Implicit discourse relations bind smaller linguistic units into coherent texts. Automatic sense prediction for implicit relations is hard, because it requires understanding the semantics of the linked arguments. Furthermore, annotated datasets contain relatively few labeled examples, due to the scale of the phenomenon: on average each discourse relation encompasses several dozen words. In this paper, we explore the utility of pre-trained sentence embeddings as base representations in a neural network for implicit discourse relation sense classification. We present a series of experiments using both supervised end-to-end trained models and pre-trained sentence encoding techniques - SkipThought, Sent2vec and Infersent. The pre-trained embeddings are competitive with the end-to-end model, and the approaches are complementary, with combined models yielding significant performance improvements on two of the three evaluations.
Research in Natural Language Processing (NLP) has increasingly become important due to applications such as text classification, text mining, sentiment analysis, POS tagging, named entity recognition, textual entailment, and many others. This paper introduces several machine and deep learning methods with manual and automatic labelling for news classification in the Bangla language. We implemented several machine (ML) and deep learning (DL) algorithms. The ML algorithms are Logistic Regression (LR), Stochastic Gradient Descent (SGD), Support Vector Machine (SVM), Random Forest (RF), and K-Nearest Neighbour (KNN), used with Bag of Words (BoW), Term Frequency-Inverse Document Frequency (TF-IDF), and Doc2Vec embedding models. The DL algorithms are Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), Gated Recurrent Unit (GRU), and Convolutional Neural Network (CNN), used with Word2vec, Glove, and FastText word embedding models. We develop automatic labelling methods using Latent Dirichlet Allocation (LDA) and investigate the performance of single-label and multi-label article classification methods. To investigate performance, we developed from scratch Potrika, the largest and the most extensive dataset for news classification in the Bangla language, comprising 185.51 million words and 12.57 million sentences contained in 664,880 news articles in eight distinct categories, curated from six popular online news portals in Bangladesh for the period 2014-2020. GRU and Fasttext with 91.83% achieve the highest accuracy for manually-labelled data. For the automatic labelling case, KNN and Doc2Vec at 57.72% and 75% achieve the highest accuracy for single-label and multi-label data, respectively. The methods developed in this paper are expected to advance research in Bangla and other languages.
Reliability measures associated with the prediction of the machine learning models are critical to strengthening user confidence in artificial intelligence. Therefore, those models that are able to provide not only predictions, but also reliability, enjoy greater popularity. In the field of recommender systems, reliability is crucial, since users tend to prefer those recommendations that are sure to interest them, that is, high predictions with high reliabilities. In this paper, we propose Restricted Bernoulli Matrix Factorization (ResBeMF), a new algorithm aimed at enhancing the performance of classification-based collaborative filtering. The proposed model has been compared to other existing solutions in the literature in terms of prediction quality (Mean Absolute Error and accuracy scores), prediction quantity (coverage score) and recommendation quality (Mean Average Precision score). The experimental results demonstrate that the proposed model provides a good balance in terms of the quality measures used compared to other recommendation models.
Uncertainty quantification is one of the most crucial tasks to obtain trustworthy and reliable machine learning models for decision making. However, most research in this domain has only focused on problems with small label spaces and ignored eXtreme Multi-label Classification (XMC), which is an essential task in the era of big data for web-scale machine learning applications. Moreover, enormous label spaces could also lead to noisy retrieval results and intractable computational challenges for uncertainty quantification. In this paper, we aim to investigate general uncertainty quantification approaches for tree-based XMC models with a probabilistic ensemble-based framework. In particular, we analyze label-level and instance-level uncertainty in XMC, and propose a general approximation framework based on beam search to efficiently estimate the uncertainty with a theoretical guarantee under long-tail XMC predictions. Empirical studies on six large-scale real-world datasets show that our framework not only outperforms single models in predictive performance, but also can serve as strong uncertainty-based baselines for label misclassification and out-of-distribution detection, with significant speedup. Besides, our framework can further yield better state-of-the-art results based on deep XMC models with uncertainty quantification.
Raman spectroscopy is a promising technique used for noninvasive analysis of samples in various fields of application due to its ability for fingerprint probing of samples at the molecular level. Chemometrics methods are widely used nowadays for better understanding of the recorded spectral fingerprints of samples and differences in their chemical composition. This review considers a number of manuscripts published in the Spectrochimica Acta, Part A: Molecular and Biomolecular Spectroscopy Journal that presented findings regarding the application of Raman spectroscopy in combination with chemometrics to study samples and their changes caused by different factors. In 57 reviewed manuscripts, we analyzed application of chemometrics algorithms, statistical modeling parameters, utilization of cross validation, sample sizes, as well as the performance of the proposed classification and regression model. We summarized the best strategies for creating classification models and highlighted some common drawbacks when it comes to the application of chemometrics techniques. According to our estimations, about 70% of the papers are likely to contain unsupported or invalid data due to insufficient description of the utilized methods or drawbacks of the proposed classification models. These drawbacks include: (1) insufficient experimental sample size for classification/regression to achieve significant and reliable results, (2) lack of cross validation (or a test set) for verification of the classifier/regression performance, (3) incorrect division of the spectral data into the training and the test/validation sets; (4) improper selection of the PC number to reduce the analyzed spectral data dimension.
We propose a method for computing binary orthogonal non-negative matrix factorization (BONMF) for clustering and classification. The method is tested on several representative real-world data sets. The numerical results confirm that the method has improved accuracy compared to the related techniques. The proposed method is fast for training and classification and space efficient.
In recent years, there has been growing attention to interpretable machine learning models which can give explanatory insights on their behaviour. Thanks to their interpretability, decision trees have been intensively studied for classification tasks and, due to the remarkable advances in mixed integer programming (MIP), various approaches have been proposed to formulate the problem of training an Optimal Classification Tree (OCT) as a MIP model. We present a novel mixed integer quadratic formulation for the OCT problem, which exploits the generalization capabilities of Support Vector Machines for binary classification. Our model, denoted as Margin Optimal Classification Tree (MARGOT), encompasses maximum margin multivariate hyperplanes nested in a binary tree structure. To enhance the interpretability of our approach, we analyse two alternative versions of MARGOT, which include feature selection constraints inducing sparsity of the hyperplanes' coefficients. First, MARGOT has been tested on non-linearly separable synthetic datasets in a 2-dimensional feature space to provide a graphical representation of the maximum margin approach. Finally, the proposed models have been tested on benchmark datasets from the UCI repository. The MARGOT formulation turns out to be easier to solve than other OCT approaches, and the generated tree better generalizes on new observations. The two interpretable versions effectively select the most relevant features, maintaining good prediction quality.
In this technical report, the systems we submitted for subtask 1B of the DCASE 2021 challenge, regarding audiovisual scene classification, are described in detail. They are essentially multi-source transformers employing a combination of auditory and visual features to make predictions. These models are evaluated utilizing the macro-averaged multi-class cross-entropy and accuracy metrics. In terms of the macro-averaged multi-class cross-entropy, our best model achieved a score of 0.620 on the validation data. This is slightly better than the performance of the baseline system (0.658). With regard to the accuracy measure, our best model achieved a score of 77.1\% on the validation data, which is about the same as the performance obtained by the baseline system (77.0\%).
We study the application of large language models to zero-shot and few-shot classification of tabular data. We prompt the large language model with a serialization of the tabular data to a natural-language string, together with a short description of the classification problem. In the few-shot setting, we fine-tune the large language model using some labeled examples. We evaluate several serialization methods including templates, table-to-text models, and large language models. Despite its simplicity, we find that this technique outperforms prior deep-learning-based tabular classification methods on several benchmark datasets. In most cases, even zero-shot classification obtains non-trivial performance, illustrating the method's ability to exploit prior knowledge encoded in large language models. Unlike many deep learning methods for tabular datasets, this approach is also competitive with strong traditional baselines like gradient-boosted trees, especially in the very-few-shot setting.
Selective classification (or classification with a reject option) pairs a classifier with a selection function to determine whether or not a prediction should be accepted. This framework trades off coverage (probability of accepting a prediction) with predictive performance, typically measured by distributive loss functions. In many application scenarios, such as credit scoring, performance is instead measured by ranking metrics, such as the Area Under the ROC Curve (AUC). We propose a model-agnostic approach to associate a selection function to a given probabilistic binary classifier. The approach is specifically targeted at optimizing the AUC. We provide both theoretical justifications and a novel algorithm, called AUCROSS, to achieve such a goal. Experiments show that our method succeeds in trading-off coverage for AUC, improving over existing selective classification methods targeted at optimizing accuracy.
In this study we have presented a novel feature representation for malicious programs that can be used for malware classification. We have shown how to construct the features in a bottom-up approach, and analyzed the overlap of malicious and benign programs in terms of their components. We have shown that our method of analysis offers an increase in feature resolution that is descriptive of data movement in comparison to tf-idf features.
Fair classification aims to stress the classification models to achieve the equality (treatment or prediction quality) among different sensitive groups. However, fair classification can be under the risk of poisoning attacks that deliberately insert malicious training samples to manipulate the trained classifiers' performance. In this work, we study the poisoning scenario where the attacker can insert a small fraction of samples into training data, with arbitrary sensitive attributes as well as other predictive features. We demonstrate that the fairly trained classifiers can be greatly vulnerable to such poisoning attacks, with much worse accuracy & fairness trade-off, even when we apply some of the most effective defenses (originally proposed to defend traditional classification tasks). As countermeasures to defend fair classification tasks, we propose a general and theoretically guaranteed framework which accommodates traditional defense methods to fair classification against poisoning attacks. Through extensive experiments, the results validate that the proposed defense framework obtains better robustness in terms of accuracy and fairness than representative baseline methods.
In this paper, we explore legal argument mining using multiple levels of granularity. Argument mining has usually been conceptualized as a sentence classification problem. In this work, we conceptualize argument mining as a token-level (i.e., word-level) classification problem. We use a Longformer model to classify the tokens. Results show that token-level text classification identifies certain legal argument elements more accurately than sentence-level text classification. Token-level classification also provides greater flexibility to analyze legal texts and to gain more insight into what the model focuses on when processing a large amount of input data.
The recent years we have seen the rise of graph neural networks for prediction tasks on graphs. One of the dominant architectures is graph attention due to its ability to make predictions using weighted edge features and not only node features. In this paper we analyze, theoretically and empirically, graph attention networks and their ability of correctly labelling nodes in a classic classification task. More specifically, we study the performance of graph attention on the classic contextual stochastic block model (CSBM). In CSBM the nodes and edge features are obtained from a mixture of Gaussians and the edges from a stochastic block model. We consider a general graph attention mechanism that takes random edge features as input to determine the attention coefficients. We study two cases, in the first one, when the edge features are noisy, we prove that the majority of the attention coefficients are up to a constant uniform. This allows us to prove that graph attention with edge features is not better than simple graph convolution for achieving perfect node classification. Second, we prove that when the edge features are clean graph attention can distinguish intra- from inter-edges and this makes graph attention better than classic graph convolution.
In recent years, the optical 4f system has drawn much attention in building high-speed and ultra-low-power optical neural networks (ONNs). Most optical systems suffer from the misalignment of the optical devices during installment. The performance of ONN based on the optical 4f system (4f-ONN) is considered sensitive to the misalignment in the optical path introduced. In order to comprehensively investigate the influence caused by the misalignment, we proposed a method for estimating the performance of a 4f-ONN in response to various misalignment in the context of the image classification task.The misalignment in numerical simulation is estimated by manipulating the optical intensity distributions in the fourth focus plane in the 4f system. Followed by a series of physical experiments to validate the simulation results. Using our method to test the impact of misalignment of 4f system on the classification accuracy of two popular image classification datasets, MNIST and Quickdraw16. On both datasets, we found that the performances of 4f-ONN generally degraded dramatically as the positioning error increased. Different positioning error tolerance in the misalignment orientations was observed over the two datasets. Classification performance could be preserved by positioning errors up to 200 microns in a specific direction.
Mitigating bias in training on biased datasets is an important open problem. Several techniques have been proposed, however the typical evaluation regime is very limited, considering very narrow data conditions. For instance, the effect of target class imbalance and stereotyping is under-studied. To address this gap, we examine the performance of various debiasing methods across multiple tasks, spanning binary classification (Twitter sentiment), multi-class classification (profession prediction), and regression (valence prediction). Through extensive experimentation, we find that data conditions have a strong influence on relative model performance, and that general conclusions cannot be drawn about method efficacy when evaluating only on standard datasets, as is current practice in fairness research.
Solar energy is one of the most dependable renewable energy technologies, as it is feasible almost everywhere globally. However, improving the efficiency of a solar PV system remains a significant challenge. To enhance the robustness of the solar system, this paper proposes a trained convolutional neural network (CNN) based fault detection scheme to divide the images of photovoltaic modules. For binary classification, the algorithm classifies the input images of PV cells into two categories (i.e. faulty or normal). To further assess the network's capability, the defective PV cells are organized into shadowy, cracked, or dusty cells, and the model is utilized for multiple classifications. The success rate for the proposed CNN model is 91.1% for binary classification and 88.6% for multi-classification. Thus, the proposed trained CNN model remarkably outperforms the CNN model presented in a previous study which used the same datasets. The proposed CNN-based fault detection model is straightforward, simple and effective and could be applied in the fault detection of solar panel.
In the last few years, various types of machine learning algorithms, such as Support Vector Machine (SVM), Support Vector Regression (SVR), and Non-negative Matrix Factorization (NMF) have been introduced. The kernel approach is an effective method for increasing the classification accuracy of machine learning algorithms. This paper introduces a family of one-parameter kernel functions for improving the accuracy of SVM classification. The proposed kernel function consists of a trigonometric term and differs from all existing kernel functions. We show this function is a positive definite kernel function. Finally, we evaluate the SVM method based on the new trigonometric kernel, the Gaussian kernel, the polynomial kernel, and a convex combination of the new kernel function and the Gaussian kernel function on various types of datasets. Empirical results show that the SVM based on the new trigonometric kernel function and the mixed kernel function achieve the best classification accuracy. Moreover, some numerical results of performing the SVR based on the new trigonometric kernel function and the mixed kernel function are presented.
AI-powered Medical Imaging has recently achieved enormous attention due to its ability to provide fast-paced healthcare diagnoses. However, it usually suffers from a lack of high-quality datasets due to high annotation cost, inter-observer variability, human annotator error, and errors in computer-generated labels. Deep learning models trained on noisy labelled datasets are sensitive to the noise type and lead to less generalization on the unseen samples. To address this challenge, we propose a Robust Stochastic Knowledge Distillation (RoS-KD) framework which mimics the notion of learning a topic from multiple sources to ensure deterrence in learning noisy information. More specifically, RoS-KD learns a smooth, well-informed, and robust student manifold by distilling knowledge from multiple teachers trained on overlapping subsets of training data. Our extensive experiments on popular medical imaging classification tasks (cardiopulmonary disease and lesion classification) using real-world datasets, show the performance benefit of RoS-KD, its ability to distill knowledge from many popular large networks (ResNet-50, DenseNet-121, MobileNet-V2) in a comparatively small network, and its robustness to adversarial attacks (PGD, FSGM). More specifically, RoS-KD achieves >2% and >4% improvement on F1-score for lesion classification and cardiopulmonary disease classification tasks, respectively, when the underlying student is ResNet-18 against recent competitive knowledge distillation baseline. Additionally, on cardiopulmonary disease classification task, RoS-KD outperforms most of the SOTA baselines by ~1% gain in AUC score.
Point cloud classification is a popular task in 3D vision. However, previous works, usually assume that point clouds at test time are obtained with the same procedure or sensor as those at training time. Unsupervised Domain Adaptation (UDA) instead, breaks this assumption and tries to solve the task on an unlabeled target domain, leveraging only on a supervised source domain. For point cloud classification, recent UDA methods try to align features across domains via auxiliary tasks such as point cloud reconstruction, which however do not optimize the discriminative power in the target domain in feature space. In contrast, in this work, we focus on obtaining a discriminative feature space for the target domain enforcing consistency between a point cloud and its augmented version. We then propose a novel iterative self-training methodology that exploits Graph Neural Networks in the UDA context to refine pseudo-labels. We perform extensive experiments and set the new state-of-the-art in standard UDA benchmarks for point cloud classification. Finally, we show how our approach can be extended to more complex tasks such as part segmentation.