As machine learning and deep learning models have become highly prevalent in a multitude of domains, the main reservation in their adoption for decision-making processes is their black-box nature. The Explainable Artificial Intelligence (XAI) paradigm has gained a lot of momentum lately due to its ability to reduce models opacity. XAI methods have not only increased stakeholders' trust in the decision process but also helped developers ensure its fairness. Recent efforts have been invested in creating transparent models and post-hoc explanations. However, fewer methods have been developed for time series data, and even less when it comes to multivariate datasets. In this work, we take advantage of the inherent interpretability of shapelets to develop a model agnostic multivariate time series (MTS) counterfactual explanation algorithm. Counterfactuals can have a tremendous impact on making black-box models explainable by indicating what changes have to be performed on the input to change the final decision. We test our approach on a real-life solar flare prediction dataset and prove that our approach produces high-quality counterfactuals. Moreover, a comparison to the only MTS counterfactual generation algorithm shows that, in addition to being visually interpretable, our explanations are superior in terms of proximity, sparsity, and plausibility.

Automatic identification of hateful and abusive content is vital in combating the spread of harmful online content and its damaging effects. Most existing works evaluate models by examining the generalization error on train-test splits on hate speech datasets. These datasets often differ in their definitions and labeling criteria, leading to poor model performance when predicting across new domains and datasets. In this work, we propose a new Multi-task Learning (MTL) pipeline that utilizes MTL to train simultaneously across multiple hate speech datasets to construct a more encompassing classification model. We simulate evaluation on new previously unseen datasets by adopting a leave-one-out scheme in which we omit a target dataset from training and jointly train on the other datasets. Our results consistently outperform a large sample of existing work. We show strong results when examining generalization error in train-test splits and substantial improvements when predicting on previously unseen datasets. Furthermore, we assemble a novel dataset, dubbed PubFigs, focusing on the problematic speech of American Public Political Figures. We automatically detect problematic speech in the $305,235$ tweets in PubFigs, and we uncover insights into the posting behaviors of public figures.

Couples generally manage chronic diseases together and the management takes an emotional toll on both patients and their romantic partners. Consequently, recognizing the emotions of each partner in daily life could provide an insight into their emotional well-being in chronic disease management. Currently, the process of assessing each partner's emotions is manual, time-intensive, and costly. Despite the existence of works on emotion recognition among couples, none of these works have used data collected from couples' interactions in daily life. In this work, we collected 85 hours (1,021 5-minute samples) of real-world multimodal smartwatch sensor data (speech, heart rate, accelerometer, and gyroscope) and self-reported emotion data (n=612) from 26 partners (13 couples) managing diabetes mellitus type 2 in daily life. We extracted physiological, movement, acoustic, and linguistic features, and trained machine learning models (support vector machine and random forest) to recognize each partner's self-reported emotions (valence and arousal). Our results from the best models (balanced accuracies of 63.8% and 78.1% for arousal and valence respectively) are better than chance and our prior work that also used data from German-speaking, Swiss-based couples, albeit, in the lab. This work contributes toward building automated emotion recognition systems that would eventually enable partners to monitor their emotions in daily life and enable the delivery of interventions to improve their emotional well-being.

The majority of knowledge graph embedding techniques treat entities and predicates as separate embedding matrices, using aggregation functions to build a representation of the input triple. However, these aggregations are lossy, i.e. they do not capture the semantics of the original triples, such as information contained in the predicates. To combat these shortcomings, current methods learn triple embeddings from scratch without utilizing entity and predicate embeddings from pre-trained models. In this paper, we design a novel fine-tuning approach for learning triple embeddings by creating weak supervision signals from pre-trained knowledge graph embeddings. We develop a method for automatically sampling triples from a knowledge graph and estimating their pairwise similarities from pre-trained embedding models. These pairwise similarity scores are then fed to a Siamese-like neural architecture to fine-tune triple representations. We evaluate the proposed method on two widely studied knowledge graphs and show consistent improvement over other state-of-the-art triple embedding methods on triple classification and triple clustering tasks.

Center-based clustering (e.g., $k$-means, $k$-medians) and clustering using linear subspaces are two most popular techniques to partition real-world data into smaller clusters. However, when the data consists of sensitive demographic groups, significantly different clustering cost per point for different sensitive groups can lead to fairness-related harms (e.g., different quality-of-service). The goal of socially fair clustering is to minimize the maximum cost of clustering per point over all groups. In this work, we propose a unified framework to solve socially fair center-based clustering and linear subspace clustering, and give practical, efficient approximation algorithms for these problems. We do extensive experiments to show that on multiple benchmark datasets our algorithms either closely match or outperform state-of-the-art baselines.

Understanding the computational complexity of training simple neural networks with rectified linear units (ReLUs) has recently been a subject of intensive research. Closing gaps and complementing results from the literature, we present several results on the parameterized complexity of training two-layer ReLU networks with respect to various loss functions. After a brief discussion of other parameters, we focus on analyzing the influence of the dimension d of the training data on the computational complexity. We provide running time lower bounds in terms of W[1]-hardness for parameter d and prove that known brute-force strategies are essentially optimal (assuming the Exponential Time Hypothesis). In comparison with previous work, our results hold for a broad(er) range of loss functions, including lp-loss for all p ∈ [0, ∞]. In particular, we improve a known polynomial-time algorithm for constant d and convex loss functions to a more general class of loss functions, matching our running time lower bounds also in these cases.

Artificial intelligence (AI) is a term you must have heard, even if you are from the IT world. AI is when machines and computer systems simulate human intelligence processes. Right now, AI is literally taking over the world – at least 90% of tech giants invest in it. According to the Data and AI Leadership Executive Survey, the number of AI-friendly companies participating in the survey has doubled in one year. Another survey states that half of the interviewed companies use AI. Some more specific applications of AI include expert systems, natural language processing, speech recognition, and machine (computer) vision. The latter type of AI – computer vision – has already been integrated into road traffic, bank payments, and social networks. For the last decades, AI vision has learned to solve many tasks with an accuracy reaching the human one. "As many others have noticed and pointed out, the neocortex has a highly uniform architecture too across all of its input modalities. Perhaps nature has stumbled by a very similar powerful architecture and replicated it in a similar fashion, varying only some of the details. This consolidation in architecture will in turn focus and concentrate software, hardware, and infrastructure, further speeding up progress across AI. […] Anyway, exciting times." Many companies have started using computer vision in artificial intelligence tasks.

The advantages and difficulties of application of Pad\'e approximants to two-dimensional regression analysis are discussed. New formulation of residuals is suggested in the method of least squares. It leads to a system of linear equations in case of rational functions. The possibility of using Tikhonov regularization technique to avoid overfitting is demonstrated in this approach. To illustrate the efficiency of the suggested method, several practical cases from physics and reliability theory are considered.

Time series models often deal with extreme events and anomalies, both prevalent in real-world datasets. Such models often need to provide careful probabilistic forecasting, which is vital in risk management for extreme events such as hurricanes and pandemics. However, it is challenging to automatically detect and learn to use extreme events and anomalies for large-scale datasets, which often require manual effort. Hence, we propose an anomaly-aware forecast framework that leverages the previously seen effects of anomalies to improve its prediction accuracy during and after the presence of extreme events. Specifically, the framework automatically extracts anomalies and incorporates them through an attention mechanism to increase its accuracy for future extreme events. Moreover, the framework employs a dynamic uncertainty optimization algorithm that reduces the uncertainty of forecasts in an online manner. The proposed framework demonstrated consistent superior accuracy with less uncertainty on three datasets with different varieties of anomalies over the current prediction models.

Predicting mechanical properties in metal additive manufacturing (MAM) is vital to ensure the printed parts' performance, reliability, and whether they can fulfill requirements for a specific application. Conducting experiments to estimate mechanical properties in MAM processes, however, is a laborious and expensive task. Also, they can solely be designed for a particular material in a certain MAM process. Nonetheless, Machine learning (ML) methods, which are more flexible and cost-effective solutions, can be utilized to predict mechanical properties based on the processing parameters and material properties. To this end, in this work, a comprehensive framework for benchmarking ML for mechanical properties is introduced. An extensive experimental dataset is collected from more than 90 MAM articles and 140 MAM companies' data sheets containing MAM processing conditions, machines, materials, and resultant mechanical properties, including yield strength, ultimate tensile strength, elastic modulus, elongation, hardness as well as surface roughness. Physics-aware MAM featurization, adjustable ML models, and evaluation metrics are proposed to construct a comprehensive learning framework for mechanical properties prediction. Additionally, the Explainable AI method, i.e., SHAP analysis was studied to explain and interpret the ML models' predicted values for mechanical properties. Moreover, data-driven explicit models have been identified to estimate mechanical properties based on the processing parameters and material properties with more interpretability as compared to the employed ML models.