Dynamic Network Information Research Articles

Analyst network centrality, forecast accuracy, and persistent influence

ABSTRACT This paper explores how analysts’ forecasting behaviour is related to their centrality within a dynamic information network. In this network, analysts who issued coverage reports on the same listed firms in clusters are connected. The social learning hypothesis and social capital theory suggest that financial analysts could learn from other analyst forecasts and obtain information from analyst reports. Employing a dynamic complex network methodology, we focus on analysts’ network centrality – degree, betweenness, and closeness – to represent their information access based on a sample of 819,539 analyst forecasts in the Chinese A-share market from 2018 to 2022. Our findings suggest that analysts with more central positions in the network produce more accurate earnings-per-share forecasts and have a longer persistent influence on other analysts. Our results support the perspective that the diffusion of information among analysts affects their forecasts and reporting behaviour.

SCAN Algorithm to Optimize Dynamic Instructional Information Network for Predicting Student Behavior

With the integration of work, study and life on campus taking shape gradually in major universities across China, the concept of education from classroom to life is more widely accepted and the smart education model has become a trend in education informatization. However, most of the existing studies are not applicable to student behaviour data in the campus environment, and the temporal as well as cyclical characteristics in the data are not accessible in the student behaviour prediction problem. In this study, a hypergraph-based dynamic campus behaviour information network is designed to address the needs of the student behaviour prediction problem, and a student campus behaviour prediction algorithm is proposed in the dynamic campus behaviour information network-based student behaviour prediction problem. The effectiveness and rationality of the algorithm is verified through experiments with real campus data sets. The experimental results demonstrated that the periodic nature of the data acquired by the cycle gated cyclic unit module needs to be built on top of the snapshot gated cyclic unit module to help the algorithm achieve better results. The area under the curve of the algorithm proposed in the study achieves more advantageous results on both the 21-day and 35-day datasets. The cycle gated cyclic unit module of the student campus behaviour prediction algorithm proposed in this study can more effectively extract the cyclic features present in the dynamic campus behaviour information network and better accomplish the prediction of student campus behaviour.

Detecting tipping points of complex diseases by network information entropy.

The progression of complex diseases often involves abrupt and non-linear changes characterized by sudden shifts that trigger critical transformations. Identifying these critical states or tipping points is crucial for understanding disease progression and developing effective interventions. To address this challenge, we have developed a model-free method named Network Information Entropy of Edges (NIEE). Leveraging dynamic network biomarkers, sample-specific networks, and information entropy theories, NIEE can detect critical states or tipping points in diverse data types, including bulk, single-sample expression data. By applying NIEE to real disease datasets, we successfully identified critical predisease stages and tipping points before disease onset. Our findings underscore NIEE's potential to enhance comprehension of complex disease development.

Linkage vector autoregressive model

AbstractTo accommodate linkage effects of individuals, we develop a new linkage vector autoregressive (LAR) model for dynamic panel data. A main feature of the LAR model is incorporating dynamic network information in autoregressive time series modeling. The dynamic network can be given, or we can formulate the network links as a function of historical data, where unknown parameters of the function can be estimated from the data. We propose a simulation technique to check the stationarity condition of the LAR model and suggest a Bayesian Markov chain Monte Carlo method for estimation. Empirical results for the quarterly growth rates of gross domestic product (GDP) in 45 countries indicate that (i) the autoregressive (AR) coefficient for the aggregated growth rate is hard to distinguish from zero; (ii) a panel AR model with individual effects has a positive autocorrelation; and (iii) the alternative LAR models are preferred to the panel AR model. Depending on the specification of the linkage variables, the sign and size of the linkage effect can differ. The logistic linkage function has a flexible structure to accommodate the size of the linkage of individual GDP growth rates, and it strengthens the dynamics.

Community-enhanced Link Prediction in Dynamic Networks

The growing popularity of online social networks is quite evident nowadays and provides an opportunity to allow researchers in finding solutions for various practical applications. Link prediction is the technique of understanding network structure and identifying missing and future links in social networks. One of the well-known classes of methods in link prediction is a similarity-based method, which uses local and global topological information of the network to predict missing links. Some methods also exist based on quasi-local features to achieve a trade-off between local and global information on static networks. These quasi-local similarity-based methods are not best suited for considering community information in dynamic networks, failing to balance accuracy and efficiency. Therefore, a community-enhanced framework is presented in this article to predict missing links on dynamic social networks. First, a link prediction framework is presented to predict missing links using parameterized influence regions of nodes and their contribution in community partitions. Then, a unique feature set is generated using local, global, and quasi-local similarity-based as well as community information-based features. This feature set is further optimized using scoring-based feature selection methods to select only the most relevant features. Finally, four machine learning-based classification models are used for link prediction. The experiments are performed on six well-known dynamic networks and three performance metrics, and the results demonstrate that the proposed method outperforms the state-of-the-art methods.

On Predicting ESG Ratings Using Dynamic Company Networks

Environmental, social and governance (ESG) considerations play an increasingly important role due to the growing focus on sustainability globally. Entities, such as banks and investors, utilize ESG ratings of companies issued by specialized rating agencies to evaluate ESG risks of companies. The process of assigning ESG ratings by human analysts is however laborious and time intensive. Developing methods to predict ESG ratings could alleviate such challenges, allow ESG ratings to be generated in a more timely manner, cover more companies, and be more accessible. Most works study the effects of ESG ratings on target variables such as stock prices or financial fundamentals of companies, but few works study how different types of company information can be utilized to predict ESG ratings. Previous works also largely focus on using only the financial information of individual companies to predict ESG ratings, leaving out the different types of inter-company relationship networks. Such inter-company relationship networks are typically dynamic, i.e., they evolve across time. In this paper, we focus on utilizing dynamic inter-company relationships for ESG ratings prediction, and examine the relative importance of different financial and dynamic network information in this prediction task. Our analysis shows that utilizing dynamic inter-company network information, based on common director, common investor and news event-based knowledge graph relationships, can significantly improve ESG rating prediction performance. Robustness checks over different time-periods and different number of time-steps in the future further validate these insights.

Developing an agent-based model to minimize spreading of malicious information in dynamic social networks.

This research introduces a systematic and multidisciplinary agent-based model to interpret and simplify the dynamic actions of the users and communities in an evolutionary online (offline) social network. The organizational cybernetics approach is used to control/monitor the malicious information spread between communities. The stochastic one-median problem minimizes the agent response time and eliminates the information spread across the online (offline) environment. The performance of these methods was measured against a Twitter network related to an armed protest demonstration against the COVID-19 lockdown in Michigan state in May 2020. The proposed model demonstrated the dynamicity of the network, enhanced the agent level performance, minimized the malicious information spread, and measured the response to the second stochastic information spread in the network.

The Intelligentization of Second Language Acquisition Assisted Cognitive Linguistics Based on Internet Dynamic Information Network

This paper combs the basic concepts of dynamic system theory in detail, including the overall connectivity, nonlinearity, self-organization and attractive state of the system, and the sensitivity and difference of the initial state. And from the neurophysiological level, the hot issues of second language acquisition are discussed briefly, so as to provide a new idea for the research of second language acquisition. It is proposed that cognitive linguistics can provide coherent and appropriate theoretical guidance and method reference for second language acquisition. The deepening of second language acquisition research can enrich and test the theoretical assumptions of cognitive linguistics, and promote the continuous maturity and improvement of the theoretical system. Through the statistical analysis of the pre-test and post-test of the CET4 simulated test scores of the two groups of students, it is found that this training mode is helpful to improve the students' English ability.

Model-Independent Robust Consensus of Multiple Euler–Lagrange Systems

The robustness of multiple Euler–Lagrange systems (MELSs) measures the capability of maintaining coordination control performance when experiencing disturbance or faults. This article investigates a leader–follower robust consensus problem of MELSs, which experience time-varying input disturbance and uncertain communication link faults (CLFs). First of all, based on an adaptive control theory, we design fully distributed observers for estimating the dynamic and state of leader, which have robustness to CLFs. Then, an observer-based proportional–integral (PI) control protocol is designed to achieve consensus of MELSs with robustness to time-varying input disturbance. Different from the existing related results, this robust observer-based PI controller is fully distributed and model independent, which is irrelevant to any prior information (i.e., the structures and features) of agent dynamic or global network information. At last, the validity of the proposed theoretical results is confirmed by a simulation example.

Temporal link prediction via adjusted sigmoid function and 2-simplex structure

Temporal network link prediction is an important task in the field of network science, and has a wide range of applications in practical scenarios. Revealing the evolutionary mechanism of the network is essential for link prediction, and how to effectively utilize the historical information for temporal links and efficiently extract the high-order patterns of network structure remains a vital challenge. To address these issues, in this paper, we propose a novel temporal link prediction model with adjusted sigmoid function and 2-simplex structure (TLPSS). The adjusted sigmoid decay mode takes the active, decay and stable states of edges into account, which properly fits the life cycle of information. Moreover, the latent matrix sequence is introduced, which is composed of simplex high-order structure, to enhance the performance of link prediction method since it is highly feasible in sparse network. Combining the life cycle of information and simplex high-order structure, the overall performance of TLPSS is achieved by satisfying the consistency of temporal and structural information in dynamic networks. Experimental results on six real-world datasets demonstrate the effectiveness of TLPSS, and our proposed model improves the performance of link prediction by an average of 15% compared to other baseline methods.

Visual analysis method of foundation pit monitoring information based on BIM platform

In order to visually express the safety monitoring information of foundation pits and underground engineering, realize the efficient management of massive dynamic safety monitoring information during the construction of foundation pits and underground engineering, as well as assist safety analysis, a building information model (BIM)-based Foundation pit and underground engineering dynamic safety monitoring information integration and network visualization method is proposed in the article. Firstly, the research builds a three-dimensional BIM model of foundation pit engineering based on the analysis of the element composition of the three-dimensional virtual scene of the foundation pit and underground engineering. Then, apply the method of key field mapping to establish the dynamic coupling between the BIM model and the safety monitoring information. Finally, the research realizes the virtual display of the construction process based on the three-dimensional visualization function of BIM technology. Furthermore, combined with the actual situation, the corresponding system is developed and applied in a certain project, which realized the visual integration of dynamic information of engineering safety monitoring and BIM under the network environment, and provided a support platform for the safety analysis of foundation pits and underground engineering.

Stochastic Event-Triggered H∞ Control for Networked Systems Under Denial of Service Attacks

This article presents a novel stochastic event-triggered communication scheme (SETS) and a switching-like <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$H_{\infty }$ </tex-math></inline-formula> control method for networked control systems (NCSs) through an open bandwidth-limited network. To overcome the stochastic Denial of Service (DoS) attacks and save the limited network resource, a SETS is first proposed to decrease the number of packets transmitted while considering the malicious DoS attacks. Compared with the existing event-triggered schemes under a precondition that all triggered packets must be successfully transmitted, the proposed SETS has outstanding flexibility since it allows part event-triggered packets to be lost during the communication process. To fully use the dynamic features of communication in an open network, a switching-like control scheme is well designed, which can actively choose the different controller gains based on the current network Quality of Services (QoSs). Then, a networked closed-loop model is constructed, which considered both the effects of SETS and stochastic DoS attacks in a unified framework. Sufficient conditions for the existence of the switching-like controller are presented to ensure the stability of the networked control system while achieving the prescribed performance index. Gain matrices of the desired switching-like controller and the SETS parameters are reached in the light of the solutions to certain matrix inequalities. Compared with the existing time-invariant control strategy in a transmission interval, higher control performance can be expected since both the dynamic network information and the latest available state are well considered in the proposed communication and control framework. Finally, an illustrative example is given to verify the effectiveness of the proposed scheme.

Effects of Data Corruption on Network Identification Using Directed Information

Complex networked systems can be modeled and represented as graphs, with nodes representing the agents and the links describing the dynamic coupling between them. The fundamental objective of network identification for dynamic systems is to identify causal influence pathways. However, dynamically related data streams that originate from different sources are prone to corruption caused by asynchronous time-stamps, packet drops, and noise. In this article, we show that identifying causal structure using corrupt measurements results in the inference of spurious links. A necessary and sufficient condition that delineates the effects of corruption on a set of nodes is obtained. Our theory applies to nonlinear systems, and systems with feedback loops. Our results are obtained by the analysis of conditional directed information (DI) in dynamic Bayesian networks. We provide consistency results for the conditional DI estimator that we use by showing almost-sure convergence.

Dynamic Structural Role Node Embedding for User Modeling in Evolving Networks

Complex user behavior, especially in settings such as social media, can be organized as time-evolving networks. Through network embedding, we can extract general-purpose vector representations of these dynamic networks which allow us to analyze them without extensive feature engineering. Prior work has shown how to generate network embeddings while preserving the structural role proximity of nodes. These methods, however, cannot capture the temporal evolution of the structural identity of the nodes in dynamic networks. Other works, on the other hand, have focused on learning microscopic dynamic embeddings. Though these methods can learn node representations over dynamic networks, these representations capture the local context of nodes and do not learn the structural roles of nodes. In this article, we propose a novel method for learning structural node embeddings in discrete-time dynamic networks. Our method, called HR2vec , tracks historical topology information in dynamic networks to learn dynamic structural role embeddings. Through experiments on synthetic and real-world temporal datasets, we show that our method outperforms other well-known methods in tasks where structural equivalence and historical information both play important roles. HR2vec can be used to model dynamic user behavior in any networked setting where users can be represented as nodes. Additionally, we propose a novel method (called network fingerprinting) that uses HR2vec embeddings for modeling whole (or partial) time-evolving networks. We showcase our network fingerprinting method on synthetic and real-world networks. Specifically, we demonstrate how our method can be used for detecting foreign-backed information operations on Twitter.

Reducing Uncertainty in the Onset of Combustion Instabilities Using Dynamic Pressure Information and Bayesian Neural Networks

Abstract Modern low-emission combustion systems with improved fuel-air mixing are more prone to combustion instabilities and, therefore, use advanced control methods to balance minimum NOx emissions and the presence of thermoacoustic combustion instabilities. The exact operating conditions at which the system encounters an instability are uncertain because of sources of stochasticity, such as turbulent combustion, and the influence of hidden variables, such as unmeasured wall temperatures or differences in machine geometry within manufacturing tolerances. Practical systems tend to be more elaborate than laboratory systems and tend to have less instrumentation, meaning that they suffer more from uncertainty induced by hidden variables. In many commercial systems, the only direct measurement of the combustor comes from a dynamic pressure sensor. In this study, we train a Bayesain Neural Network to predict the probability of onset of thermoacoustic instability at various times in the future, using only dynamic pressure measurements and the current operating condition. We show that on a practical system, the error in the onset time predicted by the Bayesain Neural Networks is 45% lower than the error when using the operating condition alone and more informative than the warning provided by commonly used precursor detection methods. This is demonstrated on two systems: (i) a premixed hydrogen/methane annular combustor, where the hidden variables are wall temperatures that depend on the rate of change of operating condition, and (ii) full-scale prototype combustion system, where the hidden variables arise from differences between the systems.

Leave or not leave? Group members’ departure prediction in dynamic information networks

• Group members’ departure prediction in dynamic information networks is meaningful. • Only utilizing neighborhood information causes precision loss. • A novel group-combined activeness score of each user is proposed. • An unsupervised prediction algorithm with a sliding window is presented. • Experiments show that our algorithm effectively improves prediction precision. Dynamic information networks, containing evolving nodes and links, exist in various applications. For example, in a Facebook network, nodes represent users, links represent friendship, and users often form different groups. Over time, some users will leave some groups. Thus, for both users and groups, it’s meaningful to predict which users would leave which groups. Existing studies consider that a user is more likely to leave if most of his/her friends leave. However, in reality, the low-degree nodes usually make up the majority of all nodes and there exist some users with very few friends but keeping staying in a group. Therefore, it might lead to precision loss if only neighborhood information is utilized, but previous work ignored this. To improve prediction precision, we firstly introduce novel definitions of a group’s activeness and a user’s own activeness respectively. Then we propose the group-combined activeness score of each user so that a user with a lower score would be more possible to leave. After that, we present an unsupervised prediction algorithm to continuously predict group members’ departure behaviors in a dynamic information network. Experiments on several real datasets show the effectiveness, efficiency and superiority of our algorithm compared with the state-of-the-art competitors.

Perspectives on Organelle Interaction, Protein Dysregulation, and Cancer Disease.

In recent decades, compelling evidence has emerged showing that organelles are not static structures but rather form a highly dynamic cellular network and exchange information through membrane contact sites. Although high-throughput techniques facilitate identification of novel contact sites (e.g., organelle-organelle and organelle-vesicle interactions), little is known about their impact on cellular physiology. Moreover, even less is known about how the dysregulation of these structures impacts on cellular function and therefore, disease. Particularly, cancer cells display altered signaling pathways involving several cell organelles; however, the relevance of interorganelle communication in oncogenesis and/or cancer progression remains largely unknown. This review will focus on organelle contacts relevant to cancer pathogenesis. We will highlight specific proteins and protein families residing in these organelle-interfaces that are known to be involved in cancer-related processes. First, we will review the relevance of endoplasmic reticulum (ER)-mitochondria interactions. This section will focus on mitochondria-associated membranes (MAMs) and particularly the tethering proteins at the ER-mitochondria interphase, as well as their role in cancer disease progression. Subsequently, the role of Ca2+ at the ER-mitochondria interphase in cancer disease progression will be discussed. Members of the Bcl-2 protein family, key regulators of cell death, also modulate Ca2+ transport pathways at the ER-mitochondria interphase. Furthermore, we will review the role of ER-mitochondria communication in the regulation of proteostasis, focusing on the ER stress sensor PERK (PRKR-like ER kinase), which exerts dual roles in cancer. Second, we will review the relevance of ER and mitochondria interactions with other organelles. This section will focus on peroxisome and lysosome organelle interactions and their impact on cancer disease progression. In this context, the peroxisome biogenesis factor (PEX) gene family has been linked to cancer. Moreover, the autophagy-lysosome system is emerging as a driving force in the progression of numerous human cancers. Thus, we will summarize our current understanding of the role of each of these organelles and their communication, highlighting how alterations in organelle interfaces participate in cancer development and progression. A better understanding of specific organelle communication sites and their relevant proteins may help to identify potential pharmacological targets for novel therapies in cancer control.

Lime: Low-Cost and Incremental Learning for Dynamic Heterogeneous Information Networks

Understanding the interconnected relationships of large-scale information networks like social, scholar and Internet of Things networks is vital for tasks like recommendation and fraud detection. The vast majority of the real-world networks are inherently heterogeneous and dynamic, containing many different types of nodes and edges and can change drastically over time. The dynamicity and heterogeneity make it extremely challenging to reason about the network structure. Unfortunately, existing approaches are inadequate in modeling real-life dynamical networks as they either have strong assumption of a given stochastic process or fail to capture the heterogeneity of network structure, and they all require extensive computational resources. We introduce <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Lime</small> , a better approach for modeling dynamic and heterogeneous information networks. <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Lime</small> is designed to extract high-quality network representation with significantly lower memory resources and computational time over the state-of-the-arts. Unlike prior work that uses a vector to encode each network node, we exploit the semantic relationships among network nodes to encode multiple nodes with similar semantics in shared vectors. By using many fewer node vectors, our approach significantly reduces the required memory space for encoding large-scale networks. To effectively trade information sharing for reduced memory footprint, we employ the recursive neural network (RsNN) with carefully designed optimization strategies to explore the node semantics in a novel cuboid space. We then go further by showing, for the first time, how an effective incremental learning approach can be developed – with the help of RsNN, our cuboid structure, and a set of novel optimization techniques – to allow a learning framework to quickly and efficiently adapt to a constantly evolving network. We evaluate <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Lime</small> by applying it to three representative network-based tasks, node classification, node clustering and anomaly detection, performing on three large-scale datasets. We compare <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Lime</small> against eleven prior state-of-the-art approaches for learning network representation. Our extensive experiments demonstrate that <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Lime</small> not only reduces the memory footprint by over 80 percent and the processing time over 2x when learning network representation but also delivers comparable performance for downstream processing tasks. We show that our incremental learning method can boost the learning time by up to 20x without compromising the quality of the learned network representation.

Who Should Deserve Investment Attractive Individual and Group Search in Dynamic Information Networks

Analyzing dynamic information networks, which contain evolving objects and links, to meet users various needs has attracted much attention in recent years. For sales companies, recruiting staff who are socialites would help to increase sales volume since such staff often sell more. For universities, employing active collaborators who are productive and well connected to many different scholars over time could bring many benefits to their development. However, no previous work has focused on the discovery of socialites and active collaborators who are worthy of investment in reality. In this paper, we advocate a new concept of attractive individuals to model such special objects. We also introduce the concept of attractive groups to represent groups of well-connected attractive individuals. We analyze the complexity of the attractive individual and group search problems. A time and space efficient algorithm is presented to detect attractive individuals. Furthermore, three algorithms are respectively proposed to find top-k representative attractive groups. Experiments on 6 real-world datasets show high performance of our methods and the significance of attractive individuals and groups in reality.

Evolutionary community discovery in dynamic social networks via resistance distance

Traditional social community discovery methods concentrate mainly on static social networks, but the analysis of dynamic networks is a prerequisite for real-time and personalized social services. Through the study of community changes, the community structure in a dynamic network can be tracked over time, which helps in the mining of dynamic network information. In this paper, we propose a method of tracking dynamic community evolution that is based on resistance distance. Specifically, we model the time-varying features of dynamic networks using the convergence of a resistance-based distance. In our model, the heterogeneity of neighboring nodes can be obtained in the local topology of nodes by analyzing the resistance distance between nodes. We design a community discovery algorithm that essentially discovers community structures on dynamic networks by identifying the so-called core node. During the process of community evolution analysis, both the dynamic contribution of ordinary nodes and core nodes in each community are considered. In addition, to avoid the inclusion of spurious communities in the community structure, we define the notion of noise community and account for it in our algorithm. Experimental results show that the method proposed in this paper can yield better accuracy than other existing methods.