From the original theoretically well-defined spectral graph convolution to the subsequent spatial bassed message-passing model, spatial locality (in vertex domain) acts as a fundamental principle of most graph neural networks (GNNs). In the spectral graph convolution, the filter is approximated by polynomials, where a $k$-order polynomial covers $k$-hop neighbors. In the message-passing, various definitions of neighbors used in aggregations are actually an extensive exploration of the spatial locality information. For learning node representations, the topological distance seems necessary since it characterizes the basic relations between nodes. However, for learning representations of the entire graphs, is it still necessary to hold? In this work, we show that such a principle is not necessary, it hinders most existing GNNs from efficiently encoding graph structures. By removing it, as well as the limitation of polynomial filters, the resulting new architecture significantly boosts performance on learning graph representations. We also study the effects of graph spectrum on signals and interpret various existing improvements as different spectrum smoothing techniques. It serves as a spatial understanding that quantitatively measures the effects of the spectrum to input signals in comparison to the well-known spectral understanding as high/low-pass filters. More importantly, it sheds the light on developing powerful graph representation models.

Recent advances in artificial intelligence (AI) in healthcare hold the potential to increase patient safety, augment efficiency and improve patient outcomes. In clinical care, AI technologies can aid physicians in diagnosis and treatment selection, risk prediction and stratification, and improving patient and clinician efficiency [1]. There has been a vast expansion of available AI technologies in the past decade, creating considerable interest in healthcare data science. Yet, most sophisticated AI models exist only in high-profile publications, and only a few are implemented in clinical practice [2, 3]. The barriers to translating data science research into patient care are inadequate data quality, scarce resources, and high patient confidentiality needs. With the Health Information Technology for Economic and Clinical Health Act of 2009, many institutions have transitioned to electronic medical records that provide a rich medical data source. While initially developed for administrative purposes, most electronic health record (EHR) systems store patient data in heterogeneous formats, sometimes combined with legacy systems. In addition to the structured data for medications, laboratory data, and imaging, there are large amounts of unstructured data like physician notes, discharge summaries, and reports. The EHR data has a significant degree of missingness, misclassification, and errors [4].

Assessing the effects of the energy transition and liberalization of energy markets on resource adequacy is an increasingly important and demanding task. The rising complexity in energy systems requires adequate methods for energy system modeling leading to increased computational requirements. Furthermore, with complexity, uncertainty increases likewise calling for probabilistic assessments and scenario analyses. To adequately and efficiently address these various requirements, new methods from the field of data science are needed to accelerate current methods. With our systematic literature review, we want to close the gap between the three disciplines (1) assessment of security of electricity supply, (2) artificial intelligence, and (3) design of experiments. For this, we conduct a large-scale quantitative review on selected fields of application and methods and make a synthesis that relates the different disciplines to each other. Among other findings, we identify metamodeling of complex security of electricity supply models using AI methods and applications of AI-based methods for forecasts of storage dispatch and (non-)availabilities as promising fields of application that have not sufficiently been covered, yet. We end with deriving a new methodological pipeline for adequately and efficiently addressing the present and upcoming challenges in the assessment of security of electricity supply.

A central subject in Condensed Matter Physics and Statistical Mechanics is the study of phase transitions and critical phenomena [1, 2]. In the last decades, due to the increasing computer power resources, numerical methods have become an indispensable tool for the analysis of classical and quantum interacting systems. Most of these methods, such as Monte Carlo simulations, are performed at finite size systems, which demand the analysis by scaling theories to avoid misleading finite size effects [3-6]. However, depending on the type of systems (classical or quantum), or the geometry/dimensionality, performing a finite size scaling (FSS) analysis may be a challenge - sometimes an unfeasible task -, due to technical bottlenecks: for instance, as a paradigm, in quantum Monte Carlo simulations the occurrence of the infamous minus-sign problem, i.e. the occurrence a negative statistical weight, restricts the simulations to small lattice sizes [7-9]. Another instance is the analysis of three-dimensional systems, in which an extrapolation to the thermodynamic limit is very demanding, even in absence of the sign problem. In view of this, it is worth developing techniques that could give hints of the existing phases and their phase transitions at finite small system sizes, but, at the same time, could also provide quantitatively reasonable critical points. With the advent of big data analysis, e.g. with machine learning techniques, a great expectation is placed to this end. Indeed, over the past few years, there has been an effort to develop and benchmark supervised and unsupervised machine learning techniques [10-12].

Silicon Valley has long been the place to find the next big thing in tech. Companies have built their headquarters around the Bay Area, resulting in a highly competitive market for talent. However, recruiters are looking beyond Silicon Valley for top talent. Recruiters are now recognizing the increasing need for more diverse candidates to impact the growth of their companies. To help connect employers with talented candidates, companies have started using AI recruitment strategies.

Global Artificial Intelligence (AI) in BFSI Sector market report provides information from major key players, geography, segmentation, competitor analysis, sales, revenue, price, gross margin, market share, import-export, trends and forecast 2021-2027. The Artificial Intelligence (AI) in BFSI Sector market Research is an intelligent report with careful efforts to study accurate and valuable information. The data that has been examined is made with regard to both the best existing players and future competitors. The business strategies of the major players and new industries in the emerging market are studied in detail. A well-explained SWOT analysis, revenue sharing and contact information are shared in this report analysis.

Population-level societal events, such as civil unrest and crime, often have a significant impact on our daily life. Forecasting such events is of great importance for decision-making and resource allocation. Event prediction has traditionally been challenging due to the lack of knowledge regarding the true causes and underlying mechanisms of event occurrence. In recent years, research on event forecasting has made significant progress due to two main reasons: (1) the development of machine learning and deep learning algorithms and (2) the accessibility of public data such as social media, news sources, blogs, economic indicators, and other meta-data sources. The explosive growth of data and the remarkable advancement in software/hardware technologies have led to applications of deep learning techniques in societal event studies. This paper is dedicated to providing a systematic and comprehensive overview of deep learning technologies for societal event predictions. We focus on two domains of societal events: \textit{civil unrest} and \textit{crime}. We first introduce how event forecasting problems are formulated as a machine learning prediction task. Then, we summarize data resources, traditional methods, and recent development of deep learning models for these problems. Finally, we discuss the challenges in societal event forecasting and put forward some promising directions for future research.

How confident can we be in the generalization capacity of a predictive model? Of the many devices discussed in the statistical learning literature [1, 2, 3], a simple random split of the original data into training and test sets, and methods of folded cross-validation, stand out as the most common tools used to tackle the generalization issue. Availability of point estimates for the generalization error given by these procedures naturally raises the question of how to quantify the uncertainty involved in these estimates spending a manageable computational cost. Random forests [4] elegantly provide an alternative low cost (almost free) point estimate of the generalization error without requiring splittings of the data, and avoiding the computational burden of retraining the predictive model several times. The bagging mechanism [5] used to construct the ensemble of trees implies that each training data point is not used (stays "out-of-bag") when growing approximately 36.8% of the trees in the forest. This property gives us the so called out-of-bag estimate of the random forest generalization error: for each observation, using a suitable loss function, we compute the predictive error made by the random subforest whose trees didn't include the observation under consideration in its training process; the out-of-bag estimate is the average of these prediction errors over the whole training sample. 1

Current efficient fine-tuning methods (e.g., adapters, prefix-tuning, etc.) have optimized conditional text generation via training a small set of extra parameters of the neural language model, while freezing the rest for efficiency. While showing strong performance on some generation tasks, they don't generalize across all generation tasks. In this work, we show that prompt based conditional text generation can be improved with simple and efficient methods that simulate modeling the discourse structure of human written text. We introduce two key design choices: First we show that a higher-level discourse structure of human written text can be modelled with \textit{hierarchical blocking} on prefix parameters that enable spanning different parts of the input and output text and yield more coherent output generations. Second, we propose sparse prefix tuning by introducing \textit{attention sparsity} on the prefix parameters at different layers of the network and learn sparse transformations on the softmax-function, respectively. We find that sparse attention enables the prefix-tuning to better control of the input contents (salient facts) yielding more efficient tuning of the prefix-parameters. Experiments on a wide-variety of text generation tasks show that structured design of prefix parameters can achieve comparable results to fine-tuning all parameters while outperforming standard prefix-tuning on all generation tasks even in low-resource settings.

Subjects frequently change in moderated debates with several participants, such as in parliamentary sessions, electoral debates, and trials. Partitioning a debate into blocks with the same subject is essential for understanding. Often a moderator is responsible for defining when a new block begins so that the task of automatically partitioning a moderated debate can focus solely on the moderator's behavior. In this paper, we (i) propose a new algorithm, DEBACER, which partitions moderated debates; (ii) carry out a comparative study between conventional and BERTimbau pipelines; and (iii) validate DEBACER applying it to the minutes of the Assembly of the Republic of Portugal. Our results show the effectiveness of DEBACER.