No abstract

No abstract

Scientometrics is an area recently attracting greater research interest. To a great extent this area has been fertilized by the proposal of the h-index (2005), which represents a measure for the quality and quantity of a researcher's impact. The Perfectionism Index has been recently proposed aiming at differentiating between 'influentials' and 'mass producers' (2015); the former category produces articles, which are (almost all) with high impact, whereas the latter category produces a lot of articles with moderate or no impact at all. In this paper, we record a number of metrics that are of similar nature, i.e. they shed light into these publishing patterns (influentials vs. mass producers). We carry out a correlation analysis to reveal which metrics are describing the above phenomenon in a similar way and, thus, retain the most descriptive features. Finally, we report the results of an experiment with a dataset consisting of the academic staff of Greek Computer Science/Engineering departments.

Graph Representation Learning (GRL) has experienced significant progress as a means to extract structural information in a meaningful way for subsequent learning tasks. Current approaches including shallow embeddings and Graph Neural Networks have mostly been tested with node classification and link prediction tasks. In this work, we provide an application oriented perspective to a set of popular embedding approaches and evaluate their representational power with respect to realworld graph properties. We implement an extensive empirical data-driven framework to challenge existing norms regarding the expressive power of embedding approaches in graphs with varying patterns along with a theoretical analysis of the limitations we discovered in this process. Our results suggest that "one-to-fit-all" GRL approaches are hard to define in real-world scenarios and as new methods are being introduced they should be explicit about their ability to capture graph properties and their applicability in datasets with non-trivial structural differences.

Financial transactions can be considered edges in a heterogeneous graph between entities sending money and entities receiving money. For financial institutions, such a graph is likely large (with millions or billions of edges) while also sparsely connected. It becomes challenging to apply machine learning to such large and sparse graphs. Graph representation learning seeks to embed the nodes of a graph into a euclidean vector space such that graph topological properties are preserved after the transformation. In this paper, we present a novel application of representation learning to bipartite graphs of credit card transactions in order to learn embeddings of account and merchant entities. Our framework is inspired by popular approaches in graph embeddings and is trained on two internal transaction datasets. This approach yields highly effective embeddings, as quantified by link prediction AUC and F1 score. Further, the resulting entity vectors retain intuitive semantic similarity that is explored through visualizations and other qualitative analyses. Finally, we show how these embeddings can be used as features in downstream machine learning business applications such as fraud detection.