Generating synthetic data is a complex task that necessitates accurately replicating the statistical and mathematical properties of the original data elements. In sectors such as finance, utilizing and disseminating real data for research or model development can pose substantial privacy risks owing to the inclusion of sensitive information. Additionally, authentic data may be scarce, particularly in specialized domains where acquiring ample, varied, and high-quality data is difficult or costly. This scarcity or limited data availability can limit the training and testing of machine-learning models. In this paper, we address this challenge. In particular, our task is to synthesize a dataset with similar properties to an input dataset about the stock market. The input dataset is anonymized and consists of very few columns and rows, contains many inconsistencies, such as missing rows and duplicates, and its values are not normalized, scaled, or balanced. We explore the utilization of generative adversarial networks, a deep-learning technique, to generate synthetic data and evaluate its quality compared to the input stock dataset. Our innovation involves generating artificial datasets that mimic the statistical properties of the input elements without revealing complete information. For example, synthetic datasets can capture the distribution of stock prices, trading volumes, and market trends observed in the original dataset. The generated datasets cover a wider range of scenarios and variations, enabling researchers and practitioners to explore different market conditions and investment strategies. This diversity can enhance the robustness and generalization of machine-learning models. We evaluate our synthetic data in terms of the mean, similarities, and correlations.

Taxonomic reasoning is a typical task performed by many AI knowledge representation systems. In this paper, the effectiveness of taxonomic reasoning techniques as an active support to knowledge acquisition and conceptual schema design is shown. The idea developed is that by extending conceptual models with defined concepts and giving them rigorous logic semantics, it is possible to infer isa relationships between concepts on the basis of their descriptions. From a theoretical point of view, this approach makes it possible to give a formal definition for consistency and minimality of a conceptual schema. From a pragmatic point of view it is possible to develop an active environment that allows automatic classification of a new concept in the right position of a given taxonomy, ensuring the consistency and minimality of a conceptual schema. A formalism that includes the data semantics of models giving prominence to type constructors (E/R, TAXIS, GALILEO) and algorithms for taxonomic inferences are presented: their soundness, completeness, and tractability properties are proved. Finally, an extended formalism and taxonomic inference algorithms for models giving prominence to attributes (FDM, IFO) are given.

Long document summarization poses obstacles to current generative transformer-based models because of the broad context to process and understand. Indeed, detecting long-range dependencies is still challenging for today’s state-of-the-art solutions, usually requiring model expansion at the cost of an unsustainable demand for computing and memory capacities. This paper introduces Emma, a novel efficient memory-enhanced transformer-based architecture. By segmenting a lengthy input into multiple text fragments, our model stores and compares the current chunk with previous ones, gaining the capability to read and comprehend the entire context over the whole document with a fixed amount of GPU memory. This method enables the model to deal with theoretically infinitely long documents, using less than 18 and 13 GB of memory for training and inference, respectively. We conducted extensive performance analyses and demonstrate that Emma achieved competitive results on two datasets of different domains while consuming significantly less GPU memory than competitors do, even in low-resource settings.

We introduce a distributed method for detecting distance-based outliers in very large data sets. Our approach is based on the concept of outlier detection solving set [2], which is a small subset of the data set that can be also employed for predicting novel outliers. The method exploits parallel computation in order to obtain vast time savings. Indeed, beyond preserving the correctness of the result, the proposed schema exhibits excellent performances. From the theoretical point of view, for common settings, the temporal cost of our algorithm is expected to be at least three orders of magnitude faster than the classical nested-loop like approach to detect outliers. Experimental results show that the algorithm is efficient and that its running time scales quite well for an increasing number of nodes. We discuss also a variant of the basic strategy which reduces the amount of data to be transferred in order to improve both the communication cost and the overall runtime. Importantly, the solving set computed by our approach in a distributed environment has the same quality as that produced by the corresponding centralized method.

In knowledge graph representation learning, link prediction is among the most popular and influential tasks. Its surge in popularity has resulted in a panoply of orthogonal embedding-based methods projecting entities and relations into low-dimensional continuous vectors. To further enrich the research space, the community witnessed a prolific development of evaluation benchmarks with a variety of structures and domains. Therefore, researchers and practitioners face an unprecedented challenge in effectively identifying the best solution to their needs. To this end, we propose the most comprehensive and up-to-date study to systematically assess the effectiveness and efficiency of embedding models for knowledge graph completion. We compare 13 models on six datasets with different sizes, domains, and relational properties, covering translational, semantic matching, and neural network-based encoders. A fine-grained evaluation is conducted to compare each technique head-to-head in terms of standard metrics, training and evaluation times, memory consumption, carbon footprint, and space geometry. Our results demonstrate the high dependence between performance and graph types, identifying the best options for each scenario. Among all the encoding strategies, the new generation of translational models emerges as the most promising, bringing out the best and most consistent results across all the datasets and evaluation criteria.