Showing papers on "Network science published in 2021"

Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting

Abstract: While Graph Neural Networks (GNNs) have achieved remarkable results in a variety of applications, recent studies exposed important shortcomings in their ability to capture the structure of the underlying graph. It has been shown that the expressive power of standard GNNs is bounded by the Weisfeiler-Lehman (WL) graph isomorphism test, from which they inherit proven limitations such as the inability to detect and count graph substructures. On the other hand, there is significant empirical evidence, e.g. in network science and bioinformatics, that substructures are often informative for downstream tasks, suggesting that it is desirable to design GNNs capable of leveraging this important source of information. To this end, we propose a novel topologically-aware message passing scheme based on substructure encoding. We show that our architecture allows incorporating domain-specific inductive biases and that it is strictly more expressive than the WL test. Importantly, in contrast to recent works on the expressivity of GNNs, we do not attempt to adhere to the WL hierarchy; this allows us to retain multiple attractive properties of standard GNNs such as locality and linear network complexity, while being able to disambiguate even hard instances of graph isomorphism. We extensively evaluate our method on graph classification and regression tasks and show state-of-the-art results on multiple datasets including molecular graphs and social networks.

Foundations and Modeling of Dynamic Networks Using Dynamic Graph Neural Networks: A Survey

Abstract: Dynamic networks are used in a wide range of fields, including social network analysis, recommender systems and epidemiology. Representing complex networks as structures changing over time allow network models to leverage not only structural but also temporal patterns. However, as dynamic network literature stems from diverse fields and makes use of inconsistent terminology, it is challenging to navigate. Meanwhile, graph neural networks (GNNs) have gained a lot of attention in recent years for their ability to perform well on a range of network science tasks, such as link prediction and node classification. Despite the popularity of graph neural networks and the proven benefits of dynamic network models, there has been little focus on graph neural networks for dynamic networks. To address the challenges resulting from the fact that this research crosses diverse fields as well as to survey dynamic graph neural networks, this work is split into two main parts. First, to address the ambiguity of the dynamic network terminology we establish a foundation of dynamic networks with consistent, detailed terminology and notation. Second, we present a comprehensive survey of dynamic graph neural network models using the proposed terminology.

E-LSTM-D: A Deep Learning Framework for Dynamic Network Link Prediction

Abstract: Predicting the potential relations between nodes in networks, known as link prediction, has long been a challenge in network science. However, most studies just focused on link prediction of static network, while real-world networks always evolve over time with the occurrence and vanishing of nodes and links. Dynamic network link prediction (DNLP) thus has been attracting more and more attention since it can better capture the evolution nature of networks, but still most algorithms fail to achieve satisfied prediction accuracy. Motivated by the excellent performance of long short-term memory (LSTM) in processing time series, in this article, we propose a novel encoder-LSTM-decoder (E-LSTM-D) deep learning model to predict dynamic links end to end. It could handle long-term prediction problems, and suits the networks of different scales with fine-tuned structure. To the best of our knowledge, it is the first time that LSTM, together with an encoder–decoder architecture, is applied to link prediction in dynamic networks. This new model is able to automatically learn structural and temporal features in a unified framework, which can predict the links that never appear in the network before. The extensive experiments show that our E-LSTM-D model significantly outperforms newly proposed DNLP methods and obtain the state-of-the-art results.

Percolation on complex networks: Theory and application

Abstract: In the last two decades, network science has blossomed and influenced various fields, such as statistical physics, computer science, biology and sociology, from the perspective of the heterogeneous interaction patterns of components composing the complex systems. As a paradigm for random and semi-random connectivity, percolation model plays a key role in the development of network science and its applications. On the one hand, the concepts and analytical methods, such as the emergence of the giant cluster, the finite-size scaling, and the mean-field method, which are intimately related to the percolation theory, are employed to quantify and solve some core problems of networks. On the other hand, the insights into the percolation theory also facilitate the understanding of networked systems, such as robustness, epidemic spreading, vital node identification, and community detection. Meanwhile, network science also brings some new issues to the percolation theory itself, such as percolation of strong heterogeneous systems, topological transition of networks beyond pairwise interactions, and emergence of a giant cluster with mutual connections. So far, the percolation theory has already percolated into the researches of structure analysis and dynamic modeling in network science. Understanding the percolation theory should help the study of many fields in network science, including the still opening questions in the frontiers of networks, such as networks beyond pairwise interactions, temporal networks, and network of networks. The intention of this paper is to offer an overview of these applications, as well as the basic theory of percolation transition on network systems.

Increasing the efficiency of knowledge transfer in an Italian tourism system: a network approach

Abstract: Efficient transferring information and knowledge play a fundamental strategic role in a tourism system. This is especially important in critical times where efficient collaboration practices and a ...

Survey on graph embeddings and their applications to machine learning problems on graphs

Abstract: Dealing with relational data always required significant computational resources, domain expertise and task-dependent feature engineering to incorporate structural information into a predictive model. Nowadays, a family of automated graph feature engineering techniques has been proposed in different streams of literature. So-called graph embeddings provide a powerful tool to construct vectorized feature spaces for graphs and their components, such as nodes, edges and subgraphs under preserving inner graph properties. Using the constructed feature spaces, many machine learning problems on graphs can be solved via standard frameworks suitable for vectorized feature representation. Our survey aims to describe the core concepts of graph embeddings and provide several taxonomies for their description. First, we start with the methodological approach and extract three types of graph embedding models based on matrix factorization, random-walks and deep learning approaches. Next, we describe how different types of networks impact the ability of models to incorporate structural and attributed data into a unified embedding. Going further, we perform a thorough evaluation of graph embedding applications to machine learning problems on graphs, among which are node classification, link prediction, clustering, visualization, compression, and a family of the whole graph embedding algorithms suitable for graph classification, similarity and alignment problems. Finally, we overview the existing applications of graph embeddings to computer science domains, formulate open problems and provide experiment results, explaining how different networks properties result in graph embeddings quality in the four classic machine learning problems on graphs, such as node classification, link prediction, clustering and graph visualization. As a result, our survey covers a new rapidly growing field of network feature engineering, presents an in-depth analysis of models based on network types, and overviews a wide range of applications to machine learning problems on graphs.

GC-LSTM: graph convolution embedded LSTM for dynamic network link prediction

Abstract: Dynamic network link prediction is becoming a hot topic in network science, due to its wide applications in biology, sociology, economy and industry. However, it is a challenge since network structure evolves with time, making long-term prediction of adding/deleting links especially difficult. Inspired by the great success of deep learning frameworks, especially the convolution neural network (CNN) and long short-term memory (LSTM) network, we propose a novel end-to-end model with a Graph Convolution Network(GCN) embedded LSTM, named GC-LSTM, for dynamic network link prediction. Thereinto, LSTM is adopted as the main framework to learn the temporal features of all snapshots of a dynamic network. While for each snapshot, GCN is applied to capture the local structural properties of nodes as well as the relationship between them. One benefit is that our GC-LSTM can predict both added and removed links, making it more practical in reality, while most existing dynamic link prediction methods can only handle removed links. Extensive experiments demonstrated that GC-LSTM achieves outstanding performance and outperforms existing state-of-the-art methods.

A Survey on Centrality Metrics and Their Network Resilience Analysis

Abstract: Centrality metrics have been studied in the network science research. They have been used in various networks, such as communication, social, biological, geographic, or contact networks under different disciplines. In particular, centrality metrics have been used in order to study and analyze targeted attack behaviors and investigated their effect on network resilience. Although a rich volume of centrality metrics has been developed from 1940s, only some centrality metrics (e.g., degree, betweenness, or cluster coefficient) have been commonly in use. This paper aims to introduce various existing centrality metrics and discusses their applicabilities in various networks. In addition, we conducted extensive simulation study in order to demonstrate and analyze the network resilience of targeted attacks using the surveyed centrality metrics under four real network topologies. We also discussed algorithmic complexity of centrality metrics surveyed in this work. Through the extensive experiments and discussions of the surveyed centrality metrics, we encourage their use in solving various computing and engineering problems in networks.

Measuring Node Contribution to Community Structure With Modularity Vitality

Abstract: Community-aware centrality is an emerging research area in network science concerned with the importance of nodes in relation to community structure. Measures are a function of a network's structure and a given partition. Previous approaches extend classical centrality measures to account for community structure with little connection to community detection theory. In contrast, we propose cluster-quality vitality measures, i.e., modularity vitality, a community-aware measure which is well-grounded in both centrality and community detection theory. Modularity vitality quantifies positive and negative contributions to community structure, which indicate a node's role as a community bridge or hub. We derive a computationally efficient method of calculating modularity vitality for all nodes in $O(M+NC)$ time, where $C$ is the number of communities. We systematically fragment networks by removing central nodes, and find that modularity vitality consistently outperforms existing community-aware centrality measures. We show measures well-grounded in community theory are over 8 times more effective on a million-node infrastructure network. This result does not generalize to social media communication networks, which exhibit extreme robustness to all community-aware centrality attacks. This robustness suggests that user-based interventions to mitigate misinformation diffusion will be ineffective. Finally, we demonstrate that modularity vitality provides a new approach to community-deception.

A generalized gravity model for influential spreaders identification in complex networks

Abstract: How to identify influential spreaders in complex networks is still an open issue in network science. Many approaches from different perspectives have been proposed to identify vital nodes in complex networks. In these models, gravity model is an effective model to find vital nodes based on local information and path information. However, gravity model just uses degree of the node to judge local information, which is not precise. To address this issue, a generalized gravity model is proposed in this paper. Generalized gravity model measures local information from both local clustering coefficient and degree of each node, which is more comprehensive. Also, parameter α can be modified in different applications to get better performance. Generalized gravity model can degenerate into gravity model when α = 0 . Promising results from experiments on four real-world networks demonstrate the effectiveness of the proposed method.

Network-based brain computer interfaces: principles and applications

Abstract: Brain-computer interfaces (BCIs) make possible to interact with the external environment by decoding the mental intention of individuals. BCIs can therefore be used to address basic neuroscience questions but also to unlock a variety of applications from exoskeleton control to neurofeedback (NFB) rehabilitation. In general, BCI usability critically depends on the ability to comprehensively characterize brain functioning and correctly identify the user's mental state. To this end, much of the efforts have focused on improving the classification algorithms taking into account localized brain activities as input features. Despite considerable improvement BCI performance is still unstable and, as a matter of fact, current features represent oversimplified descriptors of brain functioning. In the last decade, growing evidence has shown that the brain works as a networked system composed of multiple specialized and spatially distributed areas that dynamically integrate information. While more complex, looking at how remote brain regions functionally interact represents a grounded alternative to better describe brain functioning. Thanks to recent advances in network science, i.e. a modern field that draws on graph theory, statistical mechanics, data mining and inferential modelling, scientists have now powerful means to characterize complex brain networks derived from neuroimaging data. Notably, summary features can be extracted from these networks to quantitatively measure specific organizational properties across a variety of topological scales. In this topical review, we aim to provide the state-of-the-art supporting the development of a network theoretic approach as a promising tool for understanding BCIs and improve usability.

Nonbacktracking Eigenvalues under Node Removal: X-Centrality and Targeted Immunization

Abstract: The nonbacktracking matrix and its eigenvalues have many applications in network science and graph mining, such as node and edge centrality, community detection, length spectrum theory, graph dista...

Cluster-based network modeling—From snapshots to complex dynamical systems

Abstract: We propose a universal method for data-driven modeling of complex nonlinear dynamics from time-resolved snapshot data without prior knowledge. Complex nonlinear dynamics govern many fields of science and engineering. Data-driven dynamic modeling often assumes a low-dimensional subspace or manifold for the state. We liberate ourselves from this assumption by proposing cluster-based network modeling (CNM) bridging machine learning, network science, and statistical physics. CNM describes short- and long-term behavior and is fully automatable, as it does not rely on application-specific knowledge. CNM is demonstrated for the Lorenz attractor, ECG heartbeat signals, Kolmogorov flow, and a high-dimensional actuated turbulent boundary layer. Even the notoriously difficult modeling benchmark of rare events in the Kolmogorov flow is solved. This automatable universal data-driven representation of complex nonlinear dynamics complements and expands network connectivity science and promises new fast-track avenues to understand, estimate, predict, and control complex systems in all scientific fields.

Identifying influential nodes in weighted complex networks using an improved WVoteRank approach

Abstract: Influence maximization is an important research problem in the field of network science because of its business value. It requires the strategic selection of seed nodes called “influential nodes,” such that information originating from these nodes can reach numerous nodes in the network. Many real-world networks, such as transportation, communication, and social networks, are weighted networks. Influence maximization in a weighted network is more challenging compared to that in an unweighted network. Many methods, such as weighted degree rank, weighted h-index, weighted betweenness, and weighted VoteRank techniques, have been used to order the nodes based on their spreading capabilities in weighted networks. The VoteRank method is a popular method for finding influential nodes in an unweighted network using the idea of a voting scheme. Recently, the WVoteRank method was proposed to find the seed nodes; it extends the idea of the VoteRank method by considering the edge weights. This method considers only 1-hop neighbors to calculate the voting score of every node. In this study, we propose an improved WVoteRank method based on an extended neighborhood concept, which takes the 1-hop neighbors as well as 2-hop neighbors into account for the voting process to decide influential nodes in a weighted network. We also extend our proposed approach to unweighted networks. We compare the performance of the proposed improved WVoteRank method against the popular centrality measures, weighted degree, weighted closeness, weighted betweenness, weighted h-index, and weighted VoteRank on several real-life and synthetic datasets of diverse sizes and properties. We utilize the widely used stochastic susceptible–infected–recovered information diffusion model to calculate the infection scale, the final infected scale as a function of time, and the average distance between spreaders. The simulation results reveal that the proposed method, improved WVoteRank, considerably outperforms the other methods described above, including the recent WVoteRank.

Review of social influence in crisis communications and evacuation decision-making

Abstract: Topography and dynamics of real networks' enable network agents to alter their functional behavior. Theoretical and analytical advancements in network science have furthered our understanding of the effects of social network characteristics on peer influence and engagement. Influence of social network occurs when network players alter their decisions and behavior based on others’ influence in the social network which is evident in different disciplines. Crisis communication networks have significant impact during disasters as people often spread pertinent information in social media due to presence of limited access to conventional information sources. Existing researches in social science and sociology indicate that social networks benefit spreading warning message and disseminate information about an imminent risk, nevertheless, the existing studies do not provide enough understanding on how to quantify such influences and how this map into decision-making during emergency evacuations. This study provides a robust review of the studies exploring how individuals are socially influenced, both on-line and off-line, while communicating risk during extreme weather events such as hurricanes. The scope of this review primarily includes studies that look into how our social networks influence the way we decide to evacuate and how crisis information spread from one agent to another agent in a network. The insights and findings obtained through this comprehensive review will be useful to diverse set of stakeholders such as emergency managers, planners, policy makers and practitioners. These include identifying and implementing targeted strategies for different groups of people in similar crisis events based on their social network properties, interactions, and activities.

A Scalable Redefined Stochastic Blockmodel

Abstract: Stochastic blockmodel (SBM) is a widely used statistical network representation model, with good interpretability, expressiveness, generalization, and flexibility, which has become prevalent and important in the field of network science over the last years. However, learning an optimal SBM for a given network is an NP-hard problem. This results in significant limitations when it comes to applications of SBMs in large-scale networks, because of the significant computational overhead of existing SBM models, as well as their learning methods. Reducing the cost of SBM learning and making it scalable for handling large-scale networks, while maintaining the good theoretical properties of SBM, remains an unresolved problem. In this work, we address this challenging task from a novel perspective of model redefinition. We propose a novel redefined SBM with Poisson distribution and its block-wise learning algorithm that can efficiently analyse large-scale networks. Extensive validation conducted on both artificial and real-world data shows that our proposed method significantly outperforms the state-of-the-art methods in terms of a reasonable trade-off between accuracy and scalability.1

Beyond COVID-19: network science and sustainable exit strategies

Abstract: On May 28th and 29th, a two day workshop was held virtually, facilitated by the Beyond Center at ASU and Moogsoft Inc. The aim was to bring together leading scientists with an interest in network science and epidemiology to attempt to inform public policy in response to the COVID-19 pandemic. Epidemics are at their core a process that progresses dynamically upon a network, and are a key area of study in network science. In the course of the workshop a wide survey of the state of the subject was conducted. We summarize in this paper a series of perspectives of the subject, and where the authors believe fruitful areas for future research are to be found.

Tunable Eigenvector-Based Centralities for Multiplex and Temporal Networks

Abstract: Characterizing the importances (i.e., centralities) of nodes in social, biological, and technological networks is a core topic in both network analysis and data science. We present a linear-algebra...

Emergence of hierarchy in networked endorsement dynamics.

Abstract: Many social and biological systems are characterized by enduring hierarchies, including those organized around prestige in academia, dominance in animal groups, and desirability in online dating. Despite their ubiquity, the general mechanisms that explain the creation and endurance of such hierarchies are not well understood. We introduce a generative model for the dynamics of hierarchies using time-varying networks, in which new links are formed based on the preferences of nodes in the current network and old links are forgotten over time. The model produces a range of hierarchical structures, ranging from egalitarianism to bistable hierarchies, and we derive critical points that separate these regimes in the limit of long system memory. Importantly, our model supports statistical inference, allowing for a principled comparison of generative mechanisms using data. We apply the model to study hierarchical structures in empirical data on hiring patterns among mathematicians, dominance relations among parakeets, and friendships among members of a fraternity, observing several persistent patterns as well as interpretable differences in the generative mechanisms favored by each. Our work contributes to the growing literature on statistically grounded models of time-varying networks.

Teaching sustainability as complex systems approach: a sustainable development goals workshop

Abstract: Approaches to solving sustainability problems require a specific problem-solving mode, encompassing the complexity, fuzziness and interdisciplinary nature of the problem. This paper aims to promote a complex systems’ view of addressing sustainability problems, in particular through the tool of network science, and provides an outline of an interdisciplinary training workshop.,The topic of the workshop is the analysis of the Sustainable Development Goals (SDGs) as a political action plan. The authors are interested in the synergies and trade-offs between the goals, which are investigated through the structure of the underlying network. The authors use a teaching approach aligned with sustainable education and transformative learning.,Methodologies from network science are experienced as valuable tools to familiarise students with complexity and to handle the proposed case study.,To the best of the authors’ knowledge, this is the first work which uses network terminology and approaches to teach sustainability problems. This work highlights the potential of network science in sustainability education and contributes to accessible material.

Is the Mind a Network? Maps, Vehicles, and Skyhooks in Cognitive Network Science.

Abstract: Cognitive researchers often carve cognition up into structures and processes. Cognitive processes operate on structures, like vehicles driving over a map. Language alongside semantic and episodic memory are proposed to have structure, as are perceptual systems. Over these structures, processes operate to construct memory and solve problems by retrieving and manipulating information. Network science offers an approach to representing cognitive structures and has made tremendous inroads into understanding the nature of cognitive structure and process. But is the mind a network? If so, what kind? In this article, we briefly review the main metaphors, assumptions, and pitfalls prevalent in cognitive network science (maps and vehicles; one network/process to rule them all), highlight the need for new metaphors that elaborate on the map-and-vehicle framework (wormholes, skyhooks, and generators), and present open questions in studying the mind as a network (the challenge of capturing network change, what should the edges of cognitive networks be made of, and aggregated vs. individual-based networks). One critical lesson of this exercise is that the richness of the mind as network approach makes it a powerful tool in its own right; it has helped to make our assumptions more visible, generating new and fascinating questions, and enriching the prospects for future research. A second lesson is that the mind as a network-though useful-is incomplete. The mind is not a network, but it may contain them.

Graph Metrics for Network Robustness—A Survey

Abstract: Research on the robustness of networks, and in particular the Internet, has gained critical importance in recent decades because more and more individuals, societies and firms rely on this global network infrastructure for communication, knowledge transfer, business processes and e-commerce. In particular, modeling the structure of the Internet has inspired several novel graph metrics for assessing important topological robustness features of large complex networks. This survey provides a comparative overview of these metrics, presents their strengths and limitations for analyzing the robustness of the Internet topology, and outlines a conceptual tool set in order to facilitate their future adoption by Internet research and practice but also other areas of network science.

A modified label propagation algorithm for community detection in attributed networks

Abstract: Community detection is an important problem in network science that discovers highly clustered groups of nodes having similar properties. Label propagation algorithm (LPA) is one of the popular clustering techniques that has attracted much attention due to its efficiency and non-dependence on parameters. Despite its advantages, an important limitation of LPA is the randomness in grouping nodes that leads to instability and the formation of large communities. In this study, we propose four variants based on LPA to overcome the random community allocation problem, henceforth generating better clusters. These variants utilize link strength and node attribute information to enhance the quality of detected communities. Furthermore, the proposed variants require no parameter for categorical attributes and only one parameter (constant for all the networks) for continuous attributes. Finally, the best results are obtained by Variant I having a maximum Normalized Mutual Information score of 0.86, 0.88 on the two synthetic networks.