Concha Bielza - Academia.edu (original) (raw)

Papers by Concha Bielza

Mathematics

Over the years, research studies have shown there is a key connection between the microbial commu... more Over the years, research studies have shown there is a key connection between the microbial community in the gut, genes, and immune system. Understanding this association may help discover the cause of complex chronic idiopathic disorders such as inflammatory bowel disease. Even though important efforts have been put into the field, the functions, dynamics, and causation of dysbiosis state performed by the microbial community remains unclear. Machine learning models can help elucidate important connections and relationships between microbes in the human host. Our study aims to extend the current knowledge of associations between the human microbiome and health and disease through the application of dynamic Bayesian networks to describe the temporal variation of the gut microbiota and dynamic relationships between taxonomic entities and clinical variables. We develop a set of preprocessing steps to clean, filter, select, integrate, and model informative metagenomics, metatranscriptom...

Advances in Artificial Intelligence, 2018

The PC algorithm is a popular method for learning the structure of Gaussian Bayesian networks. It... more The PC algorithm is a popular method for learning the structure of Gaussian Bayesian networks. It carries out statistical tests to determine absent edges in the network. It is hence governed by two parameters: (i) The type of test, and (ii) its significance level. These parameters are usually set to values recommended by an expert. Nevertheless, such an approach can suffer from human bias, leading to suboptimal reconstruction results. In this paper we consider a more principled approach for choosing these parameters in an automatic way. For this we optimize a reconstruction score evaluated on a set of different Gaussian Bayesian networks. This objective is expensive to evaluate and lacks a closed-form expression, which means that Bayesian optimization (BO) is a natural choice. BO methods use a model to guide the search and are hence able to exploit smoothness properties of the objective surface. We show that the parameters found by a BO method outperform those found by a random search strategy and the expert recommendation. Importantly, we have found that an often overlooked statistical test provides the best overall reconstruction results.

Most search and score algorithms for learning Bayesian network classifiers from data traverse the... more Most search and score algorithms for learning Bayesian network classifiers from data traverse the space of directed acyclic graphs (DAGs), making arbitrary yet possibly suboptimal arc directionality decisions. This can be remedied by learning in the space of DAG equivalence classes. We provide a number of contributions to existing work along this line. First, we identify the smallest subspace of DAGs that covers all possible class-posterior distributions when data is complete. All the DAGs in this space, which we call minimal class-focused DAGs (MC-DAGs), are such that their every arc is directed towards a child of the class variable. Second, in order to traverse the equivalence classes of MC-DAGs, we adapt the greedy equivalence search (GES) by adding operator validity criteria which ensure GES only visits states within our space. Third, we specify how to efficiently evaluate the discriminative score of a GES operator for MC-DAG in time independent of the number of variables and wi...

ArXiv, 2018

We show that, for generative classifiers, conditional independence corresponds to linear constrai... more We show that, for generative classifiers, conditional independence corresponds to linear constraints for the induced discrimination functions. Discrimination functions of undirected Markov network classifiers can thus be characterized by sets of linear constraints. These constraints are represented by a second order finite difference operator over functions of categorical variables. As an application we study the expressive power of generative classifiers under the undirected Markov property and we present a general method to combine discriminative and generative classifiers.

Multidimensional classification has become one of the most relevant topics in view of the many do... more Multidimensional classification has become one of the most relevant topics in view of the many domains that require a vector of class values to be assigned to a vector of given features. The popularity of multidimensional Bayesian network classifiers has increased in the last few years due to their expressive power and the existence of methods for learning different families of these models. The problem with this approach is that the computational cost of using the learned models is usually high, especially if there are a lot of class variables. Class-bridge decomposability means that the multidimensional classification problem can be divided into multiple subproblems for these models. In this paper, we prove that class-bridge decomposability can also be used to guarantee the tractability of the models. We also propose a strategy for efficiently bounding their inference complexity, providing a simple learning method with an order-based search that obtains tractable multidimensional ...

3 Parameter learning 2 3.1 Bayesian parameter estimation . . . . . . . . . . . . . . . . . . . . ... more 3 Parameter learning 2 3.1 Bayesian parameter estimation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 3.2 Exact model averaging for naive Bayes . . . . . . . . . . . . . . . . . . . . . . . . . . 2 3.3 Weighting to Alleviate the Naive Bayes Independence Assumption . . . . . . . . . . 3 3.4 Attribute-weighted naive Bayes . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4

Nature Neuroscience, 2020

To understand the function of cortical circuits, it is necessary to catalog their cellular divers... more To understand the function of cortical circuits, it is necessary to catalog their cellular diversity. Past attempts to do so using anatomical, physiological or molecular features of cortical cells have not resulted in a unified taxonomy of neuronal or glial cell types, partly due to limited data. Single-cell transcriptomics is enabling, for the first time, systematic high-throughput measurements of cortical cells and generation of datasets that hold the promise of being complete, accurate and permanent. Statistical analyses of these data reveal clusters that often correspond to cell types previously defined by morphological or physiological criteria and that appear conserved across cortical areas and species. To capitalize on these new methods, we propose the adoption of a transcriptome-based taxonomy of cell types for mammalian neocortex. This classification should be hierarchical and use a standardized nomenclature. It should be based on a probabilistic definition of a cell type and incorporate data from different approaches, developmental stages and species. A community-based classification and data aggregation model, such as a knowledge graph, could provide a common foundation for the study of cortical circuits. This community-based classification, nomenclature and data aggregation could serve as an example for cell type atlases in other parts of the body.

Artificial Intelligence Review, 2020

Multi-dimensional classification is a cutting-edge problem, in which the values of multiple class... more Multi-dimensional classification is a cutting-edge problem, in which the values of multiple class variables have to be simultaneously assigned to a given example. It is an extension of the well known multi-label subproblem, in which the class variables are all binary. In this article, we review and expand the set of performance evaluation measures suitable for assessing multi-dimensional classifiers. We focus on multi-dimensional Bayesian network classifiers, which directly cope with multi-dimensional classification and consider dependencies among class variables. A comprehensive survey of this state-of-the-art classification model is offered by covering aspects related to their learning and inference process complexities. We also describe algorithms for structural learning, provide real-world applications where they have been used, and compile a collection of related software.

ABSTRACTPyramidal neurons are the most common neurons in the cerebral cortex. Understanding how t... more ABSTRACTPyramidal neurons are the most common neurons in the cerebral cortex. Understanding how they differ between species is a key challenge in neuroscience. We compared human temporal cortex and mouse visual cortex pyramidal neurons from the Allen Cell Types Database in terms of their electrophysiology and basal dendrites’ morphology. We found that, among other differences, human pyramidal neurons had a higher threshold voltage, a lower input resistance, and a larger basal dendritic arbor. We learned Gaussian Bayesian networks from the data in order to identify correlations and conditional independencies between the variables and compare them between the species. We found strong correlations between electrophysiological and morphological variables in both species. One result is that, in human cells, dendritic arbor width had the strongest effect on input resistance after accounting for the remaining variables. Electrophysiological variables were correlated, in both species, even ...

ABSTRACTPyramidal neurons are the most common cell type in the cerebral cortex. Understanding how... more ABSTRACTPyramidal neurons are the most common cell type in the cerebral cortex. Understanding how they differ between species is a key challenge in neuroscience. A recent study provided a unique set of human and mouse pyramidal neurons of the CA1 region of the hippocampus, and used it to compare the morphology of apical and basal dendritic branches of the two species. The study found inter-species differences in the magnitude of the morphometrics and similarities regarding their variation with respect to morphological determinants such as branch type and branch order. We use the same data set to perform additional comparisons of basal dendrites. In order to isolate the heterogeneity due to intrinsic differences between species from the heterogeneity due to differences in morphological determinants, we fit multivariate models over the morphometrics and the determinants. In particular, we use conditional linear Gaussian Bayesian networks, which provide a concise graphical representati...

NeuroSuites-BNs is the first web framework for learning, visualizing, and interpreting Bayesian n... more NeuroSuites-BNs is the first web framework for learning, visualizing, and interpreting Bayesian networks (BNs) that can scale to tens of thousands of nodes while providing fast and friendly user experience. All the necessary features that enable this are reviewed in this paper; these features include scalability, extensibility, interoperability, ease of use, and interpretability. Scalability is the key factor in learning and processing massive networks within reasonable time; for a maintainable software open to new functionalities, extensibility and interoperability are necessary. Ease of use and interpretability are fundamental aspects of model interpretation, fairly similar to the case of the recent explainable artificial intelligence trend. We present the capabilities of our proposed framework by highlighting a real example of a BN learned from genomic data obtained from Allen Institute for Brain Science. The extensibility properties of the software are also demonstrated with the...

Data & Knowledge Engineering, 2019

Capturing the dependences among circular variables within supervised classification models is a c... more Capturing the dependences among circular variables within supervised classification models is a challenging task. In this paper, we propose four different supervised Bayesian classification algorithms where the predictor variables follow all circular wrapped Cauchy distributions. For this purpose, we introduce four wrapped Cauchy classifiers. The bivariate wrapped Cauchy distribution is the only bivariate circular distribution whose marginals and conditionals are also wrapped Cauchy distributions, a property that makes it possible to define these models easily. Furthermore, the wrapped Cauchy tree-augmented naive Bayes classifier requires the definition of a conditional circular mutual information measure between variables that follow wrapped Cauchy distributions. Synthetic data is used to illustrate, compare and evaluate the classification algorithms (including a comparison with the Gaussian TAN classifier, decision tree, random forest, multinomial logistic regression, support vector machine and simple neural network), leading to satisfactory predictive results. We also use a real neuromorphological dataset obtained from juvenile rat somatosensory cortex cells, where we measure the bifurcation angles of the dendritic basal arbors.

The R Journal, 2019

The bnclassify package provides state-of-the art algorithms for learning Bayesian network classif... more The bnclassify package provides state-of-the art algorithms for learning Bayesian network classifiers from data. For structure learning it provides variants of the greedy hill-climbing search, a well-known adaptation of the Chow-Liu algorithm and averaged one-dependence estimators. It provides Bayesian and maximum likelihood parameter estimation, as well as three naive-Bayesspecific methods based on discriminative score optimization and Bayesian model averaging. The implementation is efficient enough to allow for time-consuming discriminative scores on mediumsized data sets. The bnclassify package provides utilities for model evaluation, such as cross-validated accuracy and penalized log-likelihood scores, and analysis of the underlying networks, including network plotting via the Rgraphviz package. It is extensively tested, with over 200 automated tests that give a code coverage of 94%. Here we present the main functionalities, illustrate them with a number of data sets, and comment on related software.

International Journal of Approximate Reasoning, 2018

Multidimensional Bayesian network classifiers have gained popularity over the last few years due ... more Multidimensional Bayesian network classifiers have gained popularity over the last few years due to their expressive power and their intuitive graphical representation. A drawback of this approach is that their use to perform multidimensional classification, a generalization of multi-label classification, can be very computationally demanding when there are a large number of class variables. Thus, a key challenge in this field is to ensure the tractability of these models during the learning process. In this paper, we show how information about the most common queries of multidimen-sional Bayesian network classifiers affects the complexity of these models. We provide upper bounds for the complexity of the most probable explanations and marginals of class variables conditioned to an instantiation of all feature variables. We use these bounds to propose efficient strategies for bounding the complexity of multidimensional Bayesian network classifiers during the learning process, and provide a simple learning method with an order-based search that guarantees the tractability of the returned models. Experimental results show that our approach is competitive with other methods in the state of the art and also ensures the tractability of the learned models.

Journal of Heuristics, 2017

Finding the degree-constrained minimum spanning tree (DCMST) of a graph is a widely studied NP-ha... more Finding the degree-constrained minimum spanning tree (DCMST) of a graph is a widely studied NP-hard problem. One of its most important applications is network design. Here we deal with a new variant of the DCMST problem, which consists of finding not only the degree-but also the roleconstrained minimum spanning tree (DRCMST), i.e., we add constraints to restrict the role of the nodes in the tree to root, intermediate or leaf node. Furthermore, we do not limit the number of root nodes to one, thereby, generally, building a forest of DRCMSTs. The modeling of network design problems can benefit from the possibility of generating more than one tree and determining the role of the nodes in the network. We propose a novel permutation-based representation to encode these forests. In this new representation, one permutation simultaneously encodes all the trees to be built. We simulate a wide variety of DRCMST problem instances which we optimize using different evolutionary computation algorithms encoding individuals of the population using the proposed representation. To illustrate the applicability of our approach, we formulate the trans-European transport network as a DRCMST problem. In this network design, we simultaneously optimize nine transport corridors and show that it is straightforward using the proposed representation to add constraints depending on the specific characteristics of the network. Keywords Degree-and role-constrained minimum spanning tree • forest • network design • permutation problems • evolutionary computation

Machine Learning for Cyber Physical Systems, 2016

We present the application of a cyber-physical system for inprocess quality control based on the ... more We present the application of a cyber-physical system for inprocess quality control based on the visual inspection of a laser surface heat treatment process. To do this, we propose a classication framework that detects anomalies in recorded video sequences that have been preprocessed using a clustering-based method for feature subset selection. One peculiarity of the classication task is that there are no examples with errors, since major irregularities seldom occur in ecient industrial processes. Additionally, the parts to be processed are expensive so the sample size is small. The proposed framework uses anomaly detection, cross-validation and sampling techniques to deal with these issues. Regarding anomaly detection, dynamic Bayesian networks (DBNs) are used to represent the temporal characteristics of the normal process. Experiments are conducted with two dierent types of DBN structure learning algorithms, and classication performance is assessed on both anomalyfree examples and sequences with anomalies simulated by experts.

Lecture Notes in Computer Science, 2016

s, {m c b ie lz a ,p e d r o .la r r a n a g a }@ fi.u p m .e s h t t p : / / c i g. f i. u p m. ... more s, {m c b ie lz a ,p e d r o .la r r a n a g a }@ fi.u p m .e s h t t p : / / c i g. f i. u p m. e s A b s t r a c t. Modelling the relationship between directional variables is a nearly unexplored field. The bivariate wrapped Cauchy distribution has recently emerged as the first closed family of bivariate directional distri butions (marginals and conditionals belong to the same family). In this paper, we introduce a tree-structured Bayesian network suitable for m od elling directional data with bivariate wrapped Cauchy distributions. W e describe the structure learning algorithm used to learn the Bayesian net work. W e also report some simulation studies to illustrate the algorithms including a comparison with the Gaussian structure learning algorithm and an empirical experiment on real morphological data from juvenile rat somatosensory cortex cells.

Intelligent Data Analysis, 2016

In recent years, a plethora of approaches have been proposed to deal with the increasingly challe... more In recent years, a plethora of approaches have been proposed to deal with the increasingly challenging task of mining concept-drifting data streams. However, most of these approaches can only be applied to uni-dimensional classification problems where each input instance has to be assigned to a single output class variable. The problem of mining multi-dimensional data streams, which includes multiple output class variables, is largely unexplored and only few streaming multi-dimensional approaches have been recently introduced. In this paper, we propose a novel adaptive method, named Locally Adaptive-MB-MBC (LA-MB-MBC), for mining streaming multi-dimensional data. To this end, we make use of multi-dimensional Bayesian network classifiers (MBCs) as models. Basically, LAMB -MBC monitors the concept drift over time using the average log-likelihood score and the Page-Hinkley test. Then, if a concept drift is detected, LAMB -MBC adapts the current MBC network locally around

International Journal of Approximate Reasoning, 2016

Multi-label classification problems require each instance to be assigned a subset of a defined se... more Multi-label classification problems require each instance to be assigned a subset of a defined set of labels. This problem is equivalent to finding a multi-valued decisión function that predicts a vector of binary classes. In this paper we study the decisión boundaries of two widely used approaches for building multi-label classifiers, when Bayesian network-augmented naive Bayes classifiers are used as base models: Binary relevance method and chain classifiers. In particular extending previous single-label results to multi-label chain classifiers, we find polynomial expressions for the multi-valued decisión functions associated with these methods. We prove upper boundings on the expressive power of both methods and we prove that chain classifiers provide a more expressive model than the binary relevance method.

Lecture Notes in Computer Science, 2002

We have recently introduced a method for minimising the storage space of huge decision tables fac... more We have recently introduced a method for minimising the storage space of huge decision tables faced after solving real-scale decisionmaking problems under uncertainty [4]. In this paper, the method is combined with a proposal of a query system to answer expert questions about the preferred action, for a given instantiation of decision table attributes. The main difficulty is to accurately answer queries associated with incomplete instantiations. Moreover, the decision tables often only include a subset of the whole problem solution due to computational problems, leading to uncertain responses. Our proposal establishes an automatic and interactive dialogue between the decision support system and the expert to extract information from the expert to reduce uncertainty. Typically, the process involves learning a Bayesian network structure from a relevant part of the decision table and the computation of some interesting conditional probabilities that are revised accordingly.