Tiago P. Peixoto
Research Subjects
Tiago P. Peixoto has a total of 156 co-authors. Here are the top co-authors by number of shared publications:
- Carmen Pimentel Cintra Do Prado
Instituto de Física Universidade de São Paulo Caixa Postal 66318 05314-970 -São Paulo - São Paulo -Brazil
6 shared publications - Barbara Drossel
Institut für Festkörperphysik Technische Universität Darmstadt Hochschulst. 6 64289 Darmstadt Germany
5 shared publications - Stefan Bornholdt
Institut für Theoretische Physik, Universität Bremen, 28759 Bremen, Germany
5 shared publications Barbara Drossel
Institut für Festkörperphysik, TU Darmstadt, Hochschulstraße 6, D-64289 Darmstadt, Germany
3 shared publications- Eduardo G. Altmann
University of Sydney
3 shared publications - Alec Kirkley
Institute of Data Science, University of Hong Kong, Hong Kong SAR, China
2 shared publications
Latest Publications
- Open Access
- 9 October 2026
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 12 (41)
Mesoscale structures in signed networks
Mesoscale structures in signed networks have been studied under the limiting assumption of the validity of social balance theory, which predicts positive connections within groups and negative connections between groups. Here, we propose and apply a methodology that overcomes this limitation and is able to find and characterize also the different possible unbalanced structures in signed networks. Applying our methodology to 24 empirical networks, from social-political, financial, and biological domains, we find that unbalanced mesoscale structures are prevalent in real-world networks, including cases with substantial balance at the microscale of triangles. In particular, we find that assortativity often prevails regardless of the interaction sign and that core-periphery structures are typical in online social networks. Our findings highlight the complexity of mesoscale relational structures, the importance of using computational methods that are a priori agnostic to specific patterns, and the importance of independently evaluating micro- and mesoscale predictions of social balance theory.
- 9 October 2026
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 12 (41)
Open AccessMesoscale structures in signed networks
Mesoscale structures in signed networks have been studied under the limiting assumption of the validity of social balance theory, which predicts positive connections within groups and negative connections between groups. Here, we propose and apply a methodology that overcomes this limitation and is able to find and characterize also the different possible unbalanced structures in signed networks. Applying our methodology to 24 empirical networks, from social-political, financial, and biological domains, we find that unbalanced mesoscale structures are prevalent in real-world networks, including cases with substantial balance at the microscale of triangles. In particular, we find that assortativity often prevails regardless of the interaction sign and that core-periphery structures are typical in online social networks. Our findings highlight the complexity of mesoscale relational structures, the importance of using computational methods that are a priori agnostic to specific patterns, and the importance of independently evaluating micro- and mesoscale predictions of social balance theory.
- Open Access
- 31 August 2026
- Published by Springer Nature in Scientific Reports
Multiscale patterns of migration flows in Austria: regionalization, administrative barriers, and urban-rural divides
Migration is central to various societal problems related to socioeconomic development. While much of the existing research has focused on international migration, migration patterns within a single country remain relatively unexplored. In this work, we study internal migration patterns in Austria for a period of 20 years, obtained from open and high-granularity administrative records. We employ inferential network methods to characterize the flows between municipalities and extract their clustering according to similar target and destination rates. Our methodology reveals significant deviations from commonly assumed relocation patterns modeled by the gravity law. At the same time, we observe unexpected biases of internal migrations that lead to less frequent movements across boundaries at both district and state levels than predictions suggest. This leads to significant regionalization of migration at multiple geographical scales and augmented division between urban and rural areas. These patterns appear to be remarkably persistent across decades of migration data, demonstrating systematic limitations of conventionally used gravity models in migration studies. Our approach presents a robust methodology that can be used to improve such evaluations and can reveal new phenomena in migration networks.
- 31 August 2026
- Published by Springer Nature in Scientific Reports
Open AccessMultiscale patterns of migration flows in Austria: regionalization, administrative barriers, and urban-rural divides
Migration is central to various societal problems related to socioeconomic development. While much of the existing research has focused on international migration, migration patterns within a single country remain relatively unexplored. In this work, we study internal migration patterns in Austria for a period of 20 years, obtained from open and high-granularity administrative records. We employ inferential network methods to characterize the flows between municipalities and extract their clustering according to similar target and destination rates. Our methodology reveals significant deviations from commonly assumed relocation patterns modeled by the gravity law. At the same time, we observe unexpected biases of internal migrations that lead to less frequent movements across boundaries at both district and state levels than predictions suggest. This leads to significant regionalization of migration at multiple geographical scales and augmented division between urban and rural areas. These patterns appear to be remarkably persistent across decades of migration data, demonstrating systematic limitations of conventionally used gravity models in migration studies. Our approach presents a robust methodology that can be used to improve such evaluations and can reveal new phenomena in migration networks.
- Open Access
- 5 November 2025
- Published by The Royal Society in Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences
- Vol. 481 (2325)
Uncertainty quantification and posterior sampling for network reconstruction
Network reconstruction is the task of inferring the unseen interactions between elements of a system, based only on their behaviour or dynamics. This inverse problem is in general ill-posed and admits many solutions for the same observation. Nevertheless, the vast majority of statistical methods proposed for this task—formulated as the inference of a graphical generative model—can only produce a ‘point estimate’, i.e. a single network considered the most likely. In general, this can give only a limited characterization of the reconstruction, since uncertainties and competing answers cannot be conveyed, even if their probabilities are comparable, while being structurally different. In this work, we present an efficient Markov-chain Monte–Carlo algorithm for sampling from posterior distributions of reconstructed networks, which is able to reveal the full population of answers for a given reconstruction problem, weighted according to their plausibilities. Our algorithm is general, since it does not rely on specific properties of particular generative models, and is specially suited for the inference of large and sparse networks, since in this case an iteration can be performed in time O ( N log 2 N ) for a network of N nodes, instead of O ( N 2 ) , as would be the case for a more naïve approach. We demonstrate the suitability of our method in providing uncertainties and consensus of solutions (which provably increases the reconstruction accuracy) in a variety of synthetic and empirical cases.
- 5 November 2025
- Published by The Royal Society in Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences
- Vol. 481 (2325)
Open AccessUncertainty quantification and posterior sampling for network reconstruction
Network reconstruction is the task of inferring the unseen interactions between elements of a system, based only on their behaviour or dynamics. This inverse problem is in general ill-posed and admits many solutions for the same observation. Nevertheless, the vast majority of statistical methods proposed for this task—formulated as the inference of a graphical generative model—can only produce a ‘point estimate’, i.e. a single network considered the most likely. In general, this can give only a limited characterization of the reconstruction, since uncertainties and competing answers cannot be conveyed, even if their probabilities are comparable, while being structurally different. In this work, we present an efficient Markov-chain Monte–Carlo algorithm for sampling from posterior distributions of reconstructed networks, which is able to reveal the full population of answers for a given reconstruction problem, weighted according to their plausibilities. Our algorithm is general, since it does not rely on specific properties of particular generative models, and is specially suited for the inference of large and sparse networks, since in this case an iteration can be performed in time O ( N log 2 N ) for a network of N nodes, instead of O ( N 2 ) , as would be the case for a more naïve approach. We demonstrate the suitability of our method in providing uncertainties and consensus of solutions (which provably increases the reconstruction accuracy) in a variety of synthetic and empirical cases.
- Open Access
- 29 October 2025
- Published by The Royal Society in Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences
- Vol. 481 (2324)
Scalable network reconstruction in subquadratic time
Network reconstruction consists in determining the unobserved pairwise couplings between N nodes given only observational data on the resulting behaviour that is conditioned on those couplings—typically a time-series or independent samples from a graphical model. A major obstacle to the scalability of algorithms proposed for this problem is a seemingly unavoidable quadratic complexity of Ω ( N 2 ) , corresponding to the requirement of each possible pairwise coupling being contemplated at least once, despite the fact that most networks of interest are sparse, with a number of non-zero couplings that are only O ( N ) . Here, we present a general algorithm applicable to a broad range of reconstruction problems that significantly outperforms this quadratic baseline. Our algorithm relies on a stochastic second-neighbour search that produces the best edge candidates with high probability, thus bypassing an exhaustive quadratic search. If we rely on the conjecture that the second-neighbour search finishes in log-linear time, we demonstrate theoretically that our algorithm finishes in subquadratic time, with a data-dependent complexity loosely upper bounded by O ( N 3 / 2 log N ) , but with a more typical log-linear complexity of O ( N log 2 N ) . In practice, we show that our algorithm achieves a performance that is many orders of magnitude faster than the quadratic baseline—in a manner consistent with our theoretical analysis—allows for easy parallelization, and thus enables the reconstruction of networks with hundreds of thousands and even millions of nodes and edges.
- 29 October 2025
- Published by The Royal Society in Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences
- Vol. 481 (2324)
Open AccessScalable network reconstruction in subquadratic time
Network reconstruction consists in determining the unobserved pairwise couplings between N nodes given only observational data on the resulting behaviour that is conditioned on those couplings—typically a time-series or independent samples from a graphical model. A major obstacle to the scalability of algorithms proposed for this problem is a seemingly unavoidable quadratic complexity of Ω ( N 2 ) , corresponding to the requirement of each possible pairwise coupling being contemplated at least once, despite the fact that most networks of interest are sparse, with a number of non-zero couplings that are only O ( N ) . Here, we present a general algorithm applicable to a broad range of reconstruction problems that significantly outperforms this quadratic baseline. Our algorithm relies on a stochastic second-neighbour search that produces the best edge candidates with high probability, thus bypassing an exhaustive quadratic search. If we rely on the conjecture that the second-neighbour search finishes in log-linear time, we demonstrate theoretically that our algorithm finishes in subquadratic time, with a data-dependent complexity loosely upper bounded by O ( N 3 / 2 log N ) , but with a more typical log-linear complexity of O ( N log 2 N ) . In practice, we show that our algorithm achieves a performance that is many orders of magnitude faster than the quadratic baseline—in a manner consistent with our theoretical analysis—allows for easy parallelization, and thus enables the reconstruction of networks with hundreds of thousands and even millions of nodes and edges.
- Top Cited PapersOpen Access
- 20 March 2025
- Published by American Physical Society (APS) in Physical Review X
- Vol. 15 (1)
Network Reconstruction via the Minimum Description Length Principle
A fundamental problem associated with the task of network reconstruction from dynamical or behavioral data consists in determining the most appropriate model complexity in a manner that prevents overfitting and produces an inferred network with a statistically justifiable number of edges and their weight distribution. The status quo in this context is based on L 1 regularization combined with cross-validation. However, besides its high computational cost, this commonplace approach unnecessarily ties the promotion of sparsity, i.e., abundance of zero weights, with weight “shrinkage.” This combination forces a trade-off between the bias introduced by shrinkage and the network sparsity, which often results in substantial overfitting even after cross-validation. In this work, we propose an alternative nonparametric regularization scheme based on hierarchical Bayesian inference and weight quantization, which does not rely on weight shrinkage to promote sparsity. Our approach follows the minimum description length principle, and uncovers the weight distribution that allows for the most compression of the data, thus avoiding overfitting without requiring cross-validation. The latter property renders our approach substantially faster and simpler to employ, as it requires a single fit to the complete data, instead of many fits for multiple data splits and choice of regularization parameter. As a result, we have a principled and efficient inference scheme that can be used with a large variety of generative models, without requiring the number of reconstructed edges and their weight distribution to be known in advance. In a series of examples, we also demonstrate that our scheme yields systematically increased accuracy in the reconstruction of both artificial and empirical networks. We highlight the use of our method with the reconstruction of interaction networks between microbial communities from large-scale abundance samples involving on the order of 10 4 – 10 5 species and demonstrate how the inferred model can be used to predict the outcome of potential interventions and tipping points in the system.
- 20 March 2025
- Published by American Physical Society (APS) in Physical Review X
- Vol. 15 (1)
Top Cited PapersOpen AccessNetwork Reconstruction via the Minimum Description Length Principle
A fundamental problem associated with the task of network reconstruction from dynamical or behavioral data consists in determining the most appropriate model complexity in a manner that prevents overfitting and produces an inferred network with a statistically justifiable number of edges and their weight distribution. The status quo in this context is based on L 1 regularization combined with cross-validation. However, besides its high computational cost, this commonplace approach unnecessarily ties the promotion of sparsity, i.e., abundance of zero weights, with weight “shrinkage.” This combination forces a trade-off between the bias introduced by shrinkage and the network sparsity, which often results in substantial overfitting even after cross-validation. In this work, we propose an alternative nonparametric regularization scheme based on hierarchical Bayesian inference and weight quantization, which does not rely on weight shrinkage to promote sparsity. Our approach follows the minimum description length principle, and uncovers the weight distribution that allows for the most compression of the data, thus avoiding overfitting without requiring cross-validation. The latter property renders our approach substantially faster and simpler to employ, as it requires a single fit to the complete data, instead of many fits for multiple data splits and choice of regularization parameter. As a result, we have a principled and efficient inference scheme that can be used with a large variety of generative models, without requiring the number of reconstructed edges and their weight distribution to be known in advance. In a series of examples, we also demonstrate that our scheme yields systematically increased accuracy in the reconstruction of both artificial and empirical networks. We highlight the use of our method with the reconstruction of interaction networks between microbial communities from large-scale abundance samples involving on the order of 10 4 – 10 5 species and demonstrate how the inferred model can be used to predict the outcome of potential interventions and tipping points in the system.
- 21 November 2023
- Published by Springer Nature
- p. 65-82
Modelling Temporal Networks with Markov Chains, Community Structures and Change Points
- 21 November 2023
- Published by Springer Nature
- p. 65-82
Modelling Temporal Networks with Markov Chains, Community Structures and Change Points
- Open Access
Implicit models, latent compression, intrinsic biases, and cheap lunches in community detection
The task of community detection, which aims to partition a network into clusters of nodes to summarize its large-scale structure, has spawned the development of many competing algorithms with varying objectives. Some community detection methods are inferential, explicitly deriving the clustering objective through a probabilistic generative model, while other methods are descriptive, dividing a network according to an objective motivated by a particular application, making it challenging to compare these methods on the same scale. Here we present a solution to this problem that associates any community detection objective, inferential or descriptive, with its corresponding implicit network generative model. This allows us to compute the description length of a network and its partition under arbitrary objectives, providing a principled measure to compare the performance of different algorithms without the need for "ground truth" labels. Our approach also gives access to instances of the community detection problem that are optimal to any given algorithm, and in this way reveals intrinsic biases in popular descriptive methods, explaining their tendency to overfit. Using our framework, we compare a number of community detection methods on artificial networks, and on a corpus of over 500 structurally diverse empirical networks. We find that more expressive community detection methods exhibit consistently superior compression performance on structured data instances, without having degraded performance on a minority of situations where more specialized algorithms perform optimally. Our results undermine the implications of the "no free lunch" theorem for community detection, both conceptually and in practice, since it is confined to unstructured data instances, unlike relevant community detection problems which are structured by requirement.
Open AccessImplicit models, latent compression, intrinsic biases, and cheap lunches in community detection
The task of community detection, which aims to partition a network into clusters of nodes to summarize its large-scale structure, has spawned the development of many competing algorithms with varying objectives. Some community detection methods are inferential, explicitly deriving the clustering objective through a probabilistic generative model, while other methods are descriptive, dividing a network according to an objective motivated by a particular application, making it challenging to compare these methods on the same scale. Here we present a solution to this problem that associates any community detection objective, inferential or descriptive, with its corresponding implicit network generative model. This allows us to compute the description length of a network and its partition under arbitrary objectives, providing a principled measure to compare the performance of different algorithms without the need for "ground truth" labels. Our approach also gives access to instances of the community detection problem that are optimal to any given algorithm, and in this way reveals intrinsic biases in popular descriptive methods, explaining their tendency to overfit. Using our framework, we compare a number of community detection methods on artificial networks, and on a corpus of over 500 structurally diverse empirical networks. We find that more expressive community detection methods exhibit consistently superior compression performance on structured data instances, without having degraded performance on a minority of situations where more specialized algorithms perform optimally. Our results undermine the implications of the "no free lunch" theorem for community detection, both conceptually and in practice, since it is confined to unstructured data instances, unlike relevant community detection problems which are structured by requirement.
- 23 August 2023
- Published by American Physical Society (APS) in Physical Review E
- Vol. 108 (2) , 024309
Implicit models, latent compression, intrinsic biases, and cheap lunches in community detection
The task of community detection, which aims to partition a network into clusters of nodes to summarize its large-scale structure, has spawned the development of many competing algorithms with varying objectives. Some community detection methods are inferential, explicitly deriving the clustering objective through a probabilistic generative model, while other methods are descriptive, dividing a network according to an objective motivated by a particular application, making it challenging to compare these methods on the same scale. Here we present a solution to this problem that associates any community detection objective, inferential or descriptive, with its corresponding implicit network generative model. This allows us to compute the description length of a network and its partition under arbitrary objectives, providing a principled measure to compare the performance of different algorithms without the need for “ground-truth” labels. Our approach also gives access to instances of the community detection problem that are optimal to any given algorithm and in this way reveals intrinsic biases in popular descriptive methods, explaining their tendency to overfit. Using our framework, we compare a number of community detection methods on artificial networks and on a corpus of over 500 structurally diverse empirical networks. We find that more expressive community detection methods exhibit consistently superior compression performance on structured data instances, without having degraded performance on a minority of situations where more specialized algorithms perform optimally. Our results undermine the implications of the “no free lunch” theorem for community detection, both conceptually and in practice, since it is confined to unstructured data instances, unlike relevant community detection problems which are structured by requirement.
- 23 August 2023
- Published by American Physical Society (APS) in Physical Review E
- Vol. 108 (2) , 024309
Implicit models, latent compression, intrinsic biases, and cheap lunches in community detection
The task of community detection, which aims to partition a network into clusters of nodes to summarize its large-scale structure, has spawned the development of many competing algorithms with varying objectives. Some community detection methods are inferential, explicitly deriving the clustering objective through a probabilistic generative model, while other methods are descriptive, dividing a network according to an objective motivated by a particular application, making it challenging to compare these methods on the same scale. Here we present a solution to this problem that associates any community detection objective, inferential or descriptive, with its corresponding implicit network generative model. This allows us to compute the description length of a network and its partition under arbitrary objectives, providing a principled measure to compare the performance of different algorithms without the need for “ground-truth” labels. Our approach also gives access to instances of the community detection problem that are optimal to any given algorithm and in this way reveals intrinsic biases in popular descriptive methods, explaining their tendency to overfit. Using our framework, we compare a number of community detection methods on artificial networks and on a corpus of over 500 structurally diverse empirical networks. We find that more expressive community detection methods exhibit consistently superior compression performance on structured data instances, without having degraded performance on a minority of situations where more specialized algorithms perform optimally. Our results undermine the implications of the “no free lunch” theorem for community detection, both conceptually and in practice, since it is confined to unstructured data instances, unlike relevant community detection problems which are structured by requirement.
- Open Access
Descriptive vs. inferential community detection in networks: pitfalls, myths, and half-truths
Community detection is one of the most important methodological fields of network science, and one which has attracted a significant amount of attention over the past decades. This area deals with the automated division of a network into fundamental building blocks, with the objective of providing a summary of its large-scale structure. Despite its importance and widespread adoption, there is a noticeable gap between what is arguably the state-of-the-art and the methods that are actually used in practice in a variety of fields. Here we attempt to address this discrepancy by dividing existing methods according to whether they have a "descriptive" or an "inferential" goal. While descriptive methods find patterns in networks based on context-dependent notions of community structure, inferential methods articulate generative models, and attempt to fit them to data. In this way, they are able to provide insights into the mechanisms of network formation, and separate structure from randomness in a manner supported by statistical evidence. We review how employing descriptive methods with inferential aims is riddled with pitfalls and misleading answers, and thus should be in general avoided. We argue that inferential methods are more typically aligned with clearer scientific questions, yield more robust results, and should be in many cases preferred. We attempt to dispel some myths and half-truths often believed when community detection is employed in practice, in an effort to improve both the use of such methods as well as the interpretation of their results.
Open AccessDescriptive vs. inferential community detection in networks: pitfalls, myths, and half-truths
Community detection is one of the most important methodological fields of network science, and one which has attracted a significant amount of attention over the past decades. This area deals with the automated division of a network into fundamental building blocks, with the objective of providing a summary of its large-scale structure. Despite its importance and widespread adoption, there is a noticeable gap between what is arguably the state-of-the-art and the methods that are actually used in practice in a variety of fields. Here we attempt to address this discrepancy by dividing existing methods according to whether they have a "descriptive" or an "inferential" goal. While descriptive methods find patterns in networks based on context-dependent notions of community structure, inferential methods articulate generative models, and attempt to fit them to data. In this way, they are able to provide insights into the mechanisms of network formation, and separate structure from randomness in a manner supported by statistical evidence. We review how employing descriptive methods with inferential aims is riddled with pitfalls and misleading answers, and thus should be in general avoided. We argue that inferential methods are more typically aligned with clearer scientific questions, yield more robust results, and should be in many cases preferred. We attempt to dispel some myths and half-truths often believed when community detection is employed in practice, in an effort to improve both the use of such methods as well as the interpretation of their results.
- Open Access
Social network modeling and applications, a tutorial
Social networks have been widely studied over the last century from multiple disciplines to understand societal issues such as inequality in employment rates, managerial performance, and epidemic spread. Today, these and many more issues can be studied at global scale thanks to the digital footprints that we generate when browsing the Web or using social media platforms. Unfortunately, scientists often struggle to access to such data primarily because it is proprietary, and even when it is shared with privacy guarantees, such data is either no representative or too big. In this tutorial, we will discuss recent advances and future directions in network modeling. In particular, we focus on how to exploit synthetic networks to study real-world problems such as data privacy, spreading dynamics, algorithmic bias, and ranking inequalities. We start by reviewing different types of generative models for social networks including node-attributed and scale-free networks. Then, we showcase how to perform a network selection analysis to characterize the mechanisms of edge formation of any given real-world network.
Open AccessSocial network modeling and applications, a tutorial
Social networks have been widely studied over the last century from multiple disciplines to understand societal issues such as inequality in employment rates, managerial performance, and epidemic spread. Today, these and many more issues can be studied at global scale thanks to the digital footprints that we generate when browsing the Web or using social media platforms. Unfortunately, scientists often struggle to access to such data primarily because it is proprietary, and even when it is shared with privacy guarantees, such data is either no representative or too big. In this tutorial, we will discuss recent advances and future directions in network modeling. In particular, we focus on how to exploit synthetic networks to study real-world problems such as data privacy, spreading dynamics, algorithmic bias, and ranking inequalities. We start by reviewing different types of generative models for social networks including node-attributed and scale-free networks. Then, we showcase how to perform a network selection analysis to characterize the mechanisms of edge formation of any given real-world network.