Active learning holds promise of significantly reducing data annotation costs while maintaining reasonable model performance. However, it requires sending data to annotators for labeling. This presents a possible privacy leak when the training set includes sensitive user data. In this paper, we describe an approach for carrying out privacy preserving active learning with quantifiable guarantees. We evaluate our approach by showing the tradeoff between privacy, utility and annotation budget on a binary classification task in a active learning setting.
Quantization, a commonly used technique to reduce the memory footprint of a neural network for edge computing, entails reducing the precision of the floating-point representation used for the parameters of the network. The impact of such rounding-off errors on the overall performance of the neural network is estimated using testing, which is not exhaustive and thus cannot be used to guarantee the safety of the model. We present a framework based on Satisfiability Modulo Theory (SMT) solvers to quantify the robustness of neural networks to parameter perturbation. To this end, we introduce notions of local and global robustness that capture the deviation in the confidence of class assignments due to parameter quantization. The robustness notions are then cast as instances of SMT problems and solved automatically using solvers, such as dReal. We demonstrate our framework on two simple Multi-Layer Perceptrons (MLP) that perform binary classification on a two-dimensional input. In addition to quantifying the robustness, we also show that Rectified Linear Unit activation results in higher robustness than linear activations for our MLPs.
Data augmentation is rapidly gaining attention in machine learning. Synthetic data can be generated by simple transformations or through the data distribution. In the latter case, the main challenge is to estimate the label associated to new synthetic patterns. This paper studies the effect of generating synthetic data by convex combination of patterns and the use of these as unsupervised information in a semi-supervised learning framework with support vector machines, avoiding thus the need to label synthetic examples. We perform experiments on a total of 53 binary classification datasets. Our results show that this type of data over-sampling supports the well-known cluster assumption in semi-supervised learning, showing outstanding results for small high-dimensional datasets and imbalanced learning problems.
The paper studies binary classification and aims at estimating the underlying regression function which is the conditional expectation of the class labels given the inputs. The regression function is the key component of the Bayes optimal classifier, moreover, besides providing optimal predictions, it can also assess the risk of misclassification. We aim at building non-asymptotic confidence regions for the regression function and suggest three kernel-based semi-parametric resampling methods. We prove that all of them guarantee regions with exact coverage probabilities and they are strongly consistent.
Efficient point cloud compression is fundamental to enable the deployment of virtual and mixed reality applications, since the number of points to code can range in the order of millions. In this paper, we present a novel data-driven geometry compression method for static point clouds based on learned convolutional transforms and uniform quantization. We perform joint optimization of both rate and distortion using a trade-off parameter. In addition, we cast the decoding process as a binary classification of the point cloud occupancy map. Our method outperforms the MPEG reference solution in terms of rate-distortion on the Microsoft Voxelized Upper Bodies dataset with 51.5% BDBR savings on average. Moreover, while octree-based methods face exponential diminution of the number of points at low bitrates, our method still produces high resolution outputs even at low bitrates. Code and supplementary material are available at https://github.com/mauriceqch/pcc_geo_cnn .
We present a set of probabilistic models applied to binary classification as defined in the DEFT'05 challenge. The challenge consisted a mixture of two differents problems in Natural Language Processing : identification of author (a sequence of Fran\c{c}ois Mitterrand's sentences might have been inserted into a speech of Jacques Chirac) and thematic break detection (the subjects addressed by the two authors are supposed to be different). Markov chains, Bayes models and an adaptative process have been used to identify the paternity of these sequences. A probabilistic model of the internal coherence of speeches which has been employed to identify thematic breaks. Adding this model has shown to improve the quality results. A comparison with different approaches demostrates the superiority of a strategy that combines learning, coherence and adaptation. Applied to the DEFT'05 data test the results in terms of precision (0.890), recall (0.955) and Fscore (0.925) measure are very promising.
With the globalization of the semiconductor manufacturing process, electronic devices are powerless against malicious modification of hardware in the supply chain. The ever-increasing threat of hardware Trojan attacks against integrated circuits has spurred a need for accurate and efficient detection methods. Ring oscillator network (RON) is used to detect the Trojan by capturing the difference in power consumption; the power consumption of a Trojan-free circuit is different from the Trojan-inserted circuit. However, the process variation and measurement noise are the major obstacles to detect hardware Trojan with high accuracy. In this paper, we quantitatively compare four supervised machine learning algorithms and classifier optimization strategies for maximizing accuracy and minimizing the false positive rate (FPR). These supervised learning techniques show an improved false positive rate compared to principal component analysis (PCA) and convex hull classification by nearly 40% while maintaining > 90\% binary classification accuracy.
Multiple kernel learning (MKL) algorithms combine different base kernels to obtain a more efficient representation in the feature space. Focusing on discriminative tasks, MKL has been used successfully for feature selection and finding the significant modalities of the data. In such applications, each base kernel represents one dimension of the data or is derived from one specific descriptor. Therefore, MKL finds an optimal weighting scheme for the given kernels to increase the classification accuracy. Nevertheless, the majority of the works in this area focus on only binary classification problems or aim for linear separation of the classes in the kernel space, which are not realistic assumptions for many real-world problems. In this paper, we propose a novel multi-class MKL framework which improves the state-of-the-art by enhancing the local separation of the classes in the feature space. Besides, by using a sparsity term, our large-margin multiple kernel algorithm (LMMK) performs discriminative feature selection by aiming to employ a small subset of the base kernels. Based on our empirical evaluations on different real-world datasets, LMMK provides a competitive classification accuracy compared with the state-of-the-art algorithms in MKL. Additionally, it learns a sparse set of non-zero kernel weights which leads to a more interpretable feature selection and representation learning.
Largest theoretical contribution to Neural Networks comes from VC Dimension which characterizes the sample complexity of classification model in a probabilistic view and are widely used to study the generalization error. So far in the literature the VC Dimension has only been used to approximate the generalization error bounds on different Neural Network architectures. VC Dimension has not yet been implicitly or explicitly stated to fix the network size which is important as the wrong configuration could lead to high computation effort in training and leads to over fitting. So there is a need to bound these units so that task can be computed with only sufficient number of parameters. For binary classification tasks shallow networks are used as they have universal approximation property and it is enough to size the hidden layer width for such networks. The paper brings out a theoretical justification on required attribute size and its corresponding hidden layer dimension for a given sample set that gives an optimal binary classification results with minimum training complexity in a single layered feed forward network framework. The paper also establishes proof on the existence of bounds on the width of the hidden layer and its range subjected to certain conditions. Findings in this paper are experimentally analyzed on three different dataset using Mathlab 2018 (b) software.
Despite the widespread use of machine learning algorithms to solve problems of technological, economic, and social relevance, provable guarantees on the performance of these data-driven algorithms are critically lacking, especially when the data originates from unreliable sources and is transmitted over unprotected and easily accessible channels. In this paper we take an important step to bridge this gap and formally show that, in a quest to optimize their accuracy, binary classification algorithms -- including those based on machine-learning techniques -- inevitably become more sensitive to adversarial manipulation of the data. Further, for a given class of algorithms with the same complexity (i.e., number of classification boundaries), the fundamental tradeoff curve between accuracy and sensitivity depends solely on the statistics of the data, and cannot be improved by tuning the algorithm.
The annotated medical images are usually expensive to be collected. This paper proposes a deep learning method on small data to classify Common Imaging Signs of Lung diseases (CISL) in computed tomography (CT) images. We explore both the real data and the data generated by Generative Adversarial Network (GAN) to improve the reliability and the generalization of learning. First, we use GAN to generate a large number of CISLs from small annotated data, which are difficult to be distinguished from real counterparts. These generated samples are used to pre-train a Convolutional Neural Network (CNN) for classifying CISLs. Second, we fine-tune the CNN classification model with real data. Experiments were conducted on the LISS database of CISLs. We successfully convinced radiologists that our generated CISLs samples were real for 56.7% of our experiments. The pre-trained CNN model achieves 88.4% of mean accuracy of binary classification, and after fine-tuning, the mean accuracy is significantly increased to 95.0%. For multi-classification of all types of CISLs and normal tissues, through the two stages of training, the mean accuracy, sensitivity and specificity are up to about 91.83%, 92.73% and 99.0%, respectively. To our knowledge, this is the best result achieved on the LISS database, which demonstrates that the proposed method is effective and promising for fulfilling deep learning on small data.
Earthquake magnitude prediction for Hindukush region has been carried out in this research using the temporal sequence of historic seismic activities in combination with the machine learning classifiers. Prediction has been made on the basis of mathematically calculated eight seismic indicators using the earthquake catalog of the region. These parameters are based on the well-known geophysical facts of Gutenberg–Richter’s inverse law, distribution of characteristic earthquake magnitudes and seismic quiescence. In this research, four machine learning techniques including pattern recognition neural network, recurrent neural network, random forest and linear programming boost ensemble classifier are separately applied to model relationships between calculated seismic parameters and future earthquake occurrences. The problem is formulated as a binary classification task and predictions are made for earthquakes of magnitude greater than or equal to 5.5 (\(M \ge\) 5.5), for the duration of 1 month. Furthermore, the analysis of earthquake prediction results is carried out for every machine learning classifier in terms of sensitivity, specificity, true and false predictive values. Accuracy is another performance measure considered for analyzing the results. Earthquake magnitude prediction for the Hindukush using these aforementioned techniques show significant and encouraging results, thus constituting a step forward toward the final robust prediction mechanism which is not available so far.
Many wireless networks, including 5G NR (New Radio) and future beyond 5G cellular systems, are expected to operate on multiple frequency bands. This paper considers the band assignment (BA) problem in dual-band systems, where the basestation (BS) chooses one of the two available frequency bands (centimeter-wave and millimeter-wave bands) to communicate with the user equipment (UE). While the millimeter-wave band might offer higher data rate, there is a significant probability of outage during which the communication should be carried on the (more reliable) centimeter-wave band. With mobility, the BA can be perceived as a sequential problem, where the BS uses previously observed information to predict the best band for a future time step. We formulate the BA as a binary classification problem and propose supervised Machine Learning (ML) solutions. We study the problem when both the BS and the UE use (i) omnidirectional antennas and (ii) both use directional antennas. In the omnidirectional case, we derive analytical benchmark solutions based on the Gaussian Process (GP) assumption for the inter-band shadow fading. In the directional case, where the labeling is shown to be complex, we propose an efficient labeling approach based on the Viterbi Algorithm (VA). We compare the performances for two channel models: (i) a stochastic channel and (ii) a ray-tracing based channel.
As an effective data preprocessing step, feature selection has shown its effectiveness to prepare high-dimensional data for many machine learning tasks. The proliferation of high di-mension and huge volume big data, however, has brought major challenges, e.g. computation complexity and stability on noisy data, upon existing feature-selection techniques. This paper introduces a novel neural network-based feature selection architecture, dubbed Attention-based Feature Selec-tion (AFS). AFS consists of two detachable modules: an at-tention module for feature weight generation and a learning module for the problem modeling. The attention module for-mulates correlation problem among features and supervision target into a binary classification problem, supported by a shallow attention net for each feature. Feature weights are generated based on the distribution of respective feature se-lection patterns adjusted by backpropagation during the train-ing process. The detachable structure allows existing off-the-shelf models to be directly reused, which allows for much less training time, demands for the training data and requirements for expertise. A hybrid initialization method is also intro-duced to boost the selection accuracy for datasets without enough samples for feature weight generation. Experimental results show that AFS achieves the best accuracy and stability in comparison to several state-of-art feature selection algo-rithms upon both MNIST, noisy MNIST and several datasets with small samples.
This paper proposes a data-efficient, semi-supervised, two-pass framework for segmenting bird vocalizations. The framework utilizes a binary classification model to categorize frames of an input audio recording into the background or bird vocalization. The first pass of the framework automatically generates training labels from the input recording itself, while model training and classification is done during the second pass. The proposed framework utilizes a reference directional model for obtaining a feature representation called directional embeddings (DE). This reference directional model acts as an acoustic model for bird vocalizations and is obtained using the mixtures of Von-Mises Fisher distribution (moVMF). The proposed DE space only contains information about bird vocalizations, while no information about the background disturbances is reflected. The framework employs supervised information only for obtaining the reference directional model and avoids the background modeling. Hence, it can be regarded as semi-supervised in nature. The proposed framework is tested on approximately 79000 vocalizations of seven different bird species. The performance of the framework is also analyzed in the presence of noise at different SNRs. Experimental results convey that the proposed framework performs better than the existing bird vocalization segmentation methods.
Positive-Unlabeled (PU) learning is an analog to supervised binary classification for the case when only the positive sample is clean, while the negative sample is contaminated with latent instances of positive class and hence can be considered as an unlabeled mixture. The objectives are to classify the unlabeled sample and train an unbiased PN classifier, which generally requires to identify the mixing proportions of positives and negatives first. Recently, unbiased risk estimation framework has achieved state-of-the-art performance in PU learning. This approach, however, exhibits two major bottlenecks. First, the mixing proportions are assumed to be identified, i.e. known in the domain or estimated with additional methods. Second, the approach relies on the classifier being a neural network. In this paper, we propose DEDPUL, a method that solves PU Learning without the aforementioned issues. The mechanism behind DEDPUL is to apply a computationally cheap post-processing procedure to the predictions of any classifier trained to distinguish positive and unlabeled data. Instead of assuming the proportions to be identified, DEDPUL estimates them alongside with classifying unlabeled sample. Experiments show that DEDPUL outperforms the current state-of-the-art in both proportion estimation and PU Classification.
We present our system, CruzAffect, for the CL-Aff Shared Task 2019. CruzAffect consists of several types of robust and efficient models for affective classification tasks. We utilize both traditional classifiers, such as XGBoosted Forest, as well as a deep learning Convolutional Neural Networks (CNN) classifier. We explore rich feature sets such as syntactic features, emotional features, and profile features, and utilize several sentiment lexicons, to discover essential indicators of social involvement and control that a subject might exercise in their happy moments, as described in textual snippets from the HappyDB database. The data comes with a labeled set (10K), and a larger unlabeled set (70K). We therefore use supervised methods on the 10K dataset, and a bootstrapped semi-supervised approach for the 70K. We evaluate these models for binary classification of agency and social labels (Task 1), as well as multi-class prediction for concepts labels (Task 2). We obtain promising results on the held-out data, suggesting that the proposed feature sets effectively represent the data for affective classification tasks. We also build concepts models that discover general themes recurring in happy moments. Our results indicate that generic characteristics are shared between the classes of agency, social and concepts, suggesting it should be possible to build general models for affective classification tasks.
Where machine-learned predictive risk scores inform high-stakes decisions, such as bail and sentencing in criminal justice, fairness has been a serious concern. Recent work has characterized the disparate impact that such risk scores can have when used for a binary classification task. This may not account, however, for the more diverse downstream uses of risk scores and their non-binary nature. To better account for this, in this paper, we investigate the fairness of predictive risk scores from the point of view of a bipartite ranking task, where one seeks to rank positive examples higher than negative ones. We introduce the xAUC disparity as a metric to assess the disparate impact of risk scores and define it as the difference in the probabilities of ranking a random positive example from one protected group above a negative one from another group and vice versa. We provide a decomposition of bipartite ranking loss into components that involve the discrepancy and components that involve pure predictive ability within each group. We use xAUC analysis to audit predictive risk scores for recidivism prediction, income prediction, and cardiac arrest prediction, where it describes disparities that are not evident from simply comparing within-group predictive performance.
Many post-disaster and -conflict regions do not have sufficient data on their transportation infrastructure assets, hindering both mobility and reconstruction. In particular, as the number of aging and deteriorating bridges increase, it is necessary to quantify their load characteristics in order to inform maintenance and prevent failure. The load carrying capacity and the design load are considered as the main aspects of any civil structures. Human examination can be costly and slow when expertise is lacking in challenging scenarios. In this paper, we propose to employ deep learning as method to estimate the load carrying capacity from crowd sourced images. A new convolutional neural network architecture is trained on data from over 6000 bridges, which will benefit future research and applications. We tackle significant variations in the dataset (e.g. class interval, image completion, image colour) and quantify their impact on the prediction accuracy, precision, recall and F1 score. Finally, practical optimisation is performed by converting multiclass classification into binary classification to achieve a promising field use performance.
We present $\alpha$-loss, $\alpha \in [1,\infty]$, a tunable loss function for binary classification that bridges log-loss ($\alpha=1$) and $0$-$1$ loss ($\alpha = \infty$). We prove that $\alpha$-loss has an equivalent margin-based form and is classification-calibrated, two desirable properties for a good surrogate loss function for the ideal yet intractable $0$-$1$ loss. For logistic regression-based classification, we provide an upper bound on the difference between the empirical and expected risk at the empirical risk minimizers for $\alpha$-loss by exploiting its Lipschitzianity along with recent results on the landscape features of empirical risk functions. Finally, we show that $\alpha$-loss with $\alpha = 2$ performs better than log-loss on MNIST for logistic regression.