Reconstructing Networks

Cimini, Giulio; Mastrandrea, Rossana; Squartini, Tiziano

doi:10.1017/9781108771030

Cited by 21 publications

(5 citation statements)

References 235 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, studying liabilities in banking networks has been key to developing the notion of systemic risk [1,2], and explaining how certain banks' interconnections may amplify the impact of isolated shocks. A key component of this research was the development of methods to reconstruct the network of interdependencies between financial institutions, which are not easily observable [3,4].…”

Section: Introductionmentioning

confidence: 99%

Reconstructing supply networks

Mungo,

Brintrup,

Garlaschelli

et al. 2024

J. Phys. Complex.

View full text Add to dashboard Cite

Network reconstruction is a well-developed sub-field of network science, but it has only recently been applied to production networks, where nodes are firms and edges represent customer-supplier relationships. We review the literature that has flourished to infer the topology of these networks by partial, aggregate, or indirect observation of the data. We discuss why this is an important endeavour, what needs to be reconstructed, what makes it different from other network reconstruction problems, and how different researchers have approached the problem. We conclude with a research agenda.

show abstract

Section: Introductionmentioning

confidence: 99%

Reconstructing supply networks

Mungo,

Brintrup,

Garlaschelli

et al. 2024

J. Phys. Complex.

View full text Add to dashboard Cite

show abstract

“…The aforementioned limitations can be complemented by network reconstruction (18). Network reconstruction entails generating a network from another network that has missing or spurious links in its observed status (19).…”

Section: Introductionmentioning

confidence: 99%

The effectiveness of intervention measures on MERS-CoV transmission by using the contact networks reconstructed from link prediction data

Kim,

Jin

et al. 2024

Front. Public Health

View full text Add to dashboard Cite

IntroductionMitigating the spread of infectious diseases is of paramount concern for societal safety, necessitating the development of effective intervention measures. Epidemic simulation is widely used to evaluate the efficacy of such measures, but realistic simulation environments are crucial for meaningful insights. Despite the common use of contact-tracing data to construct realistic networks, they have inherent limitations. This study explores reconstructing simulation networks using link prediction methods as an alternative approach.MethodsThe primary objective of this study is to assess the effectiveness of intervention measures on the reconstructed network, focusing on the 2015 MERS-CoV outbreak in South Korea. Contact-tracing data were acquired, and simulation networks were reconstructed using the graph autoencoder (GAE)-based link prediction method. A scale-free (SF) network was employed for comparison purposes. Epidemic simulations were conducted to evaluate three intervention strategies: Mass Quarantine (MQ), Isolation, and Isolation combined with Acquaintance Quarantine (AQ + Isolation).ResultsSimulation results showed that AQ + Isolation was the most effective intervention on the GAE network, resulting in consistent epidemic curves due to high clustering coefficients. Conversely, MQ and AQ + Isolation were highly effective on the SF network, attributed to its low clustering coefficient and intervention sensitivity. Isolation alone exhibited reduced effectiveness. These findings emphasize the significant impact of network structure on intervention outcomes and suggest a potential overestimation of effectiveness in SF networks. Additionally, they highlight the complementary use of link prediction methods.DiscussionThis innovative methodology provides inspiration for enhancing simulation environments in future endeavors. It also offers valuable insights for informing public health decision-making processes, emphasizing the importance of realistic simulation environments and the potential of link prediction methods.

show abstract

“…A second aspect of our work is the connection between spectral methods and random models. Many graph embedding 20 , re-ordering 12 , clustering 21 , and structure recovery 22 , 23 techniques solve maximum-likelihood problems on graphs assuming specific generative models. Besides their application in these inverse problems, random graph models are useful inference tools for quantifying structure, predicting new or missing links, and improving the interpretability of learning algorithms by relating node embeddings to edge probabilities 24 , 25 .…”

Section: Introductionmentioning

confidence: 99%

Generative hypergraph models and spectral embedding

Gong

Higham

Zygalakis

2023

Sci Rep

View full text Add to dashboard Cite

Many complex systems involve interactions between more than two agents. Hypergraphs capture these higher-order interactions through hyperedges that may link more than two nodes. We consider the problem of embedding a hypergraph into low-dimensional Euclidean space so that most interactions are short-range. This embedding is relevant to many follow-on tasks, such as node reordering, clustering, and visualization. We focus on two spectral embedding algorithms customized to hypergraphs which recover linear and periodic structures respectively. In the periodic case, nodes are positioned on the unit circle. We show that the two spectral hypergraph embedding algorithms are associated with a new class of generative hypergraph models. These models generate hyperedges according to node positions in the embedded space and encourage short-range connections. They allow us to quantify the relative presence of periodic and linear structures in the data through maximum likelihood. They also improve the interpretability of node embedding and provide a metric for hyperedge prediction. We demonstrate the hypergraph embedding and follow-on tasks—including quantifying relative strength of structures, clustering and hyperedge prediction—on synthetic and real-world hypergraphs. We find that the hypergraph approach can outperform clustering algorithms that use only dyadic edges. We also compare several triadic edge prediction methods on high school and primary school contact hypergraphs where our algorithm improves upon benchmark methods when the amount of training data is limited.

show abstract

Reconstructing Networks

Cited by 21 publications

References 235 publications

Reconstructing supply networks

Reconstructing supply networks

The effectiveness of intervention measures on MERS-CoV transmission by using the contact networks reconstructed from link prediction data

Generative hypergraph models and spectral embedding

Contact Info

Product

Resources

About