed that baseliner and surface water had aweak linear relationship with leachate, except for PO₄3 (r = 0.99), SO₄2⁻(r = 0.71), TSS (r = 0.82), and pH (r = 0.95)in surface water across seasons, which could be as a result of runoff, sediment transport, and environmental factors rather than direct leachate infiltration. The study also demonstrated that while seasonal variations in precipitation influenced leachate volume and pollutant concentrations, the landfill's engineered barriers effectively mitigated the potential environmental impact of leachate migration. Ball Mapper successfully showed the hidden behavior that traditional clustering methods may miss, highlighting its potential as a valuable tool for environmental monitoring.

Towards Multimodal Sentiment Analysis via Hierarchical Correlation Modeling with Semantic Distribution Constraints

Sentiment analysis is rapidly advancing by utilizing various data modalities (e.g., text, video, and audio). However, most existing techniques only learn the atomic-level features that reflect strong correlations, while ignoring more complex compositions in multimodal data. Moreover, they also neglected the incongruity in semantic distribution among modalities. In light of this, we introduce a novel Hierarchical Correlation Modeling Network (HCMNet), which enhances the multimodal sentiment analysis by exploring both the atomic-level correlations based on dynamic attention reasoning and the composition-level correlations through topological graph reasoning. In addition, we also alleviate the impact of distributional inconsistencies between modalities from both atomic-level and composition-level perspectives. Specifically, we first design an atomic-level contrastive loss that constrains the semantic distribution across modalities to mitigate the atomic-level inconsistency. Then, we design a graph optimal transport module that integrates transport flows with different graphs to constrain the composition-level semantic distribution, thus reducing the inconsistency of compositional nodes. Experiments on three public benchmark datasets have demonstrated the superiority of the proposed model over the state-of-the-art methods.

Temporal Structural Preserving with Subtree Attention in Dynamic Graph Transformers

Dynamic graph learning is a rapidly developing area of research due to its widespread application in various real-world networks. Most existing works combine graph neural networks and sequential models to exploit the graph topology and the temporal information of dynamic graphs. However, these methods exhibit certain limitations in extracting local and global information and capturing fine-grained temporal structure in dynamic graphs. In this article, we present our novel framework, Dynamic Graph Subtree Attention, which is centralized by a learnable temporal edge sampling module and a lightweight attention operator to address the aforementioned issues. Our approach first constructs a temporal union graph for each time step using an adaptive edge sampling module, which preserves relevant interactions for our graph encoder to directly exploit fine-gained interactions across different times. Based on the temporal union graph, we further propose a subtree attention module that leverages the multi-hop representation and the self-attention mechanism to properly extract the local and global information from first- to high-order neighborhoods. To further reduce the computation complexity, the subtree module is equipped with a kernelized attention operation, which scales linearly with respect to the number of edges. By performing extensive experiments, we demonstrate the superiority of our proposed model in dynamic graph representation learning, as it consistently outperforms existing methods in future link prediction tasks. The code is publicly available at: https://github.com/minhduc1122002/DySubTree .

SCGG: Smart City Network Topology Graph Generator

ABSTRACTSmart cities use information and communication technology to promote citizen welfare and economic growth within a sustainable environment. To guarantee that different urban actors, including people, devices, companies, and governments, can communicate efficiently, securely, and reliably, a robust, adaptable network infrastructure is required. However, the increasing complexity of the systems involved poses a challenge to smart city network modeling. Network topology generators produce synthetic networks that can reflect the underlying properties of real‐world networks, providing a practical approach to designing, testing, and implementing complex systems such as smart cities, yet the limited number of network topology generators for smart city applications has long prevented the proper development, investigation, and evaluation of various network configurations. In this article, a novel Smart City Network Topology Graph Generator (SCGG) is proposed to create a pseudorandom topology that mimics real smart city networks. The main goal of SCGG is to generate a network topology for smart cities that captures the interconnectivity of several communication technologies, such as wireless sensor networks (WSN), Internet of Things (IoT), and cellular networks. The SCGG system is characterized by the number of clusters, the average number of nodes, the number of layers, and the node density. The general network architecture and path‐related variables of the generated topologies are evaluated based on different graph theory measures, focusing on both global graph‐level characteristics and local node‐level features. The experimental results, demonstrating high natural connectivity and a low spectral radius value, offer a reliable tool for optimizing and strengthening the behavior and performance of smart city networks under different conditions to improve their robustness, minimize the probability of disruptions or failures, and enhance overall efficiency to ensure a resilient network.