Background and Objective:Currently, the whole world is facing a pandemic disease, novel Coronavirus also known as COVID-19, which spread in more than 200 countries with around 3.3 million active cases and 4.4 lakh deaths approximately. Due to rapid increase in number of cases and limited supply of testing kits, availability of alternative diagnostic method is necessary for containing the spread of COVID-19 cases at an early stage and reducing the death count. For making available an alternative diagnostic method, we proposed a deep neural network based diagnostic method which can be easily integrated with mobile devices for detection of COVID-19 and viral pneumonia using Chest X-rays (CXR) images. Methods:In this study, we have proposed a method named COVIDLite, which is a combination of white balance followed by Contrast Limited Adaptive Histogram Equalization (CLAHE) and depth-wise separable convolutional neural network (DSCNN). In this method, white balance followed by CLAHE is used as an image preprocessing step for enhancing the visibility of CXR images and DSCNN trained using sparse cross entropy is used for image classification with lesser parameters and significantly lighter in size, i.e., 8.4 MB without quantization. Results:The proposed COVIDLite method resulted in improved performance in comparison to vanilla DSCNN with no pre-processing. The proposed method achieved higher accuracy of 99.58% for binary classification, whereas 96.43% for multiclass classification and out-performed various state-of-the-art methods. Conclusion:Our proposed method, COVIDLite achieved exceptional results on various performance metrics. With detailed model interpretations, COVIDLite can assist radiologists in detecting COVID-19 patients from CXR images and can reduce the diagnosis time significantly.
In recent years, driven by the Asian film industry, such as China and India, the global box office has maintained a steady growth trend. Previous studies have rarely used long-term, full-sample film data in analysis, lack of research on actors' social networks. Existing film box office prediction algorithms only use film meta-data, lack of using social network characteristics and the model is less interpretable. I propose a FC-GRU-CNN binary classification model in of box office prediction task, combining five characteristics, including the film meta-data, Sina Weibo text sentiment, actors' social network measurement, all pairs shortest path and actors' art contribution. Exploiting long-term memory ability of GRU layer in long sequences and the mapping ability of CNN layer in retrieving all pairs shortest path matrix features, proposed model is 14% higher in accuracy than the current best C-LSTM model.
We introduce MANTRA, an annotated dataset of 4869 transient and 71207 non-transient object lightcurves built from the Catalina Real Time Transient Survey. We provide public access to this dataset as a plain text file to facilitate standardized quantitative comparison of astronomical transient event recognition algorithms. Some of the classes included in the dataset are: supernovae, cataclysmic variables, active galactic nuclei, high proper motion stars, blazars and flares. As an example of the tasks that can be performed on the dataset we experiment with multiple data pre-processing methods, feature selection techniques and popular machine learning algorithms (Support Vector Machines, Random Forests and Neural Networks). We assess quantitative performance in two classification tasks: binary (transient/non-transient) and eight-class classification. The best performing algorithm in both tasks is the Random Forest Classifier. It achieves an F1-score of 96.25% in the binary classification and 52.79% in the eight-class classification. For the eight-class classification, non-transients ( 96.83% ) is the class with the highest F1-score, while the lowest corresponds to high-proper-motion stars ( 16.79% ); for supernovae it achieves a value of 54.57% , close to the average across classes. The next release of MANTRA includes images and benchmarks with deep learning models.
Many fields use the ROC curve and the PR curve as standard evaluations of binary classification methods. Analysis of ROC and PR, however, often gives misleading and inflated performance evaluations, especially with an imbalanced ground truth. Here, we demonstrate the problems with ROC and PR analysis through simulations, and propose the MCC-F1 curve to address these drawbacks. The MCC-F1 curve combines two informative single-threshold metrics, MCC and the F1 score. The MCC-F1 curve more clearly differentiates good and bad classifiers, even with imbalanced ground truths. We also introduce the MCC-F1 metric, which provides a single value that integrates many aspects of classifier performance across the whole range of classification thresholds. Finally, we provide an R package that plots MCC-F1 curves and calculates related metrics.
In this paper, we propose a novel method for irregularity detection. Previous researches solve this problem as a One-Class Classification (OCC) task where they train a reference model on all of the available samples. Then, they consider a test sample as an anomaly if it has a diversion from the reference model. Generative Adversarial Networks (GANs) have achieved the most promising results for OCC while implementing and training such networks, especially for the OCC task, is a cumbersome and computationally expensive procedure. To cope with the mentioned challenges, we present a simple but effective method to solve the irregularity detection as a binary classification task in order to make the implementation easier along with improving the detection performance. We learn two deep neural networks (generator and discriminator) in a GAN-style setting on merely the normal samples. During training, the generator gradually becomes an expert to generate samples which are similar to the normal ones. In the training phase, when the generator fails to produce normal data (in the early stages of learning and also prior to the complete convergence), it can be considered as an irregularity generator. In this way, we simultaneously generate the irregular samples. Afterward, we train a binary classifier on the generated anomalous samples along with the normal instances in order to be capable of detecting irregularities. The proposed framework applies to different related applications of outlier and anomaly detection in images and videos, respectively. The results confirm that our proposed method is superior to the baseline and state-of-the-art solutions.
Accuracy at the top is a special class of binary classification problems where the performance is evaluated only on a small number of relevant (top) samples. Applications include information retrieval systems or processes with manual (expensive) postprocessing. This leads to minimizing the number of irrelevant samples above a threshold. We consider classifiers in the form of an arbitrary (deep) network and propose a new method DeepTopPush for minimizing the loss function at the top. Since the threshold depends on all samples, the problem is non-decomposable. We modify the stochastic gradient descent to handle the non-decomposability in an end-to-end training manner and propose a way to estimate the threshold only from values on the current minibatch and one delayed value. We demonstrate the excellent performance of DeepTopPush on visual recognition datasets and two real-world applications. The first one selects a small number of molecules for further drug testing. The second one uses real malware data, where we detected 46\% malware at an extremely low false alarm rate of $10^{-5}$.
The traditional approach to face anti-spoofing sees it as a binary classification problem, and binary classifiers are trained and validated on specialized anti-spoofing databases. One of the drawbacks of this approach is that, due to the variability of face spoofing attacks, environmental factors, and the typically small sample size, such classifiers do not generalize well to previously unseen databases. Anomaly detection, which approaches face anti-spoofing as a one-class classification problem, is emerging as an increasingly popular alternative approach. Nevertheless, in all existing work on anomaly detection for face anti-spoofing, the proposed training protocols utilize images from specialized anti-spoofing databases only, even though only common images of real faces are needed. Here, we explore the use of in-the-wild images, and images from non-specialized face databases, to train one-class classifiers for face anti-spoofing. Employing a well-established technique, we train a convolutional autoencoder on real faces and compare the reconstruction error of the input against a threshold to classify a face image accordingly as either client or imposter. Our results show that the inclusion in the training set of in-the-wild images increases the discriminating power of the classifier significantly on an unseen database, as evidenced by a large increase in the value of the Area Under the Curve. In a limitation of our approach, we note that the problem of finding a suitable operating point on the unseen database remains a challenge, as evidenced by the values of the Half Total Error Rate.
We study three notions of uncertainty quantification -- calibration, confidence intervals and prediction sets -- for binary classification in the distribution-free setting, that is without making any distributional assumptions on the data. With a focus towards calibration, we establish a 'tripod' of theorems that connect these three notions for score-based classifiers. A direct implication is that distribution-free calibration is only possible, even asymptotically, using a scoring function whose level sets partition the feature space into at most countably many sets. Parametric calibration schemes such as variants of Platt scaling do not satisfy this requirement, while nonparametric schemes based on binning do. To close the loop, we derive distribution-free confidence intervals for binned probabilities for both fixed-width and uniform-mass binning. As a consequence of our 'tripod' theorems, these confidence intervals for binned probabilities lead to distribution-free calibration. We also derive extensions to settings with streaming data and covariate shift.
We investigate how the training curve of isotropic kernel methods depends on the symmetry of the task to be learned, in several settings. (i) We consider a regression task, where the target function is a Gaussian random field that depends only on $d_\parallel$ variables, fewer than the input dimension $d$. We compute the expected test error $\epsilon$ that follows $\epsilon\sim p^{-\beta}$ where $p$ is the size of the training set. We find that $\beta\sim 1/d$ independently of $d_\parallel$, supporting previous findings that the presence of invariants does not resolve the curse of dimensionality for kernel regression. (ii) Next we consider support-vector binary classification and introduce the stripe model where the data label depends on a single coordinate $y(\underline{x}) = y(x_1)$, corresponding to parallel decision boundaries separating labels of different signs, and consider that there is no margin at these interfaces. We argue and confirm numerically that for large bandwidth, $\beta = \frac{d-1+\xi}{3d-3+\xi}$, where $\xi\in (0,2)$ is the exponent characterizing the singularity of the kernel at the origin. This estimation improves classical bounds obtainable from Rademacher complexity. In this setting there is no curse of dimensionality since $\beta\rightarrow 1 / 3$ as $d\rightarrow\infty$. (iii) We confirm these findings for the spherical model for which $y(\underline{x}) = y(|\underline{x}|)$. (iv) In the stripe model, we show that if the data are compressed along their invariants by some factor $\lambda$ (an operation believed to take place in deep networks), the test error is reduced by a factor $\lambda^{-\frac{2(d-1)}{3d-3+\xi}}$.
Given a convex and differentiable objective $Q(\M)$ for a real symmetric matrix $\M$ in the positive definite (PD) cone -- used to compute Mahalanobis distances -- we propose a fast general metric learning framework that is entirely projection-free. We first assume that $\M$ resides in a space $\cS$ of generalized graph Laplacian matrices corresponding to balanced signed graphs. $\M \in \cS$ that is also PD is called a graph metric matrix. Unlike low-rank metric matrices common in the literature, $\cS$ includes the important diagonal-only matrices as a special case. The key theorem to circumvent full eigen-decomposition and enable fast metric matrix optimization is Gershgorin disc perfect alignment (GDPA): given $\M \in \cS$ and diagonal matrix $\S$, where $S_{ii} = 1/v_i$ and $\v$ is $\M$'s first eigenvector, we prove that Gershgorin disc left-ends of similarity transform $\B = \S \M \S^{-1}$ are perfectly aligned at the smallest eigenvalue $\lambda_{\min}$. Using this theorem, we replace the PD cone constraint in the metric learning problem with tightest possible linear constraints per iteration, so that the alternating optimization of the diagonal / off-diagonal terms in $\M$ can be solved efficiently as linear programs via the Frank-Wolfe method. We update $\v$ using Locally Optimal Block Preconditioned Conjugate Gradient (LOBPCG) with warm start as entries in $\M$ are optimized successively. Experiments show that our graph metric optimization is significantly faster than cone-projection schemes, and produces competitive binary classification performance.
In this paper, we approach Vietnamese word segmentation as a binary classification by using the Support Vector Machine classifier. We inherit features from prior works such as n-gram of syllables, n-gram of syllable types, and checking conjunction of adjacent syllables in the dictionary. We propose two novel ways to feature extraction, one to reduce the overlap ambiguity and the other to increase the ability to predict unknown words containing suffixes. Different from UETsegmenter and RDRsegmenter, two state-of-the-art Vietnamese word segmentation methods, we do not employ the longest matching algorithm as an initial processing step or any post-processing technique. According to experimental results on benchmark Vietnamese datasets, our proposed method obtained a better F1-score than the prior state-of-the-art methods UETsegmenter, and RDRsegmenter.
Binary classification is widely used in ML production systems. Monitoring classifiers in a constrained event space is well known. However, real world production systems often lack the ground truth these methods require. Privacy concerns may also require that the ground truth needed to evaluate the classifiers cannot be made available. In these autonomous settings, non-parametric estimators of performance are an attractive solution. They do not require theoretical models about how the classifiers made errors in any given sample. They just estimate how many errors there are in a sample of an industrial or robotic datastream. We construct one such non-parametric estimator of the sample errors for an ensemble of weak binary classifiers. Our approach uses algebraic geometry to reformulate the self-assessment problem for ensembles of binary classifiers as an exact polynomial system. The polynomial formulation can then be used to prove - as an algebraic geometry algorithm - that no general solution to the self-assessment problem is possible. However, specific solutions are possible in settings where the engineering context puts the classifiers close to independent errors. The practical utility of the method is illustrated on a real-world dataset from an online advertising campaign and a sample of common classification benchmarks. The accuracy estimators in the experiments where we have ground truth are better than one part in a hundred. The online advertising campaign data, where we do not have ground truth data, is verified by an internal consistency approach whose validity we conjecture as an algebraic geometry theorem. We call this approach - algebraic ground truth inference.
Adaptive gradient methods are typically used for training over-parameterized models. To better understand their behaviour, we study a simplistic setting -- smooth, convex losses with models over-parameterized enough to interpolate the data. In this setting, we prove that AMSGrad with constant step-size and momentum converges to the minimizer at a faster $O(1/T)$ rate. When interpolation is only approximately satisfied, constant step-size AMSGrad converges to a neighbourhood of the solution at the same rate, while AdaGrad is robust to the violation of interpolation. However, even for simple convex problems satisfying interpolation, the empirical performance of both methods heavily depends on the step-size and requires tuning, questioning their adaptivity. We alleviate this problem by automatically determining the step-size using stochastic line-search or Polyak step-sizes. With these techniques, we prove that both AdaGrad and AMSGrad retain their convergence guarantees, without needing to know problem-dependent constants. Empirically, we demonstrate that these techniques improve the convergence and generalization of adaptive gradient methods across tasks, from binary classification with kernel mappings to multi-class classification with deep networks.
Automated machine learning (AutoML) and deep learning (DL) are two cutting-edge paradigms used to solve a myriad of inductive learning tasks. In spite of their successes, little guidance exists for when to choose one approach over the other in the context of specific real-world problems. Furthermore, relatively few tools exist that allow the integration of both AutoML and DL in the same analysis to yield results combining both of their strengths. Here, we seek to address both of these issues, by (1.) providing a head-to-head comparison of AutoML and DL in the context of binary classification on 6 well-characterized public datasets, and (2.) evaluating a new tool for genetic programming-based AutoML that incorporates deep estimators. Our observations suggest that AutoML outperforms simple DL classifiers when trained on similar datasets for binary classification but integrating DL into AutoML improves classification performance even further. However, the substantial time needed to train AutoML+DL pipelines will likely outweigh performance advantages in many applications.
In classical statistical learning theory, one of the most well studied problems is that of binary classification. The information-theoretic sample complexity of this task is tightly characterized by the Vapnik-Chervonenkis (VC) dimension. A quantum analog of this task, with training data given as a quantum state has also been intensely studied and is now known to have the same sample complexity as its classical counterpart. We propose a novel quantum version of the classical binary classification task by considering maps with classical input and quantum output and corresponding classical-quantum training data. We discuss learning strategies for the agnostic and for the realizable case and study their performance to obtain sample complexity upper bounds. Moreover, we provide sample complexity lower bounds which show that our upper bounds are essentially tight for pure output states. In particular, we see that the sample complexity is the same as in the classical binary classification task w.r.t. its dependence on accuracy, confidence and the VC-dimension.
Similarity learning is a general problem to elicit useful representations by predicting the relationship between a pair of patterns. This problem is related to various important preprocessing tasks such as metric learning, kernel learning, and contrastive learning. A classifier built upon the representations is expected to perform well in downstream classification; however, little theory has been given in literature so far and thereby the relationship between similarity and classification has remained elusive. Therefore, we tackle a fundamental question: can similarity information provably leads a model to perform well in downstream classification? In this paper, we reveal that a product-type formulation of similarity learning is strongly related to an objective of binary classification. We further show that these two different problems are explicitly connected by an excess risk bound. Consequently, our results elucidate that similarity learning is capable of solving binary classification by directly eliciting a decision boundary.
Recently adversarial attacks on automatic speaker verification (ASV) systems attracted widespread attention as they pose severe threats to ASV systems. However, methods to defend against such attacks are limited. Existing approaches mainly focus on retraining ASV systems with adversarial data augmentation. Also, countermeasure robustness against different attack settings are insufficiently investigated. Orthogonal to prior approaches, this work proposes to defend ASV systems against adversarial attacks with a separate detection network, rather than augmenting adversarial data into ASV training. A VGG-like binary classification detector is introduced and demonstrated to be effective on detecting adversarial samples. To investigate detector robustness in a realistic defense scenario where unseen attack settings may exist, we analyze various kinds of unseen attack settings' impact and observe that the detector is robust (6.27\% EER_{det} degradation in the worst case) against unseen substitute ASV systems, but it has weak robustness (50.37\% EER_{det} degradation in the worst case) against unseen perturbation methods. The weak robustness against unseen perturbation methods shows a direction for developing stronger countermeasures.
Achieving transparency in black-box deep learning algorithms is still an open challenge. High dimensional features and decisions given by deep neural networks (NN) require new algorithms and methods to expose its mechanisms. Current state-of-the-art NN interpretation methods (e.g. Saliency maps, DeepLIFT, LIME, etc.) focus more on the direct relationship between NN outputs and inputs rather than the NN structure and operations itself. In current deep NN operations, there is uncertainty over the exact role played by neurons with fixed activation functions. In this paper, we achieve partially explainable learning model by symbolically explaining the role of activation functions (AF) under a scalable topology. This is carried out by modeling the AFs as adaptive Gaussian Processes (GP), which sit within a novel scalable NN topology, based on the Kolmogorov-Arnold Superposition Theorem (KST). In this scalable NN architecture, the AFs are generated by GP interpolation between control points and can thus be tuned during the back-propagation procedure via gradient descent. The control points act as the core enabler to both local and global adjustability of AF, where the GP interpolation constrains the intrinsic autocorrelation to avoid over-fitting. We show that there exists a trade-off between the NN's expressive power and interpretation complexity, under linear KST topology scaling. To demonstrate this, we perform a case study on a binary classification dataset of banknote authentication. By quantitatively and qualitatively investigating the mapping relationship between inputs and output, our explainable model can provide interpretation over each of the one-dimensional attributes. These early results suggest that our model has the potential to act as the final interpretation layer for deep neural networks.
Adversarial examples have pointed out Deep Neural Networks vulnerability to small local noise. It has been shown that constraining their Lipschitz constant should enhance robustness, but make them harder to learn with classical loss functions. We propose a new framework for binary classification, based on optimal transport, which integrates this Lipschitz constraint as a theoretical requirement. We propose to learn 1-Lipschitz networks using a new loss that is an hinge regularized version of the Kantorovich-Rubinstein dual formulation for the Wasserstein distance estimation. This loss function has a direct interpretation in terms of adversarial robustness together with certifiable robustness bound. We also prove that this hinge regularized version is still the dual formulation of an optimal transportation problem, and has a solution. We also establish several geometrical properties of this optimal solution, and extend the approach to multi-class problems. Experiments show that the proposed approach provides the expected guarantees in terms of robustness without any significant accuracy drop. The adversarial examples, on the proposed models, visibly and meaningfully change the input providing an explanation for the classification.
Deep neural networks have gained momentum based on their accuracy, but their interpretability is often criticised. As a result, they are labelled as black boxes. In response, several methods have been proposed in the literature to explain their predictions. Among the explanatory methods, Shapley values is a feature attribution method favoured for its robust theoretical foundation. However, the analysis of feature attributions using Shapley values requires choosing a baseline that represents the concept of missingness. An arbitrary choice of baseline could negatively impact the explanatory power of the method and possibly lead to incorrect interpretations. In this paper, we present a method for choosing a baseline according to a neutrality value: as a parameter selected by decision-makers, the point at which their choices are determined by the model predictions being either above or below it. Hence, the proposed baseline is set based on a parameter that depends on the actual use of the model. This procedure stands in contrast to how other baselines are set, i.e. without accounting for how the model is used. We empirically validate our choice of baseline in the context of binary classification tasks, using two datasets: a synthetic dataset and a dataset derived from the financial domain.