ALBERT

Description: There is no uniform approach in the literature for modelling sequential correlations in sequence classification problems. It is easy to find examples of unstructured models ( e.g.  logistic regression) where correlations are not taken into account at all, but there are also many examples where the correlations are explicitly incorporated into a—potentially computationally expensive—structured classification model ( e.g.  conditional random fields). In this paper we lay theoretical and empirical foundations for clarifying the types of problem which necessitate direct modelling of correlations in sequences, and the types of problem where unstructured models that capture sequential aspects solely through features are sufficient. The theoretical work in this paper shows that the rate of decay of auto-correlations within a sequence is related to the excess classification risk that is incurred by ignoring the structural aspect of the data. This is an intuitively appealing result, demonstrating the intimate link between the auto-correlations and excess classification risk. Drawing directly on this theory, we develop well-founded visual analytics tools that can be applied a priori on data sequences and we demonstrate how these tools can guide practitioners in specifying feature representations based on auto-correlation profiles. Empirical analysis is performed on three sequential datasets. With baseline feature templates, structured and unstructured models achieve similar performance, indicating no initial preference for either model. We then apply the visual analytics tools to the datasets, and show that classification performance in all cases is improved over baseline results when our tools are involved in defining feature representations.

Description: We study the use of replicator dynamics for data clustering and structure identification. We investigate that replicator dynamics, while running, reveals informative transitions that correspond to the significant cuts over data. Occurrence of such transitions is significantly faster than the convergence of replicator dynamics. We exploit this observation to design an efficient clustering algorithm in two steps: (1) Cut Identification, and (2) Cluster Pruning. We propose an appropriate regularization to accelerate the appearance of transitions which leads to an adaptive replicator dynamics. A main computational advantage of this regularization is that the optimal solution of the corresponding objective function can be still computed via performing a replicator dynamics. Our experiments on synthetic and real-world datasets show the effectiveness of our algorithm compared to the alternatives.

Description: In ensemble systems, several experts, which may have access to possibly different data, make decisions which are then fused by a combiner (meta-learner) to obtain a final result. Such ensemble-based systems are well-suited for processing big-data from sources such as social media, in-stream monitoring systems, networks, and markets, and provide more accurate results than single expert systems. However, most existing ensemble-learning techniques have two limitations: (i) they are supervised, and hence they require access to the true label, which is often unknown in practice, and (ii) they are not able to evaluate the impact of the various data features/contexts on the final decision, and hence they do not learn which data is required. In this paper we propose a joint estimation–detection method for evaluating the accuracy of each expert as a function of the data features/context and for fusing the experts decisions. The proposed method is unsupervised: the true labels are not available and no prior information is assumed regarding the performance of each expert. Extensive simulation results show the improvement of the proposed method as compared to the state-of-the-art approaches. We also provide a systematic, unsupervised method for ranking the informativeness of each feature on the decision making process.

Description: Restricted Boltzmann Machines (RBMs) and models derived from them have been successfully used as basic building blocks in deep artificial neural networks for automatic features extraction, unsupervised weights initialization, but also as density estimators. Thus, their generative and discriminative capabilities, but also their computational time are instrumental to a wide range of applications. Our main contribution is to look at RBMs from a topological perspective, bringing insights from network science. Firstly, here we show that RBMs and Gaussian RBMs (GRBMs) are bipartite graphs which naturally have a small-world topology. Secondly, we demonstrate both on synthetic and real-world datasets that by constraining RBMs and GRBMs to a scale-free topology (while still considering local neighborhoods and data distribution), we reduce the number of weights that need to be computed by a few orders of magnitude, at virtually no loss in generative performance. Thirdly, we show that, for a fixed number of weights, our proposed sparse models (which by design have a higher number of hidden neurons) achieve better generative capabilities than standard fully connected RBMs and GRBMs (which by design have a smaller number of hidden neurons), at no additional computational costs.

Description: Frank–Wolfe (FW) algorithms have been often proposed over the last few years as efficient solvers for a variety of optimization problems arising in the field of machine learning. The ability to work with cheap projection-free iterations and the incremental nature of the method make FW a very effective choice for many large-scale problems where computing a sparse model is desirable. In this paper, we present a high-performance implementation of the FW method tailored to solve large-scale Lasso regression problems, based on a randomized iteration, and prove that the convergence guarantees of the standard FW method are preserved in the stochastic setting. We show experimentally that our algorithm outperforms several existing state of the art methods, including the Coordinate Descent algorithm by Friedman et al. (one of the fastest known Lasso solvers), on several benchmark datasets with a very large number of features, without sacrificing the accuracy of the model. Our results illustrate that the algorithm is able to generate the complete regularization path on problems of size up to four million variables in 〈1 min.

Description: Recommendation systems often rely on point-wise loss metrics such as the mean squared error. However, in real recommendation settings only few items are presented to a user. This observation has recently encouraged the use of rank-based metrics. LambdaMART is the state-of-the-art algorithm in learning to rank which relies on such a metric. Motivated by the fact that very often the users’ and items’ descriptions as well as the preference behavior can be well summarized by a small number of hidden factors, we propose a novel algorithm, LambdaMART matrix factorization (LambdaMART-MF), that learns latent representations of users and items using gradient boosted trees. The algorithm factorizes LambdaMART by defining relevance scores as the inner product of the learned representations of the users and items. We regularise the learned latent representations so that they reflect the user and item manifolds as these are defined by their original feature based descriptors and the preference behavior. We also propose to use a weighted variant of NDCG to reduce the penalty for similar items with large rating discrepancy. We experiment on two very different recommendation datasets, meta-mining and movies-users, and evaluate the performance of LambdaMART-MF, with and without regularization, in the cold start setting as well as in the simpler matrix completion setting. The experiments show that the factorization of LambdaMart brings significant performance improvements both in the cold start and the matrix completion settings. The incorporation of regularisation seems to have a smaller performance impact.

Description: Many important real-world applications of machine learning, statistical physics, constraint programming and information theory can be formulated using graphical models that involve determinism and cycles. Accurate and efficient inference and training of such graphical models remains a key challenge. Markov logic networks (MLNs) have recently emerged as a popular framework for expressing a number of problems which exhibit these properties. While loopy belief propagation (LBP) can be an effective solution in some cases; unfortunately, when both determinism and cycles are present, LBP frequently fails to converge or converges to inaccurate results. As such, sampling based algorithms have been found to be more effective and are more popular for general inference tasks in MLNs. In this paper, we introduce Generalized arc-consistency Expectation Maximization Message-Passing (GEM-MP), a novel message-passing approach to inference in an extended factor graph that combines constraint programming techniques with variational methods. We focus our experiments on Markov logic and Ising models but the method is applicable to graphical models in general. In contrast to LBP, GEM-MP formulates the message-passing structure as steps of variational expectation maximization. Moreover, in the algorithm we leverage the local structures in the factor graph by using generalized arc consistency when performing a variational mean-field approximation. Thus each such update increases a lower bound on the model evidence. Our experiments on Ising grids, entity resolution and link prediction problems demonstrate the accuracy and convergence of GEM-MP over existing state-of-the-art inference algorithms such as MC-SAT, LBP, and Gibbs sampling, as well as convergent message passing algorithms such as the concave–convex procedure, residual BP, and the L2-convex method.

Description: Concerned with predicting equipment failures, predictive maintenance has a high impact both at a technical and at a financial level. Most modern equipments have logging systems that allow us to collect a diversity of data regarding their operation and health. Using data mining models for anomaly and novelty detection enables us to explore those datasets, building predictive systems that can detect and issue an alert when a failure starts evolving, avoiding the unknown development up to breakdown. In the present case, we use a failure detection system to predict train door breakdowns before they happen using data from their logging system. We use sensor data from pneumatic valves that control the open and close cycles of a door. Still, the failure of a cycle does not necessarily indicates a breakdown. A cycle might fail due to user interaction. The goal of this study is to detect structural failures in the automatic train door system, not when there is a cycle failure, but when there are sequences of cycle failures. We study three methods for such structural failure detection: outlier detection, anomaly detection and novelty detection, using different windowing strategies. We propose a two-stage approach, where the output of a point-anomaly algorithm is post-processed by a low-pass filter to obtain a subsequence-anomaly detection. The main result of the two-level architecture is a strong impact in the false alarm rate.

Description: This paper introduces Accelerated Logistic Regression : a hybrid generative-discriminative approach to training Logistic Regression with high-order features. We present two main results: (1) that our combined generative-discriminative approach significantly improves the efficiency of Logistic Regression and (2) that incorporating higher order features (i.e. features that are the Cartesian products of the original features) reduces the bias of Logistic Regression, which in turn significantly reduces its error on large datasets. We assess the efficacy of Accelerated Logistic Regression by conducting an extensive set of experiments on 75 standard datasets. We demonstrate its competitiveness, particularly on large datasets, by comparing against state-of-the-art classifiers including Random Forest and Averaged n -Dependence Estimators.