CoEPinKB: A Framework to Understand the Connectivity of Entity Pairs in Knowledge Bases

A knowledge base, expressed using the Resource Description Framework (RDF), can be viewed as a graph whose nodes represent entities and whose edges denote relationships. The entity relatedness problem refers to the problem of discovering and understanding how two entities are related, directly or indirectly, that is, how they are connected by paths in a knowledge base. Strategies designed to solve the entity relatedness problem typically adopt an entity similarity measure to reduce the path search space and a path ranking measure to order and filter the list of paths returned. This paper presents a framework, called CoEPinKB, that supports the empirical evaluation of such strategies. The proposed framework allows combining entity similarity and path ranking measures to generate different path search strategies. The main goals of this paper are to describe the framework and present a performance evaluation of nine different path search strategies.

Employability tautological trauma

PurposeThis paper explores the institutional and economic drivers of employability, as existing literature focuses on the individual and skills aspects, of employability. Tertiary institutions, possessing a strong academic reputation and standing amongst potential employers, will achieve high graduate employability, however when measured, this is not the case.Design/methodology/approachThis exploratory study builds on Santos' career boundary theory, recognising organisational boundaries; those related to the labour market, personal-aspects and finally, cultural boundaries (Santos, 2020). 37 Universities that provided their employability rate, within 12 months of graduation for 2020, are analysed. The Quacquarelli Symonds (QS) Ranking, measures drivers in terms of institutional reputation through survey responses, and partnerships with employers via research and placement data.FindingsThe regression explained 19% of the variation between the number of graduates being employed and the institutional and economic drivers. Universities in the same economic context, do not have the same number of employed students. Equally, those universities with the most favourable academic reputation, do not have the most employed student rate.Research limitations/implicationsOnly 37 universities provided all their employability data, thus, research with a larger sample will have to be conducted, but equally more needs to be done to establish why the smaller universities are unable to submit all the required data.Originality/valueAn exploratory understanding of the institutional and economic drivers of employability, is provided.

Learning over No-Preferred and Preferred Sequence of Items for Robust Recommendation

In this paper, we propose a theoretically supported sequential strategy for training a large-scale Recommender System (RS) over implicit feedback, mainly in the form of clicks. The proposed approach consists in minimizing pairwise ranking loss over blocks of consecutive items constituted by a sequence of non-clicked items followed by a clicked one for each user. We present two variants of this strategy where model parameters are updated using either the momentum method or a gradient-based approach. To prevent updating the parameters for an abnormally high number of clicks over some targeted items (mainly due to bots), we introduce an upper and a lower threshold on the number of updates for each user. These thresholds are estimated over the distribution of the number of blocks in the training set. They affect the decision of RS by shifting the distribution of items that are shown to the users. Furthermore, we provide a convergence analysis of both algorithms and demonstrate their practical efficiency over six large-scale collections with respect to various ranking measures and computational time.

Graph Neural Networks for Fast Node Ranking Approximation

Graphs arise naturally in numerous situations, including social graphs, transportation graphs, web graphs, protein graphs, etc. One of the important problems in these settings is to identify which nodes are important in the graph and how they affect the graph structure as a whole. Betweenness centrality and closeness centrality are two commonly used node ranking measures to find out influential nodes in the graphs in terms of information spread and connectivity. Both of these are considered as shortest path based measures as the calculations require the assumption that the information flows between the nodes via the shortest paths. However, exact calculations of these centrality measures are computationally expensive and prohibitive, especially for large graphs. Although researchers have proposed approximation methods, they are either less efficient or suboptimal or both. We propose the first graph neural network (GNN) based model to approximate betweenness and closeness centrality. In GNN, each node aggregates features of the nodes in multihop neighborhood. We use this feature aggregation scheme to model paths and learn how many nodes are reachable to a specific node. We demonstrate that our approach significantly outperforms current techniques while taking less amount of time through extensive experiments on a series of synthetic and real-world datasets. A benefit of our approach is that the model is inductive, which means it can be trained on one set of graphs and evaluated on another set of graphs with varying structures. Thus, the model is useful for both static graphs and dynamic graphs. Source code is available at https://github.com/sunilkmaurya/GNN_Ranking

Anomalous Event Recognition in Videos Based on Joint Learning of Motion and Appearance with Multiple Ranking Measures

Given the scarcity of annotated datasets, learning the context-dependency of anomalous events as well as mitigating false alarms represent challenges in the task of anomalous activity detection. We propose a framework, Deep-network with Multiple Ranking Measures (DMRMs), which addresses context-dependency using a joint learning technique for motion and appearance features. In DMRMs, the spatial-time-dependent features are extracted from a video using a 3D residual network (ResNet), and deep motion features are extracted by integrating the motion flow maps’ information with the 3D ResNet. Afterward, the extracted features are fused for joint learning. This data fusion is then passed through a deep neural network for deep multiple instance learning (DMIL) to learn the context-dependency in a weakly-supervised manner using the proposed multiple ranking measures (MRMs). These MRMs consider multiple measures of false alarms, and the network is trained with both normal and anomalous events, thus lowering the false alarm rate. Meanwhile, in the inference phase, the network predicts each frame’s abnormality score along with the localization of moving objects using motion flow maps. A higher abnormality score indicates the presence of an anomalous event. Experimental results on two recent and challenging datasets demonstrate that our proposed framework improves the area under the curve (AUC) score by 6.5% compared to the state-of-the-art method on the UCF-Crime dataset and shows AUC of 68.5% on the ShanghaiTech dataset.

Editorial: The 13th Rothkopf Rankings: All-Time Interfaces/INFORMS Journal on Applied Analytics 50-Year Anniversary Special Edition

In 1996, Michael Rothkopf created an index of institutional contributions to the practice of operations research (OR) and management science (MS). Since then, Ron Fricker and I have continued to calculate, evolve, and extend this ranking. In this Interfaces (INT) and INFORMS Journal on Applied Analytics (IJAA) anniversary ranking, I analyze organizational contributions to the practice of OR/MS in INT since the inception of the journal in 1971. I calculate all three prior ranking measures—visibility, yield, and academic yield—and a blend of the rankings. This analysis considers only articles in INT/IJAA, which is a departure from prior rankings, which included applied work in some other journals. However, for the first time, we have a single database of every article ever published in INT/IJAA, allowing analysis of trends over time. I am also able to compute the all-time contributions of nonacademic institutions as done by Fricker in 2012.

Improving Forecast Uncertainty Quantification by Incorporating Production History and Using a Modified Ranking Method of Geostatistical Realizations

The majority of the geostatistical realizations ranking methods disregard the production history in selection of realizations, due to its requirement of high simulation run time. They also ignore to consider the degree of linear relationship between the “ranks based on the ranking measure” and “ranks based on the performance parameter” in choosing the employed ranking measure. To address these concerns, we propose an uncertainty quantification workflow, which includes two sequential stages of history matching and realization selection. In the first stage, production data are incorporated in the uncertainty quantification procedure through a history matching process. A fast simulator is employed to find the realizations with consistent flow behavior with the production history data in shorter time, compared to a comprehensive simulator. The selected realizations are the input of the second stage of the workflow, which can be any type of the realization selection method. In this study, we used the most convenient realization selection method, i.e., ranking of the realizations. To select the most efficient ranking measure, we investigated the degree of the linear correlation between the ranks based on the several ranking measures and the performance parameter. In addition, due to the shortcomings of the traditional ranking methods in uncertainty quantiles identification, a modified ranking method is introduced. This modification increases the certainty in the probability of the selected realizations. The obtained results on 3D close-to-real synthetic reservoir models revealed the capability of the modified ranking method in more accurate quantification of the uncertainty in reservoir performance prediction.

OmicsARules: a R package for integration of multi-omics datasets via association rules mining

Background The improvements of high throughput technologies have produced large amounts of multi-omics experiments datasets. Initial analysis of these data has revealed many concurrent gene alterations within single dataset or/and among multiple omics datasets. Although powerful bioinformatics pipelines have been developed to store, manipulate and analyze these data, few explicitly find and assess the recurrent co-occurring aberrations across multiple regulation levels. Results Here, we introduced a novel R-package (called OmicsARules) to identify the concerted changes among genes under association rules mining framework. OmicsARules embedded a new rule-interestingness measure, Lamda3, to evaluate the associated pattern and prioritize the most biologically meaningful gene associations. As demonstrated with DNA methlylation and RNA-seq datasets from breast invasive carcinoma (BRCA), esophageal carcinoma (ESCA) and lung adenocarcinoma (LUAD), Lamda3 achieved better biological significance over other rule-ranking measures. Furthermore, OmicsARules can illustrate the mechanistic connections between methlylation and transcription, based on combined omics dataset. OmicsARules is available as a free and open-source R package. Conclusions OmicsARules searches for concurrent patterns among frequently altered genes, thus provides a new dimension for exploring single or multiple omics data across sequencing platforms.