In this paper, we propose our enhanced approach to create a dedicated corpus for Algerian Arabic newspapers comments. The developed approach has to enhance an existing approach by the enrichment of the available corpus and the inclusion of the annotation step by following the Model Annotate Train Test Evaluate Revise (MATTER) approach. A corpus is created by collecting comments from web sites of three well know Algerian newspapers. Three classifiers, support vector machines, na{\"i}ve Bayes, and k-nearest neighbors, were used for classification of comments into positive and negative classes. To identify the influence of the stemming in the obtained results, the classification was tested with and without stemming. Obtained results show that stemming does not enhance considerably the classification due to the nature of Algerian comments tied to Algerian Arabic Dialect. The promising results constitute a motivation for us to improve our approach especially in dealing with non Arabic sentences, especially Dialectal and French ones.
Graph convolutional networks (GCNs) are a powerful architecture for representation learning on documents that naturally occur as graphs, e.g., citation or social networks. However, sensitive personal information, such as documents with people's profiles or relationships as edges, are prone to privacy leaks, as the trained model might reveal the original input. Although differential privacy (DP) offers a well-founded privacy-preserving framework, GCNs pose theoretical and practical challenges due to their training specifics. We address these challenges by adapting differentially-private gradient-based training to GCNs and conduct experiments using two optimizers on five NLP datasets in two languages. We propose a simple yet efficient method based on random graph splits that not only improves the baseline privacy bounds by a factor of 2.7 while retaining competitive F1 scores, but also provides strong privacy guarantees of epsilon = 1.0. We show that, under certain modeling choices, privacy-preserving GCNs perform up to 90% of their non-private variants, while formally guaranteeing strong privacy measures.
Based on a comprehensive study of 20 established data sets, we recommend training set sizes for any classification data set. We obtain our recommendations by systematically withholding training data and developing models through five different classification methods for each resulting training set. Based on these results, we construct accuracy confidence intervals for each training set size and fit the lower bounds to inverse power low learning curves. We also estimate a sufficient training set size (STSS) for each data set based on established convergence criteria. We compare STSS to the data sets' characteristics; based on identified trends, we recommend training set sizes between 3000 and 30000 data points, according to a data set's number of classes and number of features. Because obtaining and preparing training data has non-negligible costs that are proportional to data set size, these results afford the potential opportunity for substantial savings for predictive modeling efforts.
Quantum classification and hypothesis testing are two tightly related subjects, the main difference being that the former is data driven: how to assign to quantum states $\rho(x)$ the corresponding class $c$ (or hypothesis) is learnt from examples during training, where $x$ can be either tunable experimental parameters or classical data "embedded" into quantum states. Does the model generalize? This is the main question in any data-driven strategy, namely the ability to predict the correct class even of previously unseen states. Here we establish a link between quantum machine learning classification and quantum hypothesis testing (state and channel discrimination) and then show that the accuracy and generalization capability of quantum classifiers depend on the (R\'enyi) mutual informations $I(C{:}Q)$ and $I_2(X{:}Q)$ between the quantum state space $Q$ and the classical parameter space $X$ or class space $C$. Based on the above characterization, we then show how different properties of $Q$ affect classification accuracy and generalization, such as the dimension of the Hilbert space, the amount of noise, and the amount of neglected information from $X$ via, e.g., pooling layers. Moreover, we introduce a quantum version of the Information Bottleneck principle that allows us to explore the various tradeoffs between accuracy and generalization. Finally, in order to check our theoretical predictions, we study the classification of the quantum phases of an Ising spin chain, and we propose the Variational Quantum Information Bottleneck (VQIB) method to optimize quantum embeddings of classical data to favor generalization.
Text classifiers are at the core of many NLP applications and use a variety of algorithmic approaches and software. This paper introduces infrastructure and methodologies for text classifiers based on large-scale regular expressions. In particular, we describe how Facebook determines if a given piece of text - anything from a hashtag to a post - belongs to a narrow topic such as COVID-19. To fully define a topic and evaluate classifier performance we employ human-guided iterations of keyword discovery, but do not require labeled data. For COVID-19, we build two sets of regular expressions: (1) for 66 languages, with 99% precision and recall >50%, (2) for the 11 most common languages, with precision >90% and recall >90%. Regular expressions enable low-latency queries from multiple platforms. Response to challenges like COVID-19 is fast and so are revisions. Comparisons to a DNN classifier show explainable results, higher precision and recall, and less overfitting. Our learnings can be applied to other narrow-topic classifiers.
The field of Graph Signal Processing (GSP) has proposed tools to generalize harmonic analysis to complex domains represented through graphs. Among these tools are translations, which are required to define many others. Most works propose to define translations using solely the graph structure (i.e. edges). Such a problem is ill-posed in general as a graph conveys information about neighborhood but not about directions. In this paper, we propose to infer translations as edge-constrained operations that make a supervised classification problem invariant using a deep learning framework. As such, our methodology uses both the graph structure and labeled signals to infer translations. We perform experiments with regular 2D images and abstract hyperlink networks to show the effectiveness of the proposed methodology in inferring meaningful translations for signals supported on graphs.
Self-training is a standard approach to semi-supervised learning where the learner's own predictions on unlabeled data are used as supervision during training. In this paper, we reinterpret this label assignment process as an optimal transportation problem between examples and classes, wherein the cost of assigning an example to a class is mediated by the current predictions of the classifier. This formulation facilitates a practical annealing strategy for label assignment and allows for the inclusion of prior knowledge on class proportions via flexible upper bound constraints. The solutions to these assignment problems can be efficiently approximated using Sinkhorn iteration, thus enabling their use in the inner loop of standard stochastic optimization algorithms. We demonstrate the effectiveness of our algorithm on the CIFAR-10, CIFAR-100, and SVHN datasets in comparison with FixMatch, a state-of-the-art self-training algorithm. Our code is available at https://github.com/stanford-futuredata/sinkhorn-label-allocation.
Subsequence-based time series classification algorithms provide accurate and interpretable models, but training these models is extremely computation intensive. The asymptotic time complexity of subsequence-based algorithms remains a higher-order polynomial, because these algorithms are based on exhaustive search for highly discriminative subsequences. Pattern sampling has been proposed as an effective alternative to mitigate the pattern explosion phenomenon. Therefore, we employ pattern sampling to extract discriminative features from discretized time series data. A weighted trie is created based on the discretized time series data to sample highly discriminative patterns. These sampled patterns are used to identify the shapelets which are used to transform the time series classification problem into a feature-based classification problem. Finally, a classification model can be trained using any off-the-shelf algorithm. Creating a pattern sampler requires a small number of patterns to be evaluated compared to an exhaustive search as employed by previous approaches. Compared to previously proposed algorithms, our approach requires considerably less computational and memory resources. Experiments demonstrate how the proposed approach fares in terms of classification accuracy and runtime performance.
Deep neural networks have increasingly been used as an auxiliary tool in healthcare applications, due to their ability to improve performance of several diagnosis tasks. However, these methods are not widely adopted in clinical settings due to the practical limitations in the reliability, generalizability, and interpretability of deep learning based systems. As a result, methods have been developed that impose additional constraints during network training to gain more control as well as improve interpretabilty, facilitating their acceptance in healthcare community. In this work, we investigate the benefit of using Orthogonal Spheres (OS) constraint for classification of COVID-19 cases from chest X-ray images. The OS constraint can be written as a simple orthonormality term which is used in conjunction with the standard cross-entropy loss during classification network training. Previous studies have demonstrated significant benefits in applying such constraints to deep learning models. Our findings corroborate these observations, indicating that the orthonormality loss function effectively produces improved semantic localization via GradCAM visualizations, enhanced classification performance, and reduced model calibration error. Our approach achieves an improvement in accuracy of 1.6% and 4.8% for two- and three-class classification, respectively; similar results are found for models with data augmentation applied. In addition to these findings, our work also presents a new application of the OS regularizer in healthcare, increasing the post-hoc interpretability and performance of deep learning models for COVID-19 classification to facilitate adoption of these methods in clinical settings. We also identify the limitations of our strategy that can be explored for further research in future.
We consider the problem of classifying radar pulses given raw I/Q waveforms in the presence of noise and absence of synchronization. We also consider the problem of classifying multiple superimposed radar pulses. For both, we design deep neural networks (DNNs) that are robust to synchronization, pulse width, and SNR. Our designs yield more than 100x reduction in error-rate over the previous state-of-the-art.
The construction of multiclass classifiers from binary elements is studied in this paper, and performance is quantified by the regret, defined with respect to the Bayes optimal log-loss. We discuss two known methods. The first is one vs. all (OVA), for which we prove that the multiclass regret is upper bounded by the sum of binary regrets of the constituent classifiers. The second is hierarchical classification, based on a binary tree. For this method we prove that the multiclass regret is exactly a weighted sum of constituent binary regrets where the weighing is determined by the tree structure. We also introduce a leverage-hierarchical classification method, which potentially yields smaller log-loss and regret. The advantages of these classification methods are demonstrated by simulation on both synthetic and real-life datasets.
COVID-19 classification using chest Computed Tomography (CT) has been found pragmatically useful by several studies. Due to the lack of annotated samples, these studies recommend transfer learning and explore the choices of pre-trained models and data augmentation. However, it is still unknown if there are better strategies than vanilla transfer learning for more accurate COVID-19 classification with limited CT data. This paper provides an affirmative answer, devising a novel `model' augmentation technique that allows a considerable performance boost to transfer learning for the task. Our method systematically reduces the distributional shift between the source and target domains and considers augmenting deep learning with complementary representation learning techniques. We establish the efficacy of our method with publicly available datasets and models, along with identifying contrasting observations in the previous studies.
Topological deep learning is a formalism that is aimed at introducing topological language to deep learning for the purpose of utilizing the minimal mathematical structures to formalize problems that arise in a generic deep learning problem. This is the first of a sequence of articles with the purpose of introducing and studying this formalism. In this article, we define and study the classification problem in machine learning in a topological setting. Using this topological framework, we show when the classification problem is possible or not possible in the context of neural networks. Finally, we demonstrate how our topological setting immediately illuminates aspects of this problem that are not as readily apparent using traditional tools.
Prior research on self-supervised learning has led to considerable progress on image classification, but often with degraded transfer performance on object detection. The objective of this paper is to advance self-supervised pretrained models specifically for object detection. Based on the inherent difference between classification and detection, we propose a new self-supervised pretext task, called instance localization. Image instances are pasted at various locations and scales onto background images. The pretext task is to predict the instance category given the composited images as well as the foreground bounding boxes. We show that integration of bounding boxes into pretraining promotes better task alignment and architecture alignment for transfer learning. In addition, we propose an augmentation method on the bounding boxes to further enhance the feature alignment. As a result, our model becomes weaker at Imagenet semantic classification but stronger at image patch localization, with an overall stronger pretrained model for object detection. Experimental results demonstrate that our approach yields state-of-the-art transfer learning results for object detection on PASCAL VOC and MSCOCO.
This research identifies a gap in weakly-labelled multivariate time-series classification (TSC), where state-of-the-art TSC models do not per-form well. Weakly labelled time-series are time-series containing noise and significant redundancies. In response to this gap, this paper proposes an approach of exploiting context relevance of subsequences from previous subsequences to improve classification accuracy. To achieve this, state-of-the-art Attention algorithms are experimented in combination with the top CNN models for TSC (FCN and ResNet), in an CNN-LSTM architecture. Attention is a popular strategy for context extraction with exceptional performance in modern sequence-to-sequence tasks. This paper shows how attention algorithms can be used for improved weakly labelledTSC by evaluating models on a multivariate EEG time-series dataset obtained using a commercial Emotiv headsets from participants performing various activities while driving. These time-series are segmented into sub-sequences and labelled to allow supervised TSC.
We experimentally investigate a collection of feature engineering pipelines for use with a CNN for classifying eyes-open or eyes-closed from electroencephalogram (EEG) time-series from the Bonn dataset. Using the Takens' embedding--a geometric representation of time-series--we construct simplicial complexes from EEG data. We then compare $\epsilon$-series of Betti-numbers and $\epsilon$-series of graph spectra (a novel construction)--two topological invariants of the latent geometry from these complexes--to raw time series of the EEG to fill in a gap in the literature for benchmarking. These methods, inspired by Topological Data Analysis, are used for feature engineering to capture local geometry of the time-series. Additionally, we test these feature pipelines' robustness to downsampling and data reduction. This paper seeks to establish clearer expectations for both time-series classification via geometric features, and how CNNs for time-series respond to data of degraded resolution.
Sound Event Detection and Audio Classification tasks are traditionally addressed through time-frequency representations of audio signals such as spectrograms. However, the emergence of deep neural networks as efficient feature extractors has enabled the direct use of audio signals for classification purposes. In this paper, we attempt to recognize musical instruments in polyphonic audio by only feeding their raw waveforms into deep learning models. Various recurrent and convolutional architectures incorporating residual connections are examined and parameterized in order to build end-to-end classi-fiers with low computational cost and only minimal preprocessing. We obtain competitive classification scores and useful instrument-wise insight through the IRMAS test set, utilizing a parallel CNN-BiGRU model with multiple residual connections, while maintaining a significantly reduced number of trainable parameters.
We consider the problem of costly feature classification, where we sequentially select the subset of features to make a balance between the classification error and the feature cost. In this paper, we first cast the task into a MDP problem and use Advantage Actor Critic algorithm to solve it. In order to further improve the agent's performance and make the policy explainable, we employ the Monte Carlo Tree Search to update the policy iteratively. During the procedure, we also consider its performance on the unbalanced dataset and its sensitivity to the missing value. We evaluate our model on multiple datasets and find it outperforms other methods.
In this paper from communication channel coding perspective we are able to present both a theoretical and practical discussion of AI's uncertainty, capacity and evolution for pattern classification based on the classical Rademacher complexity and Shannon entropy. First AI capacity is defined as in communication channels. It is shown qualitatively that the classical Rademacher complexity and Shannon entropy used in communication theory is closely related by their definitions, given a pattern classification problem with a complexity measured by Rademacher complexity. Secondly based on the Shannon mathematical theory on communication coding, we derive several sufficient and necessary conditions for an AI's error rate approaching zero in classifications problems. A 1/2 criteria on Shannon entropy is derived in this paper so that error rate can approach zero or is zero for AI pattern classification problems. Last but not least, we show our analysis and theory by providing examples of AI pattern classifications with error rate approaching zero or being zero.
In pickup and delivery services, transaction classification based on customer provided free text is a challenging problem. It involves the association of a wide variety of customer inputs to a fixed set of categories while adapting to the various customer writing styles. This categorization is important for the business: it helps understand the market needs and trends, and also assist in building a personalized experience for different segments of the customers. Hence, it is vital to capture these category information trends at scale, with high precision and recall. In this paper, we focus on a specific use-case where a single category drives each transaction. We propose a cost-effective transaction classification approach based on semi-supervision and knowledge distillation frameworks. The approach identifies the category of a transaction using free text input given by the customer. We use weak labelling and notice that the performance gains are similar to that of using human-annotated samples. On a large internal dataset and on 20Newsgroup dataset, we see that RoBERTa performs the best for the categorization tasks. Further, using an ALBERT model (it has 33x fewer parameters vis-a-vis parameters of RoBERTa), with RoBERTa as the Teacher, we see a performance similar to that of RoBERTa and better performance over unadapted ALBERT. This framework, with ALBERT as a student and RoBERTa as teacher, is further referred to as R-ALBERT in this paper. The model is in production and is used by business to understand changing trends and take appropriate decisions.