John Leventides, Costas Poulios, Maria Livada, Ioannis Giannikos
We investigate the reengineeering of interbank networks with a specific focus on capital increase. We consider a scenario where all other components of the network’s infrastructure remain stable (a practical assumption for short-term situations). Our objective is to assess the impact of raising capital on the network’s robustness and to address the following key aspects. First, given a predefined target for network robustness, our aim is to achieve this goal optimally, minimizing the required capital increase. Second, in cases where a total capital increase has been determined, the central challenge lies in distributing this increase among the banks in a manner that maximizes the stability of the network. To tackle these challenges, we begin by developing a comprehensive theoretical framework. Subsequently, we formulate an optimization model for the network’s redesign. Finally, we apply this framework to practical examples, highlighting its applicability in real-world scenarios.
{"title":"Reengineering of interbank networks","authors":"John Leventides, Costas Poulios, Maria Livada, Ioannis Giannikos","doi":"10.1017/nws.2023.21","DOIUrl":"https://doi.org/10.1017/nws.2023.21","url":null,"abstract":"<p>We investigate the reengineeering of interbank networks with a specific focus on capital increase. We consider a scenario where all other components of the network’s infrastructure remain stable (a practical assumption for short-term situations). Our objective is to assess the impact of raising capital on the network’s robustness and to address the following key aspects. First, given a predefined target for network robustness, our aim is to achieve this goal optimally, minimizing the required capital increase. Second, in cases where a total capital increase has been determined, the central challenge lies in distributing this increase among the banks in a manner that maximizes the stability of the network. To tackle these challenges, we begin by developing a comprehensive theoretical framework. Subsequently, we formulate an optimization model for the network’s redesign. Finally, we apply this framework to practical examples, highlighting its applicability in real-world scenarios.</p>","PeriodicalId":51827,"journal":{"name":"Network Science","volume":null,"pages":null},"PeriodicalIF":1.7,"publicationDate":"2023-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138716125","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-01Epub Date: 2023-08-25DOI: 10.1017/nws.2023.16
David P Kennedy, Thomas N Bradbury, Benjamin R Karney
The social networks surrounding intimate couples provide them with bonding and bridging social capital and have been theorized to be associated with their well-being and relationship quality. These networks are multidimensional, featuring compositional (e.g., the proportion of family members vs. friends) and structural characteristics (e.g., density, degree of overlap between spouses' networks). Most previous studies of couple networks are based on partners' global ratings of their network characteristics or network data collected from one member of the dyad. This study presents the analysis of "duocentric networks" or the combined personal networks of both members of a couple, collected from 207 mixed-sex newlywed couples living in low-income neighborhoods of Harris County, TX. We conducted a pattern-centric analysis of compositional and structural features to identify distinct types of couple networks. We identified five qualitatively distinct network types (wife family-focused, husband family-focused, shared friends, wife friend-focused, and extremely disconnected). Couples' network types were associated with the quality of the relationships between couples and their network contacts (e.g., emotional support) but not with the quality of the couples' relationship with each other. We argue that duocentric networks provide appropriate data for measuring bonding and bridging capital in couple networks.
{"title":"Typologies of duocentric networks among low-income newlywed couples.","authors":"David P Kennedy, Thomas N Bradbury, Benjamin R Karney","doi":"10.1017/nws.2023.16","DOIUrl":"10.1017/nws.2023.16","url":null,"abstract":"<p><p>The social networks surrounding intimate couples provide them with bonding and bridging social capital and have been theorized to be associated with their well-being and relationship quality. These networks are multidimensional, featuring compositional (e.g., the proportion of family members vs. friends) and structural characteristics (e.g., density, degree of overlap between spouses' networks). Most previous studies of couple networks are based on partners' global ratings of their network characteristics or network data collected from one member of the dyad. This study presents the analysis of \"duocentric networks\" or the combined personal networks of both members of a couple, collected from 207 mixed-sex newlywed couples living in low-income neighborhoods of Harris County, TX. We conducted a pattern-centric analysis of compositional and structural features to identify distinct types of couple networks. We identified five qualitatively distinct network types (wife family-focused, husband family-focused, shared friends, wife friend-focused, and extremely disconnected). Couples' network types were associated with the quality of the relationships between couples and their network contacts (e.g., emotional support) but not with the quality of the couples' relationship with each other. We argue that duocentric networks provide appropriate data for measuring bonding and bridging capital in couple networks.</p>","PeriodicalId":51827,"journal":{"name":"Network Science","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10783164/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41905752","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Choices made by individuals have widespread impacts—for instance, people choose between political candidates to vote for, between social media posts to share, and between brands to purchase—moreover, data on these choices are increasingly abundant. Discrete choice models are a key tool for learning individual preferences from such data. Additionally, social factors like conformity and contagion influence individual choice. Traditional methods for incorporating these factors into choice models do not account for the entire social network and require hand-crafted features. To overcome these limitations, we use graph learning to study choice in networked contexts. We identify three ways in which graph learning techniques can be used for discrete choice: learning chooser representations, regularizing choice model parameters, and directly constructing predictions from a network. We design methods in each category and test them on real-world choice datasets, including county-level 2016 US election results and Android app installation and usage data. We show that incorporating social network structure can improve the predictions of the standard econometric choice model, the multinomial logit. We provide evidence that app installations are influenced by social context, but we find no such effect on app usage among the same participants, which instead is habit-driven. In the election data, we highlight the additional insights a discrete choice framework provides over classification or regression, the typical approaches. On synthetic data, we demonstrate the sample complexity benefit of using social information in choice models.
{"title":"Graph-based methods for discrete choice","authors":"Kiran Tomlinson, Austin R. Benson","doi":"10.1017/nws.2023.20","DOIUrl":"https://doi.org/10.1017/nws.2023.20","url":null,"abstract":"Abstract Choices made by individuals have widespread impacts—for instance, people choose between political candidates to vote for, between social media posts to share, and between brands to purchase—moreover, data on these choices are increasingly abundant. Discrete choice models are a key tool for learning individual preferences from such data. Additionally, social factors like conformity and contagion influence individual choice. Traditional methods for incorporating these factors into choice models do not account for the entire social network and require hand-crafted features. To overcome these limitations, we use graph learning to study choice in networked contexts. We identify three ways in which graph learning techniques can be used for discrete choice: learning chooser representations, regularizing choice model parameters, and directly constructing predictions from a network. We design methods in each category and test them on real-world choice datasets, including county-level 2016 US election results and Android app installation and usage data. We show that incorporating social network structure can improve the predictions of the standard econometric choice model, the multinomial logit. We provide evidence that app installations are influenced by social context, but we find no such effect on app usage among the same participants, which instead is habit-driven. In the election data, we highlight the additional insights a discrete choice framework provides over classification or regression, the typical approaches. On synthetic data, we demonstrate the sample complexity benefit of using social information in choice models.","PeriodicalId":51827,"journal":{"name":"Network Science","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135634032","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract In this study, we investigate the creation and persistence of interfirm ties in a large-scale business transaction network. Business transaction relations (firms buying or selling products or services to each other) are driven by economic motives, but because trust is essential to business relationships, the social connections of owners or the geographical proximity of firms can also influence their development. However, studying the formation of interfirm business transaction ties on a large scale is rare, because of the significant data demand. The business transaction and the ownership networks of Hungarian firms are constructed from two administrative datasets for 2016 and 2017. We show that direct or indirect connections in this two-layered network, including open triads in the business network, contribute to both the creation and persistence of business transaction ties. For our estimations, we utilize log-linear models and emphasize their efficiency in predicting links in such large networks. We contribute to the literature by presenting different patterns of business connections in a nationwide multilayer interfirm network.
{"title":"Business transactions and ownership ties between firms","authors":"László Lőrincz, Sándor Juhász, Rebeka O. Szabó","doi":"10.1017/nws.2023.19","DOIUrl":"https://doi.org/10.1017/nws.2023.19","url":null,"abstract":"Abstract In this study, we investigate the creation and persistence of interfirm ties in a large-scale business transaction network. Business transaction relations (firms buying or selling products or services to each other) are driven by economic motives, but because trust is essential to business relationships, the social connections of owners or the geographical proximity of firms can also influence their development. However, studying the formation of interfirm business transaction ties on a large scale is rare, because of the significant data demand. The business transaction and the ownership networks of Hungarian firms are constructed from two administrative datasets for 2016 and 2017. We show that direct or indirect connections in this two-layered network, including open triads in the business network, contribute to both the creation and persistence of business transaction ties. For our estimations, we utilize log-linear models and emphasize their efficiency in predicting links in such large networks. We contribute to the literature by presenting different patterns of business connections in a nationwide multilayer interfirm network.","PeriodicalId":51827,"journal":{"name":"Network Science","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136112723","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Within US professional sports, trades within one’s own division are often perceived to be disadvantageous. We ask how common this practice is. To examine this question, we construct a date-stamped network of all trades in the National Basketball Association between June 1976 and May 2019. We then use season-specific weighted exponential random graph models to estimate the likelihood of teams avoiding within-division trade partners, and how consistent that pattern is across the observed period. In addition to the empirical question, this analysis serves to demonstrate the necessity and difficulty of constructing the proper baseline for statistical comparison. We find limited-to-no support for the popular perception.
{"title":"Do NBA teams avoid trading within their own division?","authors":"jimi adams, Michał Bojanowski","doi":"10.1017/nws.2023.18","DOIUrl":"https://doi.org/10.1017/nws.2023.18","url":null,"abstract":"Abstract Within US professional sports, trades within one’s own division are often perceived to be disadvantageous. We ask how common this practice is. To examine this question, we construct a date-stamped network of all trades in the National Basketball Association between June 1976 and May 2019. We then use season-specific weighted exponential random graph models to estimate the likelihood of teams avoiding within-division trade partners, and how consistent that pattern is across the observed period. In addition to the empirical question, this analysis serves to demonstrate the necessity and difficulty of constructing the proper baseline for statistical comparison. We find limited-to-no support for the popular perception.","PeriodicalId":51827,"journal":{"name":"Network Science","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135154051","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Finding paths is a fundamental problem in graph theory and algorithm design due to its many applications. Recently, this problem has been considered on temporal graphs, where edges may change over a discrete time domain. The analysis of graphs has also taken into account the relevance of vertex properties, modeled by assigning to vertices labels or colors. In this work, we deal with a problem that, given a static or temporal graph, whose vertices are colored graph looks for a path such that (1) the vertices of the path have distinct colors and (2) that path includes the maximum number of colors. We analyze the approximation complexity of the problem on static and temporal graphs, and we prove an inapproximability bound. Then, we consider the problem on temporal graphs, and we design a heuristic for it. We present an experimental evaluation of our heuristic, both on synthetic and real-world graphs. The experimental results show that for many instances of the problem, our method is able to return near-optimal solutions.
{"title":"Colorful path detection in vertex-colored temporal","authors":"R. Dondi, M. Hosseinzadeh","doi":"10.1017/nws.2023.17","DOIUrl":"https://doi.org/10.1017/nws.2023.17","url":null,"abstract":"\u0000 Finding paths is a fundamental problem in graph theory and algorithm design due to its many applications. Recently, this problem has been considered on temporal graphs, where edges may change over a discrete time domain. The analysis of graphs has also taken into account the relevance of vertex properties, modeled by assigning to vertices labels or colors. In this work, we deal with a problem that, given a static or temporal graph, whose vertices are colored graph looks for a path such that (1) the vertices of the path have distinct colors and (2) that path includes the maximum number of colors. We analyze the approximation complexity of the problem on static and temporal graphs, and we prove an inapproximability bound. Then, we consider the problem on temporal graphs, and we design a heuristic for it. We present an experimental evaluation of our heuristic, both on synthetic and real-world graphs. The experimental results show that for many instances of the problem, our method is able to return near-optimal solutions.","PeriodicalId":51827,"journal":{"name":"Network Science","volume":null,"pages":null},"PeriodicalIF":1.7,"publicationDate":"2023-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44636523","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Previous studies have shown that relationship sentiments in families follow a pattern wherein either all maintain positive relationships or there are two antagonistic factions. This result is consistent with the network theory of structural balance that individuals befriend their friends’ friend and become enemies with their friends’ enemies. Fault lines in families would then endogenously emerge through the same kinds of interactional processes that organize nations into axis and allies. We argue that observed patterns may instead exogenously come about as the result of personal characteristics or homophilous partitions of family members. Disentangling these alternate theoretical possibilities requires longitudinal data. The present study tracks the sentiment dynamics of 1,710 families in a longitudinal panel study. Results show the same static patterns suggestive of balancing processes identified in earlier research, yet dynamic analysis reveals that conflict in families is not generated or resolved in accordance with balance theory.
{"title":"Limited evidence for structural balance in the family","authors":"Jonas Stein, Jornt J. Mandemakers, A. van de Rijt","doi":"10.1017/nws.2023.15","DOIUrl":"https://doi.org/10.1017/nws.2023.15","url":null,"abstract":"\u0000 Previous studies have shown that relationship sentiments in families follow a pattern wherein either all maintain positive relationships or there are two antagonistic factions. This result is consistent with the network theory of structural balance that individuals befriend their friends’ friend and become enemies with their friends’ enemies. Fault lines in families would then endogenously emerge through the same kinds of interactional processes that organize nations into axis and allies. We argue that observed patterns may instead exogenously come about as the result of personal characteristics or homophilous partitions of family members. Disentangling these alternate theoretical possibilities requires longitudinal data. The present study tracks the sentiment dynamics of 1,710 families in a longitudinal panel study. Results show the same static patterns suggestive of balancing processes identified in earlier research, yet dynamic analysis reveals that conflict in families is not generated or resolved in accordance with balance theory.","PeriodicalId":51827,"journal":{"name":"Network Science","volume":null,"pages":null},"PeriodicalIF":1.7,"publicationDate":"2023-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48892059","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Polarization makes it difficult to form positive relationships across existing groups. Decreasing polarization may improve political discourse around the world. Polarization can be modeled on a social network as structural balance, where the network is composed of groups with positive links between all individuals in the group and negative links with all others. Previous work shows that incorporating attributes of individuals usually makes structural balance, and hence polarization, harder to achieve. That work examines only a limited number and types of attributes. We present a generalized model and a simulation framework to analyze the effect of any type of attribute, including analytically as long as an expected value can be written for the type of attribute. As attributes, we consider people’s (approximately) immutable characteristics (e.g., race, wealth) and such opinions that change more slowly than relationships (e.g., political preferences). We detail and analyze five classes of attributes, recapitulating the results of previous work in this framework and extending it. While it is easier to prevent than to destabilize polarization, we find that usually the most effective at both are continuous attributes, followed by ordered attributes and, finally, binary attributes. The effectiveness of unordered attributes varies depending on the magnitude of negative impact of having differing attributes but is smaller than of continuous ones. Testing the framework on network structures containing communities revealed that destroying polarization may require introducing local tensions. This model could be used by policymakers, among others, to prevent and design effective interventions to counteract polarization.
{"title":"A general model for how attributes can reduce polarization in social groups","authors":"Piotr J. Górski, Curtis Atkisson, J. Hołyst","doi":"10.1017/nws.2023.13","DOIUrl":"https://doi.org/10.1017/nws.2023.13","url":null,"abstract":"\u0000 Polarization makes it difficult to form positive relationships across existing groups. Decreasing polarization may improve political discourse around the world. Polarization can be modeled on a social network as structural balance, where the network is composed of groups with positive links between all individuals in the group and negative links with all others. Previous work shows that incorporating attributes of individuals usually makes structural balance, and hence polarization, harder to achieve. That work examines only a limited number and types of attributes. We present a generalized model and a simulation framework to analyze the effect of any type of attribute, including analytically as long as an expected value can be written for the type of attribute. As attributes, we consider people’s (approximately) immutable characteristics (e.g., race, wealth) and such opinions that change more slowly than relationships (e.g., political preferences). We detail and analyze five classes of attributes, recapitulating the results of previous work in this framework and extending it. While it is easier to prevent than to destabilize polarization, we find that usually the most effective at both are continuous attributes, followed by ordered attributes and, finally, binary attributes. The effectiveness of unordered attributes varies depending on the magnitude of negative impact of having differing attributes but is smaller than of continuous ones. Testing the framework on network structures containing communities revealed that destroying polarization may require introducing local tensions. This model could be used by policymakers, among others, to prevent and design effective interventions to counteract polarization.","PeriodicalId":51827,"journal":{"name":"Network Science","volume":null,"pages":null},"PeriodicalIF":1.7,"publicationDate":"2023-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46345063","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract We investigate structural features and processes associated with the onset of systemic conflict using an approach which integrates complex systems theory with network modeling and analysis. We present a signed network model of cooperation and conflict dynamics in the context of international relations between states. The model evolves ties between nodes under the influence of a structural balance force and a dyad-specific force. Model simulations exhibit a sharp bifurcation from peace to systemic war as structural balance pressures increase, a bistable regime in which both peace and war stable equilibria exist, and a hysteretic reverse bifurcation from war to peace. We show how the analytical expression we derive for the peace-to-war bifurcation condition implies that polarized network structure increases susceptibility to systemic war. We develop a framework for identifying patterns of relationship perturbations that are most destabilizing and apply it to the network of European great powers before World War I. We also show that the model exhibits critical slowing down, in which perturbations to the peace equilibrium take longer to decay as the system draws closer to the bifurcation. We discuss how our results relate to international relations theories on the causes and catalysts of systemic war.
{"title":"Transitions between peace and systemic war as bifurcations in a signed network dynamical system","authors":"Megan Morrison, J. Nathan Kutz, Michael Gabbay","doi":"10.1017/nws.2023.10","DOIUrl":"https://doi.org/10.1017/nws.2023.10","url":null,"abstract":"Abstract We investigate structural features and processes associated with the onset of systemic conflict using an approach which integrates complex systems theory with network modeling and analysis. We present a signed network model of cooperation and conflict dynamics in the context of international relations between states. The model evolves ties between nodes under the influence of a structural balance force and a dyad-specific force. Model simulations exhibit a sharp bifurcation from peace to systemic war as structural balance pressures increase, a bistable regime in which both peace and war stable equilibria exist, and a hysteretic reverse bifurcation from war to peace. We show how the analytical expression we derive for the peace-to-war bifurcation condition implies that polarized network structure increases susceptibility to systemic war. We develop a framework for identifying patterns of relationship perturbations that are most destabilizing and apply it to the network of European great powers before World War I. We also show that the model exhibits critical slowing down, in which perturbations to the peace equilibrium take longer to decay as the system draws closer to the bifurcation. We discuss how our results relate to international relations theories on the causes and catalysts of systemic war.","PeriodicalId":51827,"journal":{"name":"Network Science","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136355224","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We study Granger Causality in the context of wide-sense stationary time series. The focus of the analysis is to understand how the underlying topological structure of the causality graph affects graph recovery by means of the pairwise testing heuristic. Our main theoretical result establishes a sufficient condition (in particular, the graph must satisfy a polytree assumption we refer to as strong causality) under which the graph can be recovered by means of unconditional and binary pairwise causality testing. Examples from the gene regulatory network literature are provided which establish that graphs which are strongly causal, or very nearly so, can be expected to arise in practice. We implement finite sample heuristics derived from our theory, and use simulation to compare our pairwise testing heuristic against LASSO-based methods. These simulations show that, for graphs which are strongly causal (or small perturbations thereof) the pairwise testing heuristic is able to more accurately recover the underlying graph. We show that the algorithm is scalable to graphs with thousands of nodes, and that, as long as structural assumptions are met, exhibits similar high-dimensional scaling properties as the LASSO. That is, performance degrades slowly while the system size increases and the number of available samples is held fixed. Finally, a proof-of-concept application example shows, by attempting to classify alcoholic individuals using only Granger causality graphs inferred from EEG measurements, that the inferred Granger causality graph topology carries identifiable features.
{"title":"Exact recovery of Granger causality graphs with unconditional pairwise tests","authors":"R. Kinnear, R. Mazumdar","doi":"10.1017/nws.2023.11","DOIUrl":"https://doi.org/10.1017/nws.2023.11","url":null,"abstract":"\u0000 We study Granger Causality in the context of wide-sense stationary time series. The focus of the analysis is to understand how the underlying topological structure of the causality graph affects graph recovery by means of the pairwise testing heuristic. Our main theoretical result establishes a sufficient condition (in particular, the graph must satisfy a polytree assumption we refer to as strong causality) under which the graph can be recovered by means of unconditional and binary pairwise causality testing. Examples from the gene regulatory network literature are provided which establish that graphs which are strongly causal, or very nearly so, can be expected to arise in practice. We implement finite sample heuristics derived from our theory, and use simulation to compare our pairwise testing heuristic against LASSO-based methods. These simulations show that, for graphs which are strongly causal (or small perturbations thereof) the pairwise testing heuristic is able to more accurately recover the underlying graph. We show that the algorithm is scalable to graphs with thousands of nodes, and that, as long as structural assumptions are met, exhibits similar high-dimensional scaling properties as the LASSO. That is, performance degrades slowly while the system size increases and the number of available samples is held fixed. Finally, a proof-of-concept application example shows, by attempting to classify alcoholic individuals using only Granger causality graphs inferred from EEG measurements, that the inferred Granger causality graph topology carries identifiable features.","PeriodicalId":51827,"journal":{"name":"Network Science","volume":null,"pages":null},"PeriodicalIF":1.7,"publicationDate":"2023-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"57043628","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号