Sentiment analysis is a common task in natural language processing that aims to detect polarity of a text document (typically a consumer review). In the simplest settings, we discriminate only between positive and negative sentiment, turning the task into a standard binary classification problem. We compare several ma- chine learning approaches to this problem, and combine them to achieve the best possible results. We show how to use for this task the standard generative lan- guage models, which are slightly complementary to the state of the art techniques. We achieve strong results on a well-known dataset of IMDB movie reviews. Our results are easily reproducible, as we publish also the code needed to repeat the experiments. This should simplify further advance of the state of the art, as other researchers can combine their techniques with ours with little effort.
When faced with learning a set of inter-related tasks from a limited amount of usable data, learning each task independently may lead to poor generalization performance. Multi-Task Learning (MTL) exploits the latent relations between tasks and overcomes data scarcity limitations by co-learning all these tasks simultaneously to offer improved performance. We propose a novel Multi-Task Multiple Kernel Learning framework based on Support Vector Machines for binary classification tasks. By considering pair-wise task affinity in terms of similarity between a pair's respective feature spaces, the new framework, compared to other similar MTL approaches, offers a high degree of flexibility in determining how similar feature spaces should be, as well as which pairs of tasks should share a common feature space in order to benefit overall performance. The associated optimization problem is solved via a block coordinate descent, which employs a consensus-form Alternating Direction Method of Multipliers algorithm to optimize the Multiple Kernel Learning weights and, hence, to determine task affinities. Empirical evaluation on seven data sets exhibits a statistically significant improvement of our framework's results compared to the ones of several other Clustered Multi-Task Learning methods.
We present a method for extracting depth information from a rectified image pair. Our approach focuses on the first stage of many stereo algorithms: the matching cost computation. We approach the problem by learning a similarity measure on small image patches using a convolutional neural network. Training is carried out in a supervised manner by constructing a binary classification data set with examples of similar and dissimilar pairs of patches. We examine two network architectures for this task: one tuned for speed, the other for accuracy. The output of the convolutional neural network is used to initialize the stereo matching cost. A series of post-processing steps follow: cross-based cost aggregation, semiglobal matching, a left-right consistency check, subpixel enhancement, a median filter, and a bilateral filter. We evaluate our method on the KITTI 2012, KITTI 2015, and Middlebury stereo data sets and show that it outperforms other approaches on all three data sets.
Ensemble of regression trees have become popular statistical tools for the estimation of conditional mean given a set of predictors. However, quantile regression trees and their ensembles have not yet garnered much attention despite the increasing popularity of the linear quantile regression model. This work proposes a Bayesian quantile additive regression trees model that shows very good predictive performance illustrated using simulation studies and real data applications. Further extension to tackle binary classification problems is also considered.
Current state-of-the-art human activity recognition is focused on the classification of temporally trimmed videos in which only one action occurs per frame. We propose a simple, yet effective, method for the temporal detection of activities in temporally untrimmed videos with the help of untrimmed classification. Firstly, our model predicts the top k labels for each untrimmed video by analysing global video-level features. Secondly, frame-level binary classification is combined with dynamic programming to generate the temporally trimmed activity proposals. Finally, each proposal is assigned a label based on the global label, and scored with the score of the temporal activity proposal and the global score. Ultimately, we show that untrimmed video classification models can be used as stepping stone for temporal detection.
We introduce several techniques for sampling and visualizing the latent spaces of generative models. Replacing linear interpolation with spherical linear interpolation prevents diverging from a model's prior distribution and produces sharper samples. J-Diagrams and MINE grids are introduced as visualizations of manifolds created by analogies and nearest neighbors. We demonstrate two new techniques for deriving attribute vectors: bias-corrected vectors with data replication and synthetic vectors with data augmentation. Binary classification using attribute vectors is presented as a technique supporting quantitative analysis of the latent space. Most techniques are intended to be independent of model type and examples are shown on both Variational Autoencoders and Generative Adversarial Networks.
We introduce SalGAN, a deep convolutional neural network for visual saliency prediction trained with adversarial examples. The first stage of the network consists of a generator model whose weights are learned by back-propagation computed from a binary cross entropy (BCE) loss over downsampled versions of the saliency maps. The resulting prediction is processed by a discriminator network trained to solve a binary classification task between the saliency maps generated by the generative stage and the ground truth ones. Our experiments show how adversarial training allows reaching state-of-the-art performance across different metrics when combined with a widely-used loss function like BCE. Our results can be reproduced with the source code and trained models available at https://imatge-upc.github.io/saliency-salgan-2017/.
The all-relevant problem of feature selection is the identification of all strongly and weakly relevant attributes. This problem is especially hard to solve for time series classification and regression in industrial applications such as predictive maintenance or production line optimization, for which each label or regression target is associated with several time series and meta-information simultaneously. Here, we are proposing an efficient, scalable feature extraction algorithm for time series, which filters the available features in an early stage of the machine learning pipeline with respect to their significance for the classification or regression task, while controlling the expected percentage of selected but irrelevant features. The proposed algorithm combines established feature extraction methods with a feature importance filter. It has a low computational complexity, allows to start on a problem with only limited domain knowledge available, can be trivially parallelized, is highly scalable and based on well studied non-parametric hypothesis tests. We benchmark our proposed algorithm on all binary classification problems of the UCR time series classification archive as well as time series from a production line optimization project and simulated stochastic processes with underlying qualitative change of dynamics.
Nonlinear kernel regression models are often used in statistics and machine learning because they are more accurate than linear models. Variable selection for kernel regression models is a challenge partly because, unlike the linear regression setting, there is no clear concept of an effect size for regression coefficients. In this paper, we propose a novel framework that provides an effect size analog of each explanatory variable for Bayesian kernel regression models when the kernel is shift-invariant --- for example, the Gaussian kernel. We use function analytic properties of shift-invariant reproducing kernel Hilbert spaces (RKHS) to define a linear vector space that: (i) captures nonlinear structure, and (ii) can be projected onto the original explanatory variables. The projection onto the original explanatory variables serves as an analog of effect sizes. The specific function analytic property we use is that shift-invariant kernel functions can be approximated via random Fourier bases. Based on the random Fourier expansion we propose a computationally efficient class of Bayesian approximate kernel regression (BAKR) models for both nonlinear regression and binary classification for which one can compute an analog of effect sizes. We illustrate the utility of BAKR by examining two important problems in statistical genetics: genomic selection (i.e. phenotypic prediction) and association mapping (i.e. inference of significant variants or loci). State-of-the-art methods for genomic selection and association mapping are based on kernel regression and linear models, respectively. BAKR is the first method that is competitive in both settings.
Noisy PN learning is the problem of binary classification when training examples may be mislabeled (flipped) uniformly with noise rate rho1 for positive examples and rho0 for negative examples. We propose Rank Pruning (RP) to solve noisy PN learning and the open problem of estimating the noise rates, i.e. the fraction of wrong positive and negative labels. Unlike prior solutions, RP is time-efficient and general, requiring O(T) for any unrestricted choice of probabilistic classifier with T fitting time. We prove RP has consistent noise estimation and equivalent expected risk as learning with uncorrupted labels in ideal conditions, and derive closed-form solutions when conditions are non-ideal. RP achieves state-of-the-art noise estimation and F1, error, and AUC-PR for both MNIST and CIFAR datasets, regardless of the amount of noise and performs similarly impressively when a large portion of training examples are noise drawn from a third distribution. To highlight, RP with a CNN classifier can predict if an MNIST digit is a "one"or "not" with only 0.25% error, and 0.46 error across all digits, even when 50% of positive examples are mislabeled and 50% of observed positive labels are mislabeled negative examples.
Recent advances in computer vision-in the form of deep neural networks-have made it possible to query increasing volumes of video data with high accuracy. However, neural network inference is computationally expensive at scale: applying a state-of-the-art object detector in real time (i.e., 30+ frames per second) to a single video requires a $4000 GPU. In response, we present NoScope, a system for querying videos that can reduce the cost of neural network video analysis by up to three orders of magnitude via inference-optimized model search. Given a target video, object to detect, and reference neural network, NoScope automatically searches for and trains a sequence, or cascade, of models that preserves the accuracy of the reference network but is specialized to the target video and are therefore far less computationally expensive. NoScope cascades two types of models: specialized models that forego the full generality of the reference model but faithfully mimic its behavior for the target video and object; and difference detectors that highlight temporal differences across frames. We show that the optimal cascade architecture differs across videos and objects, so NoScope uses an efficient cost-based optimizer to search across models and cascades. With this approach, NoScope achieves two to three order of magnitude speed-ups (265-15,500x real-time) on binary classification tasks over fixed-angle webcam and surveillance video while maintaining accuracy within 1-5% of state-of-the-art neural networks.
We address the problem of multi-class classification in the case where the number of classes is very large. We propose a double sampling strategy on top of a multi-class to binary reduction strategy, which transforms the original multi-class problem into a binary classification problem over pairs of examples. The aim of the sampling strategy is to overcome the curse of long-tailed class distributions exhibited in majority of large-scale multi-class classification problems and to reduce the number of pairs of examples in the expanded data. We show that this strategy does not alter the consistency of the empirical risk minimization principle defined over the double sample reduction. Experiments are carried out on DMOZ and Wikipedia collections with 10,000 to 100,000 classes where we show the efficiency of the proposed approach in terms of training and prediction time, memory consumption, and predictive performance with respect to state-of-the-art approaches.
We consider neural network training, in applications in which there are many possible classes, but at test-time, the task is a binary classification task of determining whether the given example belongs to a specific class, where the class of interest can be different each time the classifier is applied. For instance, this is the case for real-time image search. We define the Single Logit Classification (SLC) task: training the network so that at test-time, it would be possible to accurately identify whether the example belongs to a given class in a computationally efficient manner, based only on the output logit for this class. We propose a natural principle, the Principle of Logit Separation, as a guideline for choosing and designing losses suitable for the SLC. We show that the cross-entropy loss function is not aligned with the Principle of Logit Separation. In contrast, there are known loss functions, as well as novel batch loss functions that we propose, which are aligned with this principle. In total, we study seven loss functions. Our experiments show that indeed in almost all cases, losses that are aligned with the Principle of Logit Separation obtain at least 20% relative accuracy improvement in the SLC task compared to losses that are not aligned with it, and sometimes considerably more. Furthermore, we show that fast SLC does not cause any drop in binary classification accuracy, compared to standard classification in which all logits are computed, and yields a speedup which grows with the number of classes. For instance, we demonstrate a 10x speedup when the number of classes is 400,000. Tensorflow code for optimizing the new batch losses is publicly available at https://github.com/cruvadom/Logit Separation.
Background: Statistical mechanics results (Dauphin et al. (2014); Choromanska et al. (2015)) suggest that local minima with high error are exponentially rare in high dimensions. However, to prove low error guarantees for Multilayer Neural Networks (MNNs), previous works so far required either a heavily modified MNN model or training method, strong assumptions on the labels (e.g., "near" linear separability), or an unrealistic hidden layer with $\Omega\left(N\right)$ units. Results: We examine a MNN with one hidden layer of piecewise linear units, a single output, and a quadratic loss. We prove that, with high probability in the limit of $N\rightarrow\infty$ datapoints, the volume of differentiable regions of the empiric loss containing sub-optimal differentiable local minima is exponentially vanishing in comparison with the same volume of global minima, given standard normal input of dimension $d_{0}=\tilde{\Omega}\left(\sqrt{N}\right)$, and a more realistic number of $d_{1}=\tilde{\Omega}\left(N/d_{0}\right)$ hidden units. We demonstrate our results numerically: for example, $0\%$ binary classification training error on CIFAR with only $N/d_{0}\approx 16$ hidden neurons.
We propose a new splitting criterion for a meta-learning approach to multiclass classifier design that adaptively merges the classes into a tree-structured hierarchy of increasingly difficult binary classification problems. The classification tree is constructed from empirical estimates of the Henze-Penrose bounds on the pairwise Bayes misclassification rates that rank the binary subproblems in terms of difficulty of classification. The proposed empirical estimates of the Bayes error rate are computed from the minimal spanning tree (MST) of the samples from each pair of classes. Moreover, a meta-learning technique is presented for quantifying the one-vs-rest Bayes error rate for each individual class from a single MST on the entire dataset. Extensive simulations on benchmark datasets show that the proposed hierarchical method can often be learned much faster than competing methods, while achieving competitive accuracy.
The large amount of data available in social media, forums and websites motivates researches in several areas of Natural Language Processing, such as sentiment analysis. The popularity of the area due to its subjective and semantic characteristics motivates research on novel methods and approaches for classification. Hence, there is a high demand for datasets on different domains and different languages. This paper introduces TweetSentBR, a sentiment corpora for Brazilian Portuguese manually annotated with 15.000 sentences on TV show domain. The sentences were labeled in three classes (positive, neutral and negative) by seven annotators, following literature guidelines for ensuring reliability on the annotation. We also ran baseline experiments on polarity classification using three machine learning methods, reaching 80.99% on F-Measure and 82.06% on accuracy in binary classification, and 59.85% F-Measure and 64.62% on accuracy on three point classification.
We introduce a new family of MCMC samplers that combine auxiliary variables, Gibbs sampling and Taylor expansions of the target density. Our approach permits the marginalisation over the auxiliary variables yielding marginal samplers, or the augmentation of the auxiliary variables, yielding auxiliary samplers. The well-known Metropolis-adjusted Langevin algorithm (MALA) and preconditioned Crank-Nicolson Langevin (pCNL) algorithm are shown to be special cases. We prove that marginal samplers are superior in terms of asymptotic variance and demonstrate cases where they are slower in computing time compared to auxiliary samplers. In the context of latent Gaussian models we propose new auxiliary and marginal samplers whose implementation requires a single tuning parameter, which can be found automatically during the transient phase. Extensive experimentation shows that the increase in efficiency (measured as effective sample size per unit of computing time) relative to (optimised implementations of) pCNL, elliptical slice sampling and MALA ranges from 10-fold in binary classification problems to 25-fold in log-Gaussian Cox processes to 100-fold in Gaussian process regression, and it is on par with Riemann manifold Hamiltonian Monte Carlo in an example where the latter has the same complexity as the aforementioned algorithms. We explain this remarkable improvement in terms of the way alternative samplers try to approximate the eigenvalues of the target. We introduce a novel MCMC sampling scheme for hyperparameter learning that builds upon the auxiliary samplers. The MATLAB code for reproducing the experiments in the article is publicly available and a Supplement to this article contains additional experiments and implementation details.
ATPboost is a system for solving sets of large-theory problems by interleaving ATP runs with state-of-the-art machine learning of premise selection from the proofs. Unlike many previous approaches that use multi-label setting, the learning is implemented as binary classification that estimates the pairwise-relevance of (theorem, premise) pairs. ATPboost uses for this the XGBoost gradient boosting algorithm, which is fast and has state-of-the-art performance on many tasks. Learning in the binary setting however requires negative examples, which is nontrivial due to many alternative proofs. We discuss and implement several solutions in the context of the ATP/ML feedback loop, and show that ATPboost with such methods significantly outperforms the k-nearest neighbors multilabel classifier.
Can we learn a binary classifier from only positive data, without any negative data or unlabeled data? We show that if one can equip positive data with confidence (positive-confidence), one can successfully learn a binary classifier, which we name positive-confidence (Pconf) classification. Our work is related to one-class classification which is aimed at "describing" the positive class by clustering-related methods, but one-class classification does not have the ability to tune hyper-parameters and their aim is not on "discriminating" positive and negative classes. For the Pconf classification problem, we provide a simple empirical risk minimization framework that is model-independent and optimization-independent. We theoretically establish the consistency and an estimation error bound, and demonstrate the usefulness of the proposed method for training deep neural networks through experiments.
Recent work has extended the theoretical analysis of boosting algorithms to multiclass problems and to online settings. However, the multiclass extension is in the batch setting and the online extensions only consider binary classification. We fill this gap in the literature by defining, and justifying, a weak learning condition for online multiclass boosting. This condition leads to an optimal boosting algorithm that requires the minimal number of weak learners to achieve a certain accuracy. Additionally, we propose an adaptive algorithm which is near optimal and enjoys an excellent performance on real data due to its adaptive property.