Related papers: HyperNetX: A Python package for modeling complex n…
Most of the current hypergraph learning methodologies and benchmarking datasets in the hypergraph realm are obtained by lifting procedures from their graph analogs, leading to overshadowing specific characteristics of hypergraphs. This…
While social network analysis often focuses on graph structure of social actors, an increasing number of communication networks now provide textual content within social activity (email, instant messaging, blogging, collaboration networks).…
Network data mining has become an important area of study due to the large number of problems it can be applied to. This paper presents NOESIS, an open source framework for network data mining that provides a large collection of network…
Analyzing large complex image collections in domains like forensics, accident investigation, or social media analysis involves interpreting intricate, overlapping relationships among images. Traditional clustering and classification methods…
We consider the problem of explaining the predictions of graph neural networks (GNNs), which otherwise are considered as black boxes. Existing methods invariably focus on explaining the importance of graph nodes or edges but ignore the…
Many important real-world applications-such as social networks or distributed data bases-can be modeled as hypergraphs. In such a model, vertices represent entities-such as users or data records-whereas hyperedges model a group membership…
Background: The study of genome-scale metabolic models and their underlying networks is one of the most important fields in systems biology. The complexity of these models and their description makes the use of computational tools an…
Visual recognition relies on understanding the semantics of image tokens and their complex interactions. Mainstream self-attention methods, while effective at modeling global pair-wise relations, fail to capture high-order associations…
We introduce the \texttt{pyunicorn} (Pythonic unified complex network and recurrence analysis toolbox) open source software package for applying and combining modern methods of data analysis and modeling from complex network theory and…
We present Conedy, a performant scientific tool to numerically investigate dynamics on complex networks. Conedy allows to create networks and provides automatic code generation and compilation to ensure performant treatment of arbitrary…
We describe a flexible data reduction package for high resolution cross-dispersed echelle data. This open-source package is developed in Python and includes optional GUIs for most of the steps. It does not require any pre-knowledge about…
This work proposes PatchNet, an automated tool based on hierarchical deep learning for classifying patches by extracting features from commit messages and code changes. PatchNet contains a deep hierarchical structure that mirrors the…
Multiplex networks are complex graph structures in which a set of entities are connected to each other via multiple types of relations, each relation representing a distinct layer. Such graphs are used to investigate many complex…
Hypergraphs, with their capacity to depict high-order relationships, have emerged as a significant extension of traditional graphs. Although Graph Neural Networks (GNNs) have remarkable performance in graph representation learning, their…
RNA 3D architectures are stabilized by sophisticated networks of (non-canonical) base pair interactions, which can be conveniently encoded as multi-relational graphs and efficiently exploited by graph theoretical approaches and recent…
GraphNeT is an open-source python framework aimed at providing high quality, user friendly, end-to-end functionality to perform reconstruction tasks at neutrino telescopes using graph neural networks (GNNs). GraphNeT makes it fast and easy…
The largenet2 C++ library provides an infrastructure for the simulation of large dynamic and adaptive networks with discrete node and link states. The library is released as free software. It is available at…
Although deep learning models perform remarkably well across a range of tasks such as language translation and object recognition, it remains unclear what high-level logic, if any, they follow. Understanding this logic may lead to more…
Hypergraphs generalize classical graphs by allowing a single edge to connect multiple vertices, providing a natural language for modeling higher-order interactions. Superhypergraphs extend this paradigm further by accommodating nested,…
The development of spiking neural network simulation software is a critical component enabling the modeling of neural systems and the development of biologically inspired algorithms. Existing software frameworks support a wide range of…