arXiv subjects

Gonzalo Travieso

Publications and source records attributed to Gonzalo Travieso.

At least 19 recordsLinked to original sources

arXiv2025

A Benchmarking Framework for Network Classification Methods

Network classification plays a crucial role in the study of complex systems, impacting fields like biology, sociology, and computer science. In this research, we present an innovative benchmark dataset made up of synthetic networks that are categorized into various classes and subclasses. This dataset is specifically crafted to test the effectiveness and resilience of different network classification methods. To put these methods to the test, we also introduce various types and levels of structural noise. We evaluate five feature extraction techniques: traditional structural measures, Life-Like Network Automata (LLNA), Graph2Vec, Deterministic Tourist Walk (DTW), and its improved version, the Deterministic Tourist Walk with Bifurcation (DTWB). Our experimental results reveal that DTWB surpasses the other methods in classifying both classes and subclasses, even when faced with significant noise. LLNA and DTW also perform well, while Graph2Vec lands somewhere in the middle in terms of accuracy. Interestingly, topological measures, despite their simplicity and common usage, consistently show the weakest classification performance. These findings underscore the necessity of robust feature extraction techniques for effective network classification, particularly in noisy conditions.

cs.SI↗

arXiv2025

Network classification through random walks

Network models have been widely used to study diverse systems and analyze their dynamic behaviors. Given the structural variability of networks, an intriguing question arises: Can we infer the type of system represented by a network based on its structure? This classification problem involves extracting relevant features from the network. Existing literature has proposed various methods that combine structural measurements and dynamical processes for feature extraction. In this study, we introduce a novel approach to characterize networks using statistics from random walks, which can be particularly informative about network properties. We present the employed statistical metrics and compare their performance on multiple datasets with other state-of-the-art feature extraction methods. Our results demonstrate that the proposed method is effective in many cases, often outperforming existing approaches, although some limitations are observed across certain datasets.

cs.SI↗

arXiv2024

An Analytical Approach to the Jaccard Similarity Index

The Jaccard similarity index has often been employed in science and technology as a means to quantify the similarity between two sets. When modified to operate on real-valued values, the Jaccard similarity index can be applied to compare vectors, an operation which plays a central role in visualization, classification, and modeling. The present work aims at developing an analytical approach for estimating the probability density of the Jaccard similarity values as implied by set of data elements characterized by specific statistical densities, with emphasis on the uniform and normal cases. Several theoretical and practical situations can benefit directly from such an approach, as it allows several of the properties of the similarity comparisons among a given dataset to be better understood and anticipated. Situations in which the described approach can be applied include the estimation and visualization of data interrelationships in terms of similarity networks, as well as diverse problems in data analysis, pattern recognition and scientific modeling. In addition to presenting the analytical developments and results, examples are also provided in order to illustrate the potential of the approach. The work also includes extension of the reported developments to modifications of the Jaccard index intended for regularization and control of the sharpness of the implemented comparisons.

physics.data-an↗

arXiv2024

The Jaccard Similarity Mean

The arithmetic mean plays a central role in science and technology, being directly related to the concepts of statistical expectance and centrality. Yet, it is highly susceptible to the presence of outliers or biased interference in the original dataset to which it is applied. Described recently, the concept of similarity means has been preliminary found to have marked robustness to those same effects, especially when adopting the Jaccard similarity index. The present work is aimed at investigating further the properties of similarity means, especially regarding their range, translating and scaling properties, sensitivity and robustness to outliers. Several interesting contributions are reported, including an effective algorithm for obtaining the similarity mean, the analytic and experimental identification of a number of properties, as well as the confirmation of the potential stability of the similarity mean to the presence of outliers. The present work also describes an application case-example in which the Jaccard similarity is successfully employed to study cycles of sunspots, with interesting results.

physics.data-an↗

arXiv2018

Community detection in networks using self-avoiding random walks

Different kinds of random walks have proven to be useful in the study of structural properties of complex networks. Among them, the restricted dynamics of self-avoiding random walks (SAW), which visit only at most once each vertex in the same walk, has been successfully used in network exploration. The detection of communities of strongly connected vertices in networks remains an open problem, despite its importance, due to the high computational complexity of the associated optimization problem and the lack of a unique formal definition of communities. In this work, we propose a SAW-based method to extract the community distribution of a network and show that it achieves high modularity scores, specially for real-world networks. We combine SAW with principal component analysis to define the dissimilarity measure to be used for agglomerative hierarchical clustering. To evaluate the performance of this method we compare it with four popular methods for community detection: Girvan-Newman, Fastgreedy, Walktrap and Infomap using two types of synthetic networks and six well-known real-world cases.

physics.soc-ph↗

arXiv2015

A complex network approach to cloud computing

Cloud computing has become an important means to speed up computing. One problem influencing heavily the performance of such systems is the choice of nodes as servers responsible for executing the users' tasks. In this article we report how complex networks can be used to model such a problem. More specifically, we investigate the performance of the processing respectively to cloud systems underlain by Erdos-Renyi and Barabasi-Albert topology containing two servers. Cloud networks involving two communities not necessarily of the same size are also considered in our analysis. The performance of each configuration is quantified in terms of two indices: the cost of communication between the user and the nearest server, and the balance of the distribution of tasks between the two servers. Regarding the latter index, the ER topology provides better performance than the BA case for smaller average degrees and opposite behavior for larger average degrees. With respect to the cost, smaller values are found in the BA topology irrespective of the average degree. In addition, we also verified that it is easier to find good servers in the ER than in BA. Surprisingly, balance and cost are not too much affected by the presence of communities. However, for a well-defined community network, we found that it is important to assign each server to a different community so as to achieve better performance.

physics.soc-ph↗

arXiv2015

Analyzing complex networks through correlations in centrality measurements

Many real world systems can be expressed as complex networks of interconnected nodes. It is frequently important to be able to quantify the relative importance of the various nodes in the network, a task accomplished by defining some centrality measures, with different centrality definitions stressing different aspects of the network. It is interesting to know to what extent these different centrality definitions are related for different networks. In this work, we study the correlation between pairs of a set of centrality measures for different real world networks and two network models. We show that the centralities are in general correlated, but with stronger correlations for network models than for real networks. We also show that the strength of the correlation of each pair of centralities varies from network to network. Taking this fact into account, we propose the use of a centrality correlation profile, consisting of the values of the correlation coefficients between all pairs of centralities of interest, as a way to characterize networks. Using the yeast protein interaction network as an example we show also that the centrality correlation profile can be used to assess the adequacy of a network model as a representation of a given real network.

physics.soc-ph↗

arXiv2013

A Quantitative Approach to Painting Styles

This research extends a method previously applied to music and philosophy,representing the evolution of art as a time-series where relations like dialectics are measured quantitatively. For that, a corpus of paintings of 12 well-known artists from baroque and modern art is analyzed. A set of 93 features is extracted and the features which most contributed to the classification of painters are selected. The projection space obtained provides the basis to the analysis of measurements. This quantitative measures underlie revealing observations about the evolution of painting styles, specially when compared with other humanity fields already analyzed: while music evolved along a master-apprentice tradition (high dialectics) and philosophy by opposition, painting presents another pattern: constant increasing skewness, low opposition between members of the same movement and opposition peaks in the transition between movements. Differences between baroque and modern movements are also observed in the projected "painting space": while baroque paintings are presented as an overlapped cluster, the modern paintings present minor overlapping and are disposed more widely in the projection than the baroque counterparts. This finding suggests that baroque painters shared aesthetics while modern painters tend to "break rules" and develop their own style.

stat.AP↗

arXiv2012

Predicting Efficiency in master-slave grid computing systems

This work reports a quantitative analysis to predicting the efficiency of distributed computing running in three models of complex networks: Barabási-Albert, Erdős-Rényi and Watts-Strogatz. A master/slave computing model is simulated. A node is selected as master and distributes tasks among the other nodes (the clients). Topological measurements associated with the master node (e.g. its degree or betwenness centrality) are extracted and considered as predictors of the total execution time. It is found that the closeness centrality provides the best alternative. The effect of network size was also investigated.

physics.comp-ph↗

arXiv2012

Can the evolution of music be analyzed in a quantitative manner?

We propose a methodology to study music development by applying multivariate statistics on composers characteristics. Seven representative composers were considered in terms of eight main musical features. Grades were assigned to each characteristic and their correlations were analyzed. A bootstrap method was applied to simulate hundreds of artificial composers influenced by the seven representatives chosen. Afterwards we quantify non-numeric relations like dialectics, opposition and innovation. Composers differences on style and technique were represented as geometrical distances in the feature space, making it possible to quantify, for example, how much Bach and Stockhausen differ from other composers or how much Beethoven influenced Brahms. In addition, we compared the results with a prior investigation on philosophy. Opposition, strong on philosophy, was not remarkable on music. Supporting an observation already considered by music theorists, strong influences were identified between composers by the quantification of dialectics, implying inheritance and suggesting a stronger master-disciple evolution when compared to the philosophy analysis.

physics.data-an↗

arXiv2011

Evaluating links through spectral decomposition

Spectral decomposition has been rarely used to investigate complex networks. In this work we apply this concept in order to define two types of link-directed attacks while quantifying their respective effects on the topology. Several other types of more traditional attacks are also adopted and compared. These attacks had substantially diverse effects, depending on each specific network (models and real-world structures). It is also showed that the spectral-based attacks have special effect in affecting the transitivity of the networks.

physics.soc-ph↗

arXiv2010

On the Efficiency of Data Representation on the Modeling and Characterization of Complex Networks

Specific choices about how to represent complex networks can have a substantial effect on the execution time required for the respective construction and analysis of those structures. In this work we report a comparison of the effects of representing complex networks statically as matrices or dynamically as spase structures. Three theoretical models of complex networks are considered: two types of Erdos-Renyi as well as the Barabasi-Albert model. We investigated the effect of the different representations with respect to the construction and measurement of several topological properties (i.e. degree, clustering coefficient, shortest path length, and betweenness centrality). We found that different forms of representation generally have a substantial effect on the execution time, with the sparse representation frequently resulting in remarkably superior performance.

physics.comp-ph↗

arXiv2008

Analyzing and Modeling Real-World Phenomena with Complex Networks: A Survey of Applications

The success of new scientific areas can be assessed by their potential for contributing to new theoretical approaches and in applications to real-world problems. Complex networks have fared extremely well in both of these aspects, with their sound theoretical basis developed over the years and with a variety of applications. In this survey, we analyze the applications of complex networks to real-world problems and data, with emphasis in representation, analysis and modeling, after an introduction to the main concepts and models. A diversity of phenomena are surveyed, which may be classified into no less than 22 areas, providing a clear indication of the impact of the field of complex networks.

physics.soc-ph↗

arXiv2007

On the effects of geographical constraints on task execution in complex networks

In the present work we investigate the effects of spatial constraints on the efficiency of task execution in systems underlain by geographical complex networks where the probability of connection decreases with the distance between the nodes. The investigation considers several configurations of the parameters defining the network connectivity, and the Barabasi-Albert network model is also considered for comparisons. The results show that the effect of connectivity is significant only for shorter tasks, that the locality of connections implied by the spatial constraints reduces efficency, and that the addition of edges can improve the efficiency of the execution, although with increasing locality of the connections the improvement is small.

physics.soc-ph↗

arXiv2007

Chain motifs: The tails and handles of complex networks

Great part of the interest in complex networks has been motivated by the presence of structured, frequently non-uniform, connectivity. Because diverse connectivity patterns tend to result in distinct network dynamics, and also because they provide the means to identify and classify several types of complex networks, it becomes important to obtain meaningful measurements of the local network topology. In addition to traditional features such as the node degree, clustering coefficient and shortest path, motifs have been introduced in the literature in order to provide complementary description of the networks connectivity. The current work proposes a new type of motifs, namely chains of nodes, namely sequences of connected nodes with degree two. These chains have been subdivided into cords, tails, rings and handles, depending on the type of their extremities (e.g. open or connected). A theoretical analysis of the density of such motifs in random and scale free networks is described, and an algorithm for identifying those motifs in general networks is presented. The potential of considering chains for network characterization has been illustrated with respect to five categories of real-world networks including 16 cases. Several interesting findings were obtained, including the fact that several chains were observed in the real-world networks, especially the WWW, books, and power-grid. The possibility of chains resulting from incompletely sampled networks is also investigated.

cond-mat.dis-nn↗

arXiv2007

Analyzing Trails in Complex Networks

Even more interesting than the intricate organization of complex networks are the dynamical behavior of systems which such structures underly. Among the many types of dynamics, one particularly interesting category involves the evolution of trails left by moving agents progressing through random walks and dilating processes in a complex network. The emergence of trails is present in many dynamical process, such as pedestrian traffic, information flow and metabolic pathways. Important problems related with trails include the reconstruction of the trail and the identification of its source, when complete knowledge of the trail is missing. In addition, the following of trails in multi-agent systems represent a particularly interesting situation related to pedestrian dynamics and swarming intelligence. The present work addresses these three issues while taking into account permanent and transient marks left in the visited nodes. Different topologies are considered for trail reconstruction and trail source identification, including four complex networks models and four real networks, namely the Internet, the US airlines network, an email network and the scientific collaboration network of complex network researchers. Our results show that the topology of the network influence in trail reconstruction, source identification and agent dynamics.

physics.comp-ph↗

arXiv2007

Border trees of complex networks

The comprehensive characterization of the structure of complex networks is essential to understand the dynamical processes which guide their evolution. The discovery of the scale-free distribution and the small world property of real networks were fundamental to stimulate more realistic models and to understand some dynamical processes such as network growth. However, properties related to the network borders (nodes with degree equal to one), one of its most fragile parts, remain little investigated and understood. The border nodes may be involved in the evolution of structures such as geographical networks. Here we analyze complex networks by looking for border trees, which are defined as the subgraphs without cycles connected to the remainder of the network (containing cycles) and terminating into border nodes. In addition to describing an algorithm for identification of such tree subgraphs, we also consider a series of their measurements, including their number of vertices, number of leaves, and depth. We investigate the properties of border trees for several theoretical models as well as real-world networks.

physics.comp-ph↗

arXiv2007

Effective networks for real-time distributed processing

The problem of real-time processing is one of the most challenging current issues in computer sciences. Because of the large amount of data to be treated in a limited period of time, parallel and distributed systems are required, whose performance depends on a series of factors including the interconnectivity of the processing elements, the application model and the communication protocol. Given their flexibility for representing and modeling natural and human-made systems (such as the Internet and WWW), complex networks have become a primary choice in many research areas. The current work presents how the concepts and methods of complex networks can be used to develop realistic models and simulations of distributed real-time system while taking into account two representative interconnection models: uniformly random and scale free (Barabasi-Albert), including the presence of background traffic of messages. The interesting obtained results include the identification of the uniformly random interconnectivity scheme as being largely more efficient than the scale-free counterpart.

physics.soc-ph↗