@phdthesis{20357, author = {Ruzickova, Natalia}, isbn = {978-3-99078-066-4}, issn = {2663-337X}, keywords = {gene regulation, networks, omnigenic model, pancreas, collective behaviour}, pages = {160}, publisher = {Institute of Science and Technology Austria}, title = {{Effect propagation in biological networks}}, doi = {10.15479/AT-ISTA-20357}, year = {2025}, } @article{12164, abstract = {A shared-memory counter is a widely-used and well-studied concurrent object. It supports two operations: An Inc operation that increases its value by 1 and a Read operation that returns its current value. In Jayanti et al (SIAM J Comput, 30(2), 2000), Jayanti, Tan and Toueg proved a linear lower bound on the worst-case step complexity of obstruction-free implementations, from read-write registers, of a large class of shared objects that includes counters. The lower bound leaves open the question of finding counter implementations with sub-linear amortized step complexity. In this work, we address this gap. We show that n-process, wait-free and linearizable counters can be implemented from read-write registers with O(log2n) amortized step complexity. This is the first counter algorithm from read-write registers that provides sub-linear amortized step complexity in executions of arbitrary length. Since a logarithmic lower bound on the amortized step complexity of obstruction-free counter implementations exists, our upper bound is within a logarithmic factor of the optimal. The worst-case step complexity of the construction remains linear, which is optimal. This is obtained thanks to a new max register construction with O(logn) amortized step complexity in executions of arbitrary length in which the value stored in the register does not grow too quickly. We then leverage an existing counter algorithm by Aspnes, Attiya and Censor-Hillel [1] in which we “plug” our max register implementation to show that it remains linearizable while achieving O(log2n) amortized step complexity.}, author = {Baig, Mirza Ahad and Hendler, Danny and Milani, Alessia and Travers, Corentin}, issn = {1432-0452}, journal = {Distributed Computing}, keywords = {Computational Theory and Mathematics, Computer Networks and Communications, Hardware and Architecture, Theoretical Computer Science}, pages = {29--43}, publisher = {Springer Nature}, title = {{Long-lived counters with polylogarithmic amortized step complexity}}, doi = {10.1007/s00446-022-00439-5}, volume = {36}, year = {2023}, } @phdthesis{13175, abstract = {About a 100 years ago, we discovered that our universe is inherently noisy, that is, measuring any physical quantity with a precision beyond a certain point is not possible because of an omnipresent inherent noise. We call this - the quantum noise. Certain physical processes allow this quantum noise to get correlated in conjugate physical variables. These quantum correlations can be used to go beyond the potential of our inherently noisy universe and obtain a quantum advantage over the classical applications. Quantum noise being inherent also means that, at the fundamental level, the physical quantities are not well defined and therefore, objects can stay in multiple states at the same time. For example, the position of a particle not being well defined means that the particle is in multiple positions at the same time. About 4 decades ago, we started exploring the possibility of using objects which can be in multiple states at the same time to increase the dimensionality in computation. Thus, the field of quantum computing was born. We discovered that using quantum entanglement, a property closely related to quantum correlations, can be used to speed up computation of certain problems, such as factorisation of large numbers, faster than any known classical algorithm. Thus began the pursuit to make quantum computers a reality. Till date, we have explored quantum control over many physical systems including photons, spins, atoms, ions and even simple circuits made up of superconducting material. However, there persists one ubiquitous theme. The more readily a system interacts with an external field or matter, the more easily we can control it. But this also means that such a system can easily interact with a noisy environment and quickly lose its coherence. Consequently, such systems like electron spins need to be protected from the environment to ensure the longevity of their coherence. Other systems like nuclear spins are naturally protected as they do not interact easily with the environment. But, due to the same reason, it is harder to interact with such systems. After decades of experimentation with various systems, we are convinced that no one type of quantum system would be the best for all the quantum applications. We would need hybrid systems which are all interconnected - much like the current internet where all sorts of devices can all talk to each other - but now for quantum devices. A quantum internet. Optical photons are the best contenders to carry information for the quantum internet. They can carry quantum information cheaply and without much loss - the same reasons which has made them the backbone of our current internet. Following this direction, many systems, like trapped ions, have already demonstrated successful quantum links over a large distances using optical photons. However, some of the most promising contenders for quantum computing which are based on microwave frequencies have been left behind. This is because high energy optical photons can adversely affect fragile low-energy microwave systems. In this thesis, we present substantial progress on this missing quantum link between microwave and optics using electrooptical nonlinearities in lithium niobate. The nonlinearities are enhanced by using resonant cavities for all the involved modes leading to observation of strong direct coupling between optical and microwave frequencies. With this strong coupling we are not only able to achieve almost 100\% internal conversion efficiency with low added noise, thus presenting a quantum-enabled transducer, but also we are able to observe novel effects such as cooling of a microwave mode using optics. The strong coupling regime also leads to direct observation of dynamical backaction effect between microwave and optical frequencies which are studied in detail here. Finally, we also report first observation of microwave-optics entanglement in form of two-mode squeezed vacuum squeezed 0.7dB below vacuum level. With this new bridge between microwave and optics, the microwave-based quantum technologies can finally be a part of a quantum network which is based on optical photons - putting us one step closer to a future with quantum internet. }, author = {Sahu, Rishabh}, isbn = {978-3-99078-030-5}, issn = {2663-337X}, keywords = {quantum optics, electrooptics, quantum networks, quantum communication, transduction}, pages = {202}, publisher = {Institute of Science and Technology Austria}, title = {{Cavity quantum electrooptics}}, doi = {10.15479/at:ista:13175}, year = {2023}, } @phdthesis{12900, abstract = {About a 100 years ago, we discovered that our universe is inherently noisy, that is, measuring any physical quantity with a precision beyond a certain point is not possible because of an omnipresent inherent noise. We call this - the quantum noise. Certain physical processes allow this quantum noise to get correlated in conjugate physical variables. These quantum correlations can be used to go beyond the potential of our inherently noisy universe and obtain a quantum advantage over the classical applications. Quantum noise being inherent also means that, at the fundamental level, the physical quantities are not well defined and therefore, objects can stay in multiple states at the same time. For example, the position of a particle not being well defined means that the particle is in multiple positions at the same time. About 4 decades ago, we started exploring the possibility of using objects which can be in multiple states at the same time to increase the dimensionality in computation. Thus, the field of quantum computing was born. We discovered that using quantum entanglement, a property closely related to quantum correlations, can be used to speed up computation of certain problems, such as factorisation of large numbers, faster than any known classical algorithm. Thus began the pursuit to make quantum computers a reality. Till date, we have explored quantum control over many physical systems including photons, spins, atoms, ions and even simple circuits made up of superconducting material. However, there persists one ubiquitous theme. The more readily a system interacts with an external field or matter, the more easily we can control it. But this also means that such a system can easily interact with a noisy environment and quickly lose its coherence. Consequently, such systems like electron spins need to be protected from the environment to ensure the longevity of their coherence. Other systems like nuclear spins are naturally protected as they do not interact easily with the environment. But, due to the same reason, it is harder to interact with such systems. After decades of experimentation with various systems, we are convinced that no one type of quantum system would be the best for all the quantum applications. We would need hybrid systems which are all interconnected - much like the current internet where all sorts of devices can all talk to each other - but now for quantum devices. A quantum internet. Optical photons are the best contenders to carry information for the quantum internet. They can carry quantum information cheaply and without much loss - the same reasons which has made them the backbone of our current internet. Following this direction, many systems, like trapped ions, have already demonstrated successful quantum links over a large distances using optical photons. However, some of the most promising contenders for quantum computing which are based on microwave frequencies have been left behind. This is because high energy optical photons can adversely affect fragile low-energy microwave systems. In this thesis, we present substantial progress on this missing quantum link between microwave and optics using electrooptical nonlinearities in lithium niobate. The nonlinearities are enhanced by using resonant cavities for all the involved modes leading to observation of strong direct coupling between optical and microwave frequencies. With this strong coupling we are not only able to achieve almost 100\% internal conversion efficiency with low added noise, thus presenting a quantum-enabled transducer, but also we are able to observe novel effects such as cooling of a microwave mode using optics. The strong coupling regime also leads to direct observation of dynamical backaction effect between microwave and optical frequencies which are studied in detail here. Finally, we also report first observation of microwave-optics entanglement in form of two-mode squeezed vacuum squeezed 0.7dB below vacuum level. With this new bridge between microwave and optics, the microwave-based quantum technologies can finally be a part of a quantum network which is based on optical photons - putting us one step closer to a future with quantum internet. }, author = {Sahu, Rishabh}, isbn = {978-3-99078-030-5}, issn = {2663-337X}, keywords = {quantum optics, electrooptics, quantum networks, quantum communication, transduction}, pages = {190}, publisher = {Institute of Science and Technology Austria}, title = {{Cavity quantum electrooptics}}, doi = {10.15479/at:ista:12900}, year = {2023}, } @article{12134, abstract = {Standard epidemic models exhibit one continuous, second order phase transition to macroscopic outbreaks. However, interventions to control outbreaks may fundamentally alter epidemic dynamics. Here we reveal how such interventions modify the type of phase transition. In particular, we uncover three distinct types of explosive phase transitions for epidemic dynamics with capacity-limited interventions. Depending on the capacity limit, interventions may (i) leave the standard second order phase transition unchanged but exponentially suppress the probability of large outbreaks, (ii) induce a first-order discontinuous transition to macroscopic outbreaks, or (iii) cause a secondary explosive yet continuous third-order transition. These insights highlight inherent limitations in predicting and containing epidemic outbreaks. More generally our study offers a cornerstone example of a third-order explosive phase transition in complex systems.}, author = {Börner, Georg and Schröder, Malte and Scarselli, Davide and Budanur, Nazmi B and Hof, Björn and Timme, Marc}, issn = {2632-072X}, journal = {Journal of Physics: Complexity}, keywords = {Artificial Intelligence, Computer Networks and Communications, Computer Science Applications, Information Systems}, number = {4}, publisher = {IOP Publishing}, title = {{Explosive transitions in epidemic dynamics}}, doi = {10.1088/2632-072x/ac99cd}, volume = {3}, year = {2022}, } @article{12147, abstract = {Continuous-time neural networks are a class of machine learning systems that can tackle representation learning on spatiotemporal decision-making tasks. These models are typically represented by continuous differential equations. However, their expressive power when they are deployed on computers is bottlenecked by numerical differential equation solvers. This limitation has notably slowed down the scaling and understanding of numerous natural physical phenomena such as the dynamics of nervous systems. Ideally, we would circumvent this bottleneck by solving the given dynamical system in closed form. This is known to be intractable in general. Here, we show that it is possible to closely approximate the interaction between neurons and synapses—the building blocks of natural and artificial neural networks—constructed by liquid time-constant networks efficiently in closed form. To this end, we compute a tightly bounded approximation of the solution of an integral appearing in liquid time-constant dynamics that has had no known closed-form solution so far. This closed-form solution impacts the design of continuous-time and continuous-depth neural models. For instance, since time appears explicitly in closed form, the formulation relaxes the need for complex numerical solvers. Consequently, we obtain models that are between one and five orders of magnitude faster in training and inference compared with differential equation-based counterparts. More importantly, in contrast to ordinary differential equation-based continuous networks, closed-form networks can scale remarkably well compared with other deep learning instances. Lastly, as these models are derived from liquid networks, they show good performance in time-series modelling compared with advanced recurrent neural network models.}, author = {Hasani, Ramin and Lechner, Mathias and Amini, Alexander and Liebenwein, Lucas and Ray, Aaron and Tschaikowski, Max and Teschl, Gerald and Rus, Daniela}, issn = {2522-5839}, journal = {Nature Machine Intelligence}, keywords = {Artificial Intelligence, Computer Networks and Communications, Computer Vision and Pattern Recognition, Human-Computer Interaction, Software}, number = {11}, pages = {992--1003}, publisher = {Springer Nature}, title = {{Closed-form continuous-time neural networks}}, doi = {10.1038/s42256-022-00556-7}, volume = {4}, year = {2022}, } @article{10602, abstract = {Transforming ω-automata into parity automata is traditionally done using appearance records. We present an efficient variant of this idea, tailored to Rabin automata, and several optimizations applicable to all appearance records. We compare the methods experimentally and show that our method produces significantly smaller automata than previous approaches.}, author = {Kretinsky, Jan and Meggendorfer, Tobias and Waldmann, Clara and Weininger, Maximilian}, issn = {1432-0525}, journal = {Acta Informatica}, keywords = {computer networks and communications, information systems, software}, pages = {585--618}, publisher = {Springer Nature}, title = {{Index appearance record with preorders}}, doi = {10.1007/s00236-021-00412-y}, volume = {59}, year = {2022}, } @article{10842, abstract = {We determine the unique factorization of some polynomials over a finite local commutative ring with identity explicitly. This solves and generalizes the main conjecture of Qian, Shi and Solé in [13]. We also give some applications to enumeration of certain generalized double circulant self-dual and linear complementary dual (LCD) codes over some finite rings together with an application in asymptotic coding theory.}, author = {Köse, Seyda and Özbudak, Ferruh}, issn = {1936-2455}, journal = {Cryptography and Communications}, keywords = {Applied Mathematics, Computational Theory and Mathematics, Computer Networks and Communications}, number = {4}, pages = {933--948}, publisher = {Springer Nature}, title = {{Factorization of some polynomials over finite local commutative rings and applications to certain self-dual and LCD codes}}, doi = {10.1007/s12095-022-00557-8}, volume = {14}, year = {2022}, } @phdthesis{11362, abstract = {Deep learning has enabled breakthroughs in challenging computing problems and has emerged as the standard problem-solving tool for computer vision and natural language processing tasks. One exception to this trend is safety-critical tasks where robustness and resilience requirements contradict the black-box nature of neural networks. To deploy deep learning methods for these tasks, it is vital to provide guarantees on neural network agents' safety and robustness criteria. This can be achieved by developing formal verification methods to verify the safety and robustness properties of neural networks. Our goal is to design, develop and assess safety verification methods for neural networks to improve their reliability and trustworthiness in real-world applications. This thesis establishes techniques for the verification of compressed and adversarially trained models as well as the design of novel neural networks for verifiably safe decision-making. First, we establish the problem of verifying quantized neural networks. Quantization is a technique that trades numerical precision for the computational efficiency of running a neural network and is widely adopted in industry. We show that neglecting the reduced precision when verifying a neural network can lead to wrong conclusions about the robustness and safety of the network, highlighting that novel techniques for quantized network verification are necessary. We introduce several bit-exact verification methods explicitly designed for quantized neural networks and experimentally confirm on realistic networks that the network's robustness and other formal properties are affected by the quantization. Furthermore, we perform a case study providing evidence that adversarial training, a standard technique for making neural networks more robust, has detrimental effects on the network's performance. This robustness-accuracy tradeoff has been studied before regarding the accuracy obtained on classification datasets where each data point is independent of all other data points. On the other hand, we investigate the tradeoff empirically in robot learning settings where a both, a high accuracy and a high robustness, are desirable. Our results suggest that the negative side-effects of adversarial training outweigh its robustness benefits in practice. Finally, we consider the problem of verifying safety when running a Bayesian neural network policy in a feedback loop with systems over the infinite time horizon. Bayesian neural networks are probabilistic models for learning uncertainties in the data and are therefore often used on robotic and healthcare applications where data is inherently stochastic. We introduce a method for recalibrating Bayesian neural networks so that they yield probability distributions over safe decisions only. Our method learns a safety certificate that guarantees safety over the infinite time horizon to determine which decisions are safe in every possible state of the system. We demonstrate the effectiveness of our approach on a series of reinforcement learning benchmarks.}, author = {Lechner, Mathias}, isbn = {978-3-99078-017-6}, keywords = {neural networks, verification, machine learning}, pages = {124}, publisher = {Institute of Science and Technology Austria}, title = {{Learning verifiable representations}}, doi = {10.15479/at:ista:11362}, year = {2022}, } @article{10855, abstract = {Consider a distributed task where the communication network is fixed but the local inputs given to the nodes of the distributed system may change over time. In this work, we explore the following question: if some of the local inputs change, can an existing solution be updated efficiently, in a dynamic and distributed manner? To address this question, we define the batch dynamic \congest model in which we are given a bandwidth-limited communication network and a dynamic edge labelling defines the problem input. The task is to maintain a solution to a graph problem on the labeled graph under batch changes. We investigate, when a batch of α edge label changes arrive, \beginitemize \item how much time as a function of α we need to update an existing solution, and \item how much information the nodes have to keep in local memory between batches in order to update the solution quickly. \enditemize Our work lays the foundations for the theory of input-dynamic distributed network algorithms. We give a general picture of the complexity landscape in this model, design both universal algorithms and algorithms for concrete problems, and present a general framework for lower bounds. In particular, we derive non-trivial upper bounds for two selected, contrasting problems: maintaining a minimum spanning tree and detecting cliques.}, author = {Foerster, Klaus-Tycho and Korhonen, Janne and Paz, Ami and Rybicki, Joel and Schmid, Stefan}, issn = {2476-1249}, journal = {Proceedings of the ACM on Measurement and Analysis of Computing Systems}, keywords = {Computer Networks and Communications, Hardware and Architecture, Safety, Risk, Reliability and Quality, Computer Science (miscellaneous)}, number = {1}, pages = {1--33}, publisher = {Association for Computing Machinery}, title = {{Input-dynamic distributed algorithms for communication networks}}, doi = {10.1145/3447384}, volume = {5}, year = {2021}, } @inproceedings{10206, abstract = {Neural-network classifiers achieve high accuracy when predicting the class of an input that they were trained to identify. Maintaining this accuracy in dynamic environments, where inputs frequently fall outside the fixed set of initially known classes, remains a challenge. The typical approach is to detect inputs from novel classes and retrain the classifier on an augmented dataset. However, not only the classifier but also the detection mechanism needs to adapt in order to distinguish between newly learned and yet unknown input classes. To address this challenge, we introduce an algorithmic framework for active monitoring of a neural network. A monitor wrapped in our framework operates in parallel with the neural network and interacts with a human user via a series of interpretable labeling queries for incremental adaptation. In addition, we propose an adaptive quantitative monitor to improve precision. An experimental evaluation on a diverse set of benchmarks with varying numbers of classes confirms the benefits of our active monitoring framework in dynamic scenarios.}, author = {Lukina, Anna and Schilling, Christian and Henzinger, Thomas A}, booktitle = {21st International Conference on Runtime Verification}, isbn = {9-783-0308-8493-2}, issn = {1611-3349}, keywords = {monitoring, neural networks, novelty detection}, location = {Virtual}, pages = {42--61}, publisher = {Springer Nature}, title = {{Into the unknown: active monitoring of neural networks}}, doi = {10.1007/978-3-030-88494-9_3}, volume = {12974 }, year = {2021}, } @article{9234, abstract = {In this paper, we present two new inertial projection-type methods for solving multivalued variational inequality problems in finite-dimensional spaces. We establish the convergence of the sequence generated by these methods when the multivalued mapping associated with the problem is only required to be locally bounded without any monotonicity assumption. Furthermore, the inertial techniques that we employ in this paper are quite different from the ones used in most papers. Moreover, based on the weaker assumptions on the inertial factor in our methods, we derive several special cases of our methods. Finally, we present some experimental results to illustrate the profits that we gain by introducing the inertial extrapolation steps.}, author = {Izuchukwu, Chinedu and Shehu, Yekini}, issn = {1572-9427}, journal = {Networks and Spatial Economics}, keywords = {Computer Networks and Communications, Software, Artificial Intelligence}, number = {2}, pages = {291--323}, publisher = {Springer Nature}, title = {{New inertial projection methods for solving multivalued variational inequality problems beyond monotonicity}}, doi = {10.1007/s11067-021-09517-w}, volume = {21}, year = {2021}, } @article{8765, abstract = {This paper introduces a simple method for simulating highly anisotropic elastoplastic material behaviors like the dissolution of fibrous phenomena (splintering wood, shredding bales of hay) and materials composed of large numbers of irregularly‐shaped bodies (piles of twigs, pencils, or cards). We introduce a simple transformation of the anisotropic problem into an equivalent isotropic one, and we solve this new “fictitious” isotropic problem using an existing simulator based on the material point method. Our approach results in minimal changes to existing simulators, and it allows us to re‐use popular isotropic plasticity models like the Drucker‐Prager yield criterion instead of inventing new anisotropic plasticity models for every phenomenon we wish to simulate.}, author = {Schreck, Camille and Wojtan, Christopher J}, issn = {1467-8659}, journal = {Computer Graphics Forum}, keywords = {Computer Networks and Communications}, number = {2}, pages = {89--99}, publisher = {Wiley}, title = {{A practical method for animating anisotropic elastoplastic materials}}, doi = {10.1111/cgf.13914}, volume = {39}, year = {2020}, } @misc{8951, abstract = {Gene expression levels are influenced by multiple coexisting molecular mechanisms. Some of these interactions, such as those of transcription factors and promoters have been studied extensively. However, predicting phenotypes of gene regulatory networks remains a major challenge. Here, we use a well-defined synthetic gene regulatory network to study how network phenotypes depend on local genetic context, i.e. the genetic neighborhood of a transcription factor and its relative position. We show that one gene regulatory network with fixed topology can display not only quantitatively but also qualitatively different phenotypes, depending solely on the local genetic context of its components. Our results demonstrate that changes in local genetic context can place a single transcriptional unit within two separate regulons without the need for complex regulatory sequences. We propose that relative order of individual transcriptional units, with its potential for combinatorial complexity, plays an important role in shaping phenotypes of gene regulatory networks.}, author = {Nagy-Staron, Anna A}, keywords = {Gene regulatory networks, Gene expression, Escherichia coli, Synthetic Biology}, publisher = {Institute of Science and Technology Austria}, title = {{Sequences of gene regulatory network permutations for the article "Local genetic context shapes the function of a gene regulatory network"}}, doi = {10.15479/AT:ISTA:8951}, year = {2020}, } @misc{5584, abstract = {This package contains data for the publication "Nonlinear decoding of a complex movie from the mammalian retina" by Deny S. et al, PLOS Comput Biol (2018). The data consists of (i) 91 spike sorted, isolated rat retinal ganglion cells that pass stability and quality criteria, recorded on the multi-electrode array, in response to the presentation of the complex movie with many randomly moving dark discs. The responses are represented as 648000 x 91 binary matrix, where the first index indicates the timebin of duration 12.5 ms, and the second index the neural identity. The matrix entry is 0/1 if the neuron didn't/did spike in the particular time bin. (ii) README file and a graphical illustration of the structure of the experiment, specifying how the 648000 timebins are split into epochs where 1, 2, 4, or 10 discs were displayed, and which stimulus segments are exact repeats or unique ball trajectories. (iii) a 648000 x 400 matrix of luminance traces for each of the 20 x 20 positions ("sites") in the movie frame, with time that is locked to the recorded raster. The luminance traces are produced as described in the manuscript by filtering the raw disc movie with a small gaussian spatial kernel. }, author = {Deny, Stephane and Marre, Olivier and Botella-Soler, Vicente and Martius, Georg S and Tkacik, Gasper}, keywords = {retina, decoding, regression, neural networks, complex stimulus}, publisher = {Institute of Science and Technology Austria}, title = {{Nonlinear decoding of a complex movie from the mammalian retina}}, doi = {10.15479/AT:ISTA:98}, year = {2018}, } @misc{5587, abstract = {Supporting material to the article STATISTICAL MECHANICS FOR METABOLIC NETWORKS IN STEADY-STATE GROWTH boundscoli.dat Flux Bounds of the E. coli catabolic core model iAF1260 in a glucose limited minimal medium. polcoli.dat Matrix enconding the polytope of the E. coli catabolic core model iAF1260 in a glucose limited minimal medium, obtained from the soichiometric matrix by standard linear algebra (reduced row echelon form). ellis.dat Approximate Lowner-John ellipsoid rounding the polytope of the E. coli catabolic core model iAF1260 in a glucose limited minimal medium obtained with the Lovasz method. point0.dat Center of the approximate Lowner-John ellipsoid rounding the polytope of the E. coli catabolic core model iAF1260 in a glucose limited minimal medium obtained with the Lovasz method. lovasz.cpp This c++ code file receives in input the polytope of the feasible steady states of a metabolic network, (matrix and bounds), and it gives in output an approximate Lowner-John ellipsoid rounding the polytope with the Lovasz method NB inputs are referred by defaults to the catabolic core of the E.Coli network iAF1260. For further details we refer to PLoS ONE 10.4 e0122670 (2015). sampleHRnew.cpp This c++ code file receives in input the polytope of the feasible steady states of a metabolic network, (matrix and bounds), the ellipsoid rounding the polytope, a point inside and it gives in output a max entropy sampling at fixed average growth rate of the steady states by performing an Hit-and-Run Monte Carlo Markov chain. NB inputs are referred by defaults to the catabolic core of the E.Coli network iAF1260. For further details we refer to PLoS ONE 10.4 e0122670 (2015).}, author = {De Martino, Daniele and Tkacik, Gasper}, keywords = {metabolic networks, e.coli core, maximum entropy, monte carlo markov chain sampling, ellipsoidal rounding}, publisher = {Institute of Science and Technology Austria}, title = {{Supporting materials "STATISTICAL MECHANICS FOR METABOLIC NETWORKS IN STEADY-STATE GROWTH"}}, doi = {10.15479/AT:ISTA:62}, year = {2018}, } @article{11671, abstract = {Given only the URL of a Web page, can we identify its language? In this article we examine this question. URL-based language classification is useful when the content of the Web page is not available or downloading the content is a waste of bandwidth and time. We built URL-based language classifiers for English, German, French, Spanish, and Italian by applying a variety of algorithms and features. As algorithms we used machine learning algorithms which are widely applied for text classification and state-of-art algorithms for language identification of text. As features we used words, various sized n-grams, and custom-made features (our novel feature set). We compared our approaches with two baseline methods, namely classification by country code top-level domains and classification by IP addresses of the hosting Web servers. We trained and tested our classifiers in a 10-fold cross-validation setup on a dataset obtained from the Open Directory Project and from querying a commercial search engine. We obtained the lowest F1-measure for English (94) and the highest F1-measure for German (98) with the best performing classifiers. We also evaluated the performance of our methods: (i) on a set of Web pages written in Adobe Flash and (ii) as part of a language-focused crawler. In the first case, the content of the Web page is hard to extract and in the second page downloading pages of the “wrong” language constitutes a waste of bandwidth. In both settings the best classifiers have a high accuracy with an F1-measure between 95 (for English) and 98 (for Italian) for the Adobe Flash pages and a precision between 90 (for Italian) and 97 (for French) for the language-focused crawler.}, author = {Baykan, Eda and Weber, Ingmar and Henzinger, Monika H}, issn = {1559-114X}, journal = {ACM Transactions on the Web}, keywords = {Computer Networks and Communications}, number = {1}, publisher = {Association for Computing Machinery}, title = {{A comprehensive study of techniques for URL-based web page language classification}}, doi = {10.1145/2435215.2435218}, volume = {7}, year = {2013}, }