David Martínez-Rego
Research Subjects
David Martínez-Rego has a total of 47 co-authors. Here are the top co-authors by number of shared publications:
- Amparo Alonso-Betanzos
Universidade da Coruña
13 shared publications - Oscar Fontenla-Romero
Universidade da Coruña
10 shared publications Amparo Alonso-Betanzos
5 shared publications- Jose Manuel Benitez
Advanced Medical Imaging Group (TeCe22), Instituto de Investigación Biosanitaria de Granada (ibs.GRANADA), 18012 Granada, Spain
5 shared publications Beatriz Pérez-Sánchez
3 shared publications- Emil Constantine Lupu
Imperial College London
3 shared publications
Latest Publications
- 15 September 2022
- Published by Springer Nature
- p. 680-691
Jacobian Ensembles Improve Robustness Trade-Offs to Adversarial Attacks
- 15 September 2022
- Published by Springer Nature
- p. 680-691
Jacobian Ensembles Improve Robustness Trade-Offs to Adversarial Attacks
- Open Access
Jacobian Ensembles Improve Robustness Trade-offs to Adversarial Attacks
Deep neural networks have become an integral part of our software infrastructure and are being deployed in many widely-used and safety-critical applications. However, their integration into many systems also brings with it the vulnerability to test time attacks in the form of Universal Adversarial Perturbations (UAPs). UAPs are a class of perturbations that when applied to any input causes model misclassification. Although there is an ongoing effort to defend models against these adversarial attacks, it is often difficult to reconcile the trade-offs in model accuracy and robustness to adversarial attacks. Jacobian regularization has been shown to improve the robustness of models against UAPs, whilst model ensembles have been widely adopted to improve both predictive performance and model robustness. In this work, we propose a novel approach, Jacobian Ensembles-a combination of Jacobian regularization and model ensembles to significantly increase the robustness against UAPs whilst maintaining or improving model accuracy. Our results show that Jacobian Ensembles achieves previously unseen levels of accuracy and robustness, greatly improving over previous methods that tend to skew towards only either accuracy or robustness.
Open AccessJacobian Ensembles Improve Robustness Trade-offs to Adversarial Attacks
Deep neural networks have become an integral part of our software infrastructure and are being deployed in many widely-used and safety-critical applications. However, their integration into many systems also brings with it the vulnerability to test time attacks in the form of Universal Adversarial Perturbations (UAPs). UAPs are a class of perturbations that when applied to any input causes model misclassification. Although there is an ongoing effort to defend models against these adversarial attacks, it is often difficult to reconcile the trade-offs in model accuracy and robustness to adversarial attacks. Jacobian regularization has been shown to improve the robustness of models against UAPs, whilst model ensembles have been widely adopted to improve both predictive performance and model robustness. In this work, we propose a novel approach, Jacobian Ensembles-a combination of Jacobian regularization and model ensembles to significantly increase the robustness against UAPs whilst maintaining or improving model accuracy. Our results show that Jacobian Ensembles achieves previously unseen levels of accuracy and robustness, greatly improving over previous methods that tend to skew towards only either accuracy or robustness.
- 7 September 2021
- Published by Springer Nature
- p. 202-213
Jacobian Regularization for Mitigating Universal Adversarial Perturbations
- 7 September 2021
- Published by Springer Nature
- p. 202-213
Jacobian Regularization for Mitigating Universal Adversarial Perturbations
- 1 June 2019
- Published by Elsevier in Information Sciences
- Vol. 487, 115-127
Large scale anomaly detection in mixed numerical and categorical input spaces
- 1 June 2019
- Published by Elsevier in Information Sciences
- Vol. 487, 115-127
Large scale anomaly detection in mixed numerical and categorical input spaces
- 31 July 2018
- Published by Springer Nature in Progress in Artificial Intelligence
- Vol. 8 (1) , 101-109
Optimizing novelty and diversity in recommendations
- 31 July 2018
- Published by Springer Nature in Progress in Artificial Intelligence
- Vol. 8 (1) , 101-109
Optimizing novelty and diversity in recommendations
- 6 July 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics: Systems
- Vol. 48 (9) , 1441-1453
An Information Theory-Based Feature Selection Framework for Big Data Under Apache Spark
With the advent of extremely high dimensional datasets, dimensionality reduction techniques are becoming mandatory. Of the many techniques available, feature selection (FS) is of growing interest for its ability to identify both relevant features and frequently repeated instances in huge datasets. We aim to demonstrate that standard FS methods can be parallelized in big data platforms like Apache Spark so as to boost both performance and accuracy. We propose a distributed implementation of a generic FS framework that includes a broad group of well-known information theory-based methods. Experimental results for a broad set of real-world datasets show that our distributed framework is capable of rapidly dealing with ultrahigh-dimensional datasets as well as those with a huge number of samples, outperforming the sequential version in all the cases studied.
- 6 July 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics: Systems
- Vol. 48 (9) , 1441-1453
An Information Theory-Based Feature Selection Framework for Big Data Under Apache Spark
With the advent of extremely high dimensional datasets, dimensionality reduction techniques are becoming mandatory. Of the many techniques available, feature selection (FS) is of growing interest for its ability to identify both relevant features and frequently repeated instances in huge datasets. We aim to demonstrate that standard FS methods can be parallelized in big data platforms like Apache Spark so as to boost both performance and accuracy. We propose a distributed implementation of a generic FS framework that includes a broad group of well-known information theory-based methods. Experimental results for a broad set of real-world datasets show that our distributed framework is capable of rapidly dealing with ultrahigh-dimensional datasets as well as those with a huge number of samples, outperforming the sequential version in all the cases studied.
- 1 December 2016
- Published by Elsevier in Pattern Recognition Letters
- Vol. 84, 8-14
Fault detection via recurrence time statistics and one-class classification
- 1 December 2016
- Published by Elsevier in Pattern Recognition Letters
- Vol. 84, 8-14
Fault detection via recurrence time statistics and one-class classification
- 3 November 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3101-3109
Distributed variance regularized Multitask Learning
Past research on Multitask Learning (MTL) has focused mainly on devising adequate regularizers and less on their scalability. In this paper, we present a method to scale up MTL methods which penalize the variance of the task weight vectors. The method builds upon the alternating direction method of multipliers to decouple the variance regularizer. It can be efficiently implemented by a distributed algorithm, in which the tasks are first independently solved and subsequently corrected to pool information from other tasks. We show that the method works well in practice and convergences in few distributed iterations. Furthermore, we empirically observe that the number of iterations is nearly independent of the number of tasks, yielding a computational gain of O(T) over standard solvers. We also present experiments on a large URL classification dataset, which is challenging both in terms of volume of data points and dimensionality. Our results confirm that MTL can obtain superior performance over either learning a common model or independent task learning.
- 3 November 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3101-3109
Distributed variance regularized Multitask Learning
Past research on Multitask Learning (MTL) has focused mainly on devising adequate regularizers and less on their scalability. In this paper, we present a method to scale up MTL methods which penalize the variance of the task weight vectors. The method builds upon the alternating direction method of multipliers to decouple the variance regularizer. It can be efficiently implemented by a distributed algorithm, in which the tasks are first independently solved and subsequently corrected to pool information from other tasks. We show that the method works well in practice and convergences in few distributed iterations. Furthermore, we empirically observe that the number of iterations is nearly independent of the number of tasks, yielding a computational gain of O(T) over standard solvers. We also present experiments on a large URL classification dataset, which is challenging both in terms of volume of data points and dimensionality. Our results confirm that MTL can obtain superior performance over either learning a common model or independent task learning.
- Open Access
An Information Theoretic Feature Selection Framework for Big Data under Apache Spark
With the advent of extremely high dimensional datasets, dimensionality reduction techniques are becoming mandatory. Among many techniques, feature selection has been growing in interest as an important tool to identify relevant features on huge datasets --both in number of instances and features--. The purpose of this work is to demonstrate that standard feature selection methods can be parallelized in Big Data platforms like Apache Spark, boosting both performance and accuracy. We thus propose a distributed implementation of a generic feature selection framework which includes a wide group of well-known Information Theoretic methods. Experimental results on a wide set of real-world datasets show that our distributed framework is capable of dealing with ultra-high dimensional datasets as well as those with a huge number of samples in a short period of time, outperforming the sequential version in all the cases studied.
Open AccessAn Information Theoretic Feature Selection Framework for Big Data under Apache Spark
With the advent of extremely high dimensional datasets, dimensionality reduction techniques are becoming mandatory. Among many techniques, feature selection has been growing in interest as an important tool to identify relevant features on huge datasets --both in number of instances and features--. The purpose of this work is to demonstrate that standard feature selection methods can be parallelized in Big Data platforms like Apache Spark, boosting both performance and accuracy. We thus propose a distributed implementation of a generic feature selection framework which includes a wide group of well-known Information Theoretic methods. Experimental results on a wide set of real-world datasets show that our distributed framework is capable of dealing with ultra-high dimensional datasets as well as those with a huge number of samples in a short period of time, outperforming the sequential version in all the cases studied.
- 9 July 2016
- Published by Hindawi Limited in International Journal of Intelligent Systems
- Vol. 32 (2) , 134-152
Fast-mRMR: Fast Minimum Redundancy Maximum Relevance Algorithm for High-Dimensional Big Data
With the advent of large‐scale problems, feature selection has become a fundamental preprocessing step to reduce input dimensionality. The minimum‐redundancy‐maximum‐relevance (mRMR) selector is considered one of the most relevant methods for dimensionality reduction due to its high accuracy. However, it is a computationally expensive technique, sharply affected by the number of features. This paper presents fast‐mRMR, an extension of mRMR, which tries to overcome this computational burden. Associated with fast‐mRMR, we include a package with three implementations of this algorithm in several platforms, namely, CPU for sequential execution, GPU (graphics processing units) for parallel computing, and Apache Spark for distributed computing using big data technologies.
- 9 July 2016
- Published by Hindawi Limited in International Journal of Intelligent Systems
- Vol. 32 (2) , 134-152
Fast-mRMR: Fast Minimum Redundancy Maximum Relevance Algorithm for High-Dimensional Big Data
With the advent of large‐scale problems, feature selection has become a fundamental preprocessing step to reduce input dimensionality. The minimum‐redundancy‐maximum‐relevance (mRMR) selector is considered one of the most relevant methods for dimensionality reduction due to its high accuracy. However, it is a computationally expensive technique, sharply affected by the number of features. This paper presents fast‐mRMR, an extension of mRMR, which tries to overcome this computational burden. Associated with fast‐mRMR, we include a package with three implementations of this algorithm in several platforms, namely, CPU for sequential execution, GPU (graphics processing units) for parallel computing, and Apache Spark for distributed computing using big data technologies.