Regulations introduced by General Data Protection Regulation (GDPR) in the EU or California Consumer Privacy Act (CCPA) in the US have included provisions on the \textit{right to be forgotten} that mandates industry applications to remove data related to an individual from their systems. In several real world industry applications that use Machine Learning to build models on user data, such mandates require significant effort both in terms of data cleansing as well as model retraining while ensuring the models do not deteriorate in prediction quality due to removal of data. As a result, continuous removal of data and model retraining steps do not scale if these applications receive such requests at a very high frequency. Recently, a few researchers proposed the idea of \textit{Machine Unlearning} to tackle this challenge. Despite the significant importance of this task, the area of Machine Unlearning is under-explored in Natural Language Processing (NLP) tasks. In this paper, we explore the Unlearning framework on various GLUE tasks \cite{Wang:18}, such as, QQP, SST and MNLI. We propose computationally efficient approaches (SISA-FC and SISA-A) to perform \textit{guaranteed} Unlearning that provides significant reduction in terms of both memory (90-95\%), time (100x) and space consumption (99\%) in comparison to the baselines while keeping model performance constant.

Cancer is one of the most challenging diseases because of its complexity, variability, and diversity of causes. It has been one of the major research topics over the past decades, yet it is still poorly understood. To this end, multifaceted therapeutic frameworks are indispensable. \emph{Anticancer peptides} (ACPs) are the most promising treatment option, but their large-scale identification and synthesis require reliable prediction methods, which is still a problem. In this paper, we present an intuitive classification strategy that differs from the traditional \emph{black box} method and is based on the well-known statistical theory of \emph{sparse-representation classification} (SRC). Specifically, we create over-complete dictionary matrices by embedding the \emph{composition of the K-spaced amino acid pairs} (CKSAAP). Unlike the traditional SRC frameworks, we use an efficient \emph{matching pursuit} solver instead of the computationally expensive \emph{basis pursuit} solver in this strategy. Furthermore, the \emph{kernel principal component analysis} (KPCA) is employed to cope with non-linearity and dimension reduction of the feature space whereas the \emph{synthetic minority oversampling technique} (SMOTE) is used to balance the dictionary. The proposed method is evaluated on two benchmark datasets for well-known statistical parameters and is found to outperform the existing methods. The results show the highest sensitivity with the most balanced accuracy, which might be beneficial in understanding structural and chemical aspects and developing new ACPs. The Google-Colab implementation of the proposed method is available at the author's GitHub page (\href{https://github.com/ehtisham-Fazal/ACP-Kernel-SRC}{https://github.com/ehtisham-fazal/ACP-Kernel-SRC}).

With the progress of sensor technology in wearables, the collection and analysis of PPG signals are gaining more interest. Using Machine Learning, the cardiac rhythm corresponding to PPG signals can be used to predict different tasks such as activity recognition, sleep stage detection, or more general health status. However, supervised learning is often limited by the amount of available labeled data, which is typically expensive to obtain. To address this problem, we propose a Self-Supervised Learning (SSL) method with a pretext task of signal reconstruction to learn an informative generalized PPG representation. The performance of the proposed SSL framework is compared with two fully supervised baselines. The results show that in a very limited label data setting (10 samples per class or less), using SSL is beneficial, and a simple classifier trained on SSL-learned representations outperforms fully supervised deep neural networks. However, the results reveal that the SSL-learned representations are too focused on encoding the subjects. Unfortunately, there is high inter-subject variability in the SSL-learned representations, which makes working with this data more challenging when labeled data is scarce. The high inter-subject variability suggests that there is still room for improvements in learning representations. In general, the results suggest that SSL may pave the way for the broader use of machine learning models on PPG data in label-scarce regimes.

Deep neural networks (DNNs) are often used for text classification tasks as they usually achieve high levels of accuracy. However, DNNs can be computationally intensive with billions of parameters and large amounts of labeled data, which can make them expensive to use, to optimize and to transfer to out-of-distribution (OOD) cases in practice. In this paper, we propose a non-parametric alternative to DNNs that's easy, light-weight and universal in text classification: a combination of a simple compressor like gzip with a $k$-nearest-neighbor classifier. Without any training, pre-training or fine-tuning, our method achieves results that are competitive with non-pretrained deep learning methods on six in-distributed datasets. It even outperforms BERT on all five OOD datasets, including four low-resource languages. Our method also performs particularly well in few-shot settings where labeled data are too scarce for DNNs to achieve a satisfying accuracy.

Non-parametric tests can determine the better of two stochastic optimization algorithms when benchmarking results are ordinal, like the final fitness values of multiple trials. For many benchmarks, however, a trial can also terminate once it reaches a pre-specified target value. When only some trials reach the target value, two variables characterize a trial's outcome: the time it takes to reach the target value (or not) and its final fitness value. This paper describes a simple way to impose linear order on this two-variable trial data set so that traditional non-parametric methods can determine the better algorithm when neither dominates. We illustrate the method with the Mann-Whitney U-test. A simulation demonstrates that U-scores are much more effective than dominance when tasked with identifying the better of two algorithms. We test U-scores by having them determine the winners of the CEC 2022 Special Session and Competition on Real-Parameter Numerical Optimization.

Compared to K-12, US institutions of higher education, particularly four-year universities, give students a high amount of elective course choice. This choice comes with unique challenges that can inhibit their learning path, such as the choice to overload on credit hours causing early undergraduate dropout among older students with prior vocational training and completed degrees [22]. Conversely, low enrollment levels have also been found to be associated with worse educational outcomes, potentially due to a lack of financial and academic support [5]. These findings, though seemingly contradictory, suggest that semester workload may play an important role in explaining the complicated story of student success in higher education. However, recent work has found that credit hours is not a suitable proxy for course workload, as it captures only 6% of the variance in student reported course load compared to 36% captured by LMS features [36]. In this paper, we introduce course load analytics (CLA) as a machine learning approach to producing metrics about course workload relevant to student course selection. This work is the first to predict course load at scale, generalizing to over 10,000 courses at a large public institution and going beyond time load considerations by incorporating more holistic measures such as mental effort and psychological stress. Our findings suggest that the discrepancy between anticipated course load (i.e., as calculated by credit hours) and actual course load (i.e., as estimated by CLA) may be a significant factor in program stop-out.

Few-shot methods for accurate modeling under sparse label-settings have improved significantly. However, the applications of few-shot modeling in natural language processing remain solely in the field of document classification. With recent performance improvements, supervised few-shot methods, combined with a simple topic extraction method pose a significant challenge to unsupervised topic modeling methods. Our research shows that supervised few-shot learning, combined with a simple topic extraction method, can outperform unsupervised topic modeling techniques in terms of generating coherent topics, even when only a few labeled documents per class are used.

Factorization machines (FMs) are a powerful tool for regression and classification in the context of sparse observations, that has been successfully applied to collaborative filtering, especially when side information over users or items is available. Bayesian formulations of FMs have been proposed to provide confidence intervals over the predictions made by the model, however they usually involve Markov-chain Monte Carlo methods that require many samples to provide accurate predictions, resulting in slow training in the context of large-scale data. In this paper, we propose a variational formulation of factorization machines that allows us to derive a simple objective that can be easily optimized using standard mini-batch stochastic gradient descent, making it amenable to large-scale data. Our algorithm learns an approximate posterior distribution over the user and item parameters, which leads to confidence intervals over the predictions. We show, using several datasets, that it has comparable or better performance than existing methods in terms of prediction accuracy, and provide some applications in active learning strategies, e.g., preference elicitation techniques.

Machine Learning algorithms have been extensively researched throughout the last decade, leading to unprecedented advances in a broad range of applications, such as image classification and reconstruction, object recognition, and text categorization. Nonetheless, most Machine Learning algorithms are trained via derivative-based optimizers, such as the Stochastic Gradient Descent, leading to possible local optimum entrapments and inhibiting them from achieving proper performances. A bio-inspired alternative to traditional optimization techniques, denoted as meta-heuristic, has received significant attention due to its simplicity and ability to avoid local optimums imprisonment. In this work, we propose to use meta-heuristic techniques to fine-tune pre-trained weights, exploring additional regions of the search space, and improving their effectiveness. The experimental evaluation comprises two classification tasks (image and text) and is assessed under four literature datasets. Experimental results show nature-inspired algorithms' capacity in exploring the neighborhood of pre-trained weights, achieving superior results than their counterpart pre-trained architectures. Additionally, a thorough analysis of distinct architectures, such as Multi-Layer Perceptron and Recurrent Neural Networks, attempts to visualize and provide more precise insights into the most critical weights to be fine-tuned in the learning process.

Real-time individual endpoint prediction has always been a challenging task but of great clinic utility for both patients and healthcare providers. GRU-D-Weibull has a maximum C-index of 0.77 at 4.3 years of follow-up, compared to 0.68 achieved by competing models. The average absolute L1-loss of GRU-D-Weibull is around one year, with a minimum of 40% Parkes' serious error after index date. GRU-D-Weibull is not calibrated and significantly underestimates true survival probability. Feature importance tests indicate blood pressure becomes increasingly important during follow-up, while eGFR and blood albumin are less important. Most continuous features have non-linear/parabola impact on predicted survival time, and the results are generally consistent with existing knowledge. GRU-D-Weibull as a semi-parametric temporal model shows advantages in built-in parameterization of missingness, native support for asynchronously arrived measurement, capability of output both probability and point estimates at arbitrary time point for arbitrary prediction horizon, improved discrimination and point estimate accuracy after incorporating newly arrived data. Further research on its performance with more comprehensive input features, in-process or post-process calibration are warranted to benefit CKD4 or alike terminally-ill patients. Author Contribution: XR performed data analysis and manuscript writing. LW performed data extraction, curation, and proof-reading. CT and WC provided expert opinion on selection of study population, explanation of observations, and proof-reading.