The objective of this study is to develop a robust boosting framework capable of handling heterogeneous and outlier tasks in Multi-Task Learning (MTL). Conventional MTL methods assume strong relatedness among tasks, which often fails in real-world scenarios involving adversarial or unaligned tasks that degrade performance. To address this limitation, we propose Robust Multi-Task Gradient Boosting (R-MTGB), a novel ensemble framework that explicitly models task heterogeneity within the gradient boosting paradigm. The methodology structures learning into three sequential stages: (1) shared representation learning to extract common patterns across tasks, (2) outlier-aware partitioning using a learnable task-specific parameter to separate and reweight outlier and non-outlier tasks, and (3) task-specific fine-tuning to refine individual predictors. Extensive experiments on both synthetic and real-world datasets demonstrate that R-MTGB consistently improves predictive accuracy, effectively identifies outlier tasks, and enhances generalization compared to state-of-the-art methods. The achieved results confirm that R-MTGB not only ensures robust performance and interpretability through task-level outlier scores but also provides a scalable and principled framework for reliable multi-task learning in heterogeneous environments.

Multi-Task Learning (MTL) aims to boost predictive performance by sharing information across related tasks, however, conventional methods often suffer from negative transfer when unrelated or noisy tasks are forced to share representations. We propose Robust Multi-Task Boosting using Clustering and Local Ensembling (RMB-CLE), a principled MTL framework that integrates error-based task clustering with local ensembling. Unlike prior work that assumes fixed clusters or hand-crafted similarity metrics, RMB-CLE derives inter-task similarity directly from cross-task errors , which admits a principled characterization of cross-task risk in terms of functional mismatch and uncertainty, providing a theoretically grounded mechanism to prevent negative transfer. Tasks are grouped adaptively via agglomerative clustering, and within each cluster, a local ensemble enables robust knowledge sharing while preserving task-specific patterns. Experiments show that RMB-CLE recovers ground-truth clusters in synthetic data and consistently outperforms multi-task, single-task, and pooling-based ensemble methods across diverse synthetic and real-world tabular benchmarks. These results demonstrate that RMB-CLE provides an effective boosting-based framework for robust multi-task learning on structured tabular datasets, where task heterogeneity and negative transfer are central challenges.

A novel sequential procedure to train the final layers of a multi-output regression neural network (NN) based on Gradient Boosting is proposed, where the NN is an additive expansion of the Gradient Boosting.The method works by training portions of the network in an iterative manner in such a way that each new portion of the NN is learnt to compensate for the errors of the already trained portions, and the final result of the network forms by provided weight and the last hidden layer output.This is in contrast to the standard training of NNs in which the whole network is trained to learn the concept at hand.Extensive experiments show the good performance of the proposed method with respect to NN.

Classifier ensemble pruning is a strategy through which a subensemble can be identified via optimizing a predefined performance criterion. Choosing the optimum or suboptimum subensemble decreases the initial ensemble size and increases its predictive performance. In this article, a set of heuristic metrics will be analyzed to guide the pruning process. The analyzed metrics are based on modifying the order of the classifiers in the bagging algorithm, with selecting the first set in the queue. Some of these criteria include general accuracy, the complementarity of decisions, ensemble diversity, the margin of samples, minimum redundancy, discriminant classifiers, and margin hybrid diversity. The efficacy of those metrics is affected by the original ensemble size, the required subensemble size, the kind of individual classifiers, and the number of classes. While the efficiency is measured in terms of the computational cost and the memory space requirements. The performance of those metrics is assessed over fifteen binary and fifteen multiclass benchmark classification tasks, respectively. In addition, the behavior of those metrics against randomness is measured in terms of the distribution of their accuracy around the median. Results show that ordered aggregation is an efficient strategy to generate subensembles that improve both predictive performance as well as computational and memory complexities of the whole bagging ensemble.

Students interact with online courses mainly in two ways: by reviewing the course materials and by solving exercises. However, there are cases in which student behaviour differs and tends to become more focused on solving exercises without looking at course materials. This type of interaction could be an indicative of unethical behavior, such as students who collaborate by sharing answers with one another or fake accounts that are used by students to obtain the correct answers for exercises. In this paper, we propose several metrics to identify these two types of cheating based on co-occurring events and measures of interaction with the course. From the pool of accounts in the course, the pairs of accounts that solve exercises very close in time are considered to be potential collaborating accounts. The proposed metrics are computed for these pairs of accounts and K-means clustering is used to separate pairs of real students who collaborate with respect to students who use fake accounts to harvest the correct answers to exercises. A generalization accuracy over 95% to classify these types of cheating is achieved by using a Support Vector Machine (SVM).

In this work we analyze the class prediction of parallel randomized ensembles by majority voting as an urn model. For a given test instance, the ensemble can be viewed as an urn of marbles of different colors. A marble represents an individual classifier. Its color represents the class label prediction of the corresponding classifier. The sequential querying of classifiers in the ensemble can be seen as draws without replacement from the urn. An analysis of this classical urn model based on the hypergeometric distribution makes it possible to estimate the confidence on the outcome of majority voting when only a fraction of the individual predictions is known. These estimates can be used to speed up the prediction by the ensemble. Specifically, the aggregation of votes can be halted when the confidence in the final prediction is sufficiently high. If one assumes a uniform prior for the distribution of possible votes the analysis is shown to be equivalent to a previous one based on Dirichlet distributions. The advantage of the current approach is that prior knowledge on the possible vote outcomes can be readily incorporated in a Bayesian framework. We show how incorporating this type of problem-specific knowledge into the statistical analysis of majority voting leads to faster classification by the ensemble and allows us to estimate the expected average speed-up beforehand.

The benefits of using SPOC platforms into face-to-face education are yet to be completely analysed. In this work we propose to use SPOCs and video contents to flip the classroom. The objective is to improve the involvement and satisfaction of students with the course, to reduce the drop-out rates and to improve the face-to-face course success rate. We apply these ideas to an undergraduate first year course on Data Structures and Algorithms. The study is validated by collecting data from two consecutive editions of the course, one in which the flipped classroom model and videos were used and other in which they were not. The gathered data included online data about the students' interaction with the SPOC materials and offline data collected during lectures and exams. In the edition where the SPOC materials were available, we have observed a correlation between the students' final marks and their percentage rate of video accesses with respect to the total number of accesses, which indicates a better academic performance for students who prefer videos over documents.

Ensemble learning consists of generating a collection of classifiers whose predictions are then combined to yield a single unified decision. Ensembles of complementary classifiers provide accurate and robust predictions, which are often better than the predictions of the individual classifiers in the ensemble. Nevertheless, ensembles also have some drawbacks: typically, all classifiers are queried to compute the final ensemble prediction. Therefore, all the classifiers need to be accessible to address potential queries. This entails larger storage requirements and slower predictions than a single classifier. Ensemble pruning techniques are useful to alleviate these drawbacks. Static pruning techniques reduce the ensemble size by selecting a sub-ensemble of classifiers from the original ensemble. In dynamic pruning, the querying process is halted when the partial ensemble prediction is sufficient to reach a stable final decision with a reasonable amount of confidence. In this paper, we present the results of a comprehensive analysis of static and dynamic pruning techniques applied to Adaboost ensembles. These ensemble pruning techniques are evaluated on a wide range of classification problems. From this analysis, one concludes that the combination of static and dynamic pruning techniques provides a notable reduction in the memory requirements and an improvement in the classification time without a significant loss of prediction accuracy.

Automatic gender classification of face images is an area of growing interest with multiple applications. Appropriate classifiers should be robust against variations such as illumination, scale and orientation that occur in real world applications. This can be achieved by normalizing the images in order to reduce those variations (alignment, re-scaling, histogram-equalization, etc.), or by extracting features from the original images which are invariant respect to those variations. In this work we perform a robust comparison of eight different classifiers across 100 random partitions of a set of frontal face images. Four of them are state-of-the-art methods in automatic gender classification that use image normalization (SVMs, Neural Networks, ADABOOST and PCA+LDA). The other four strategies use invariant features extracted by SIFT (BOW, Evidence Random Trees, NBNN and Voted Nearest-Neighbor). The best strategies are SVM using normalized images and NBNN, the latter having the advantage that no strong image pre-processing is needed.

This paper proposes an image classification method based on extracting image features using Haar random forests and combining them with a spatial matching kernel SVM. The method works by combining multiple efficient, yet powerful, learning algorithms at every stage of the recognition process. On the task of identifying aquatic stonefly larvae, the method has state-of-the-art or better performance, but with much higher efficiency.

Current work in object categorization discriminates among objects that typically possess gross differences which are readily apparent. However, many applications require making much finer distinctions. We address an insect categorization problem that is so challenging that even trained human experts cannot readily categorize images of insects considered in this paper. The state of the art that uses visual dictionaries, when applied to this problem, yields mediocre results (16.1% error). Three possible explanations for this are (a) the dictionaries are unsupervised, (b) the dictionaries lose the detailed information contained in each keypoint, and (c) these methods rely on hand-engineered decisions about dictionary size. This paper presents a novel, dictionary-free methodology. A random forest of trees is first trained to predict the class of an image based on individual keypoint descriptors. A unique aspect of these trees is that they do not make decisions but instead merely record evidence-i.e., the number of descriptors from training examples of each category that reached each leaf of the tree. We provide a mathematical model showing that voting evidence is better than voting decisions. To categorize a new image, descriptors for all detected keypoints are “dropped” through the trees, and the evidence at each leaf is summed to obtain an overall evidence vector. This is then sent to a second-level classifier to make the categorization decision. We achieve excellent performance (6.4% error) on the 9-class STONEFLY9 data set. Also, our method achieves an average AUC of 0.921 on the PASCAL06 VOC, which places it fifth out of 21 methods reported in the literature and demonstrates that the method also works well for generic object categorization.

The global prediction of a homogeneous ensemble of classifiers generated in independent applications of a randomized learning algorithm on a fixed training set is analyzed within a Bayesian framework. Assuming that majority voting is used, it is possible to estimate with a given confidence level the prediction of the complete ensemble by querying only a subset of classifiers. For a particular instance that needs to be classified, the polling of ensemble classifiers can be halted when the probability that the predicted class will not change when taking into account the remaining votes is above the specified confidence level. Experiments on a collection of benchmark classification problems using representative parallel ensembles, such as bagging and random forests, confirm the validity of the analysis and demonstrate the effectiveness of the instance-based ensemble pruning method proposed.

Several pruning strategies that can be used to reduce the size and increase the accuracy of bagging ensembles are analyzed. These heuristics select subsets of complementary classifiers that, when combined, can perform better than the whole ensemble. The pruning methods investigated are based on modifying the order of aggregation of classifiers in the ensemble. In the original bagging algorithm, the order of aggregation is left unspecified. When this order is random, the generalization error typically decreases as the number of classifiers in the ensemble increases. If an appropriate ordering for the aggregation process is devised, the generalization error reaches a minimum at intermediate numbers of classifiers. This minimum lies below the asymptotic error of bagging. Pruned ensembles are obtained by retaining a fraction of the classifiers in the ordered ensemble. The performance of these pruned ensembles is evaluated in several benchmark classification tasks under different training conditions. The results of this empirical investigation show that ordered aggregation can be used for the efficient generation of pruned ensembles that are competitive, in terms of performance and robustness of classification, with computationally more costly methods that directly select optimal or near-optimal subensembles.

We present a novel ensemble pruning method based on reordering the classifiers obtained from bagging and then selecting a subset for aggregation. Ordering the classifiers generated in bagging makes it possible to build subensembles of increasing size by including first those classifiers that are expected to perform best when aggregated. Ensemble pruning is achieved by halting the aggregation process before all the classifiers generated are included into the ensemble. Pruned subensembles containing between 15% and 30% of the initial pool of classifiers, besides being smaller, improve the generalization performance of the full bagging ensemble in the classification problems investigated.

An efficient procedure for pruning regression ensembles is introduced. Starting from a bagging ensemble, pruning proceeds by ordering the regressors in the original ensemble and then selecting a subset for aggregation. Ensembles of increasing size are built by including first the regressors that perform best when aggregated. This strategy gives an approximate solution to the problem of extracting from the original ensemble the minimum error subensemble, which we prove to be NP-hard. Experiments show that pruned ensembles with only 20% of the initial regressors achieve better generalization accuracies than the complete bagging ensembles. The performance of pruned ensembles is analyzed by means of the bias-variance decomposition of the error.

This paper develops a new method to generate ensembles of classifiers that uses all available data to construct every individual classifier. The base algorithm builds a decision tree in an iterative manner: The training data are divided into two subsets. In each iteration, one subset is used to grow the decision tree, starting from the decision tree produced by the previous iteration. This fully grown tree is then pruned by using the other subset. The roles of the data subsets are interchanged in every iteration. This process converges to a final tree that is stable with respect to the combined growing and pruning steps. To generate a variety of classifiers for the ensemble, we randomly create the subsets needed by the iterative tree construction algorithm. The method exhibits good performance in several standard datasets at low computational cost.