activity
20242026
collaborators

5 papers

cs.LG2026

Robustness in sparse artificial neural networks trained with adaptive topology

Bendegúz Sulyok, Gergely Palla, Filippo Radicchi +1

We investigate the robustness of sparse artificial neural networks trained with adaptive topology. We focus on a simple yet effective architecture consisting of three sparse layers…

physics.soc-ph2026

Network geometry of the Drosophila brain

Bendegúz Sulyok, Sámuel G. Balogh, Gergely Palla

The recent reconstruction of the Drosophila brain provides a neural network of unprecedented size and level of details. In this work, we study the geometrical properties of this sy…

physics.soc-ph2025

Hierarchy and ranking in pairwise sports contests

Bogdán Asztalos, Boldizsár Balázs, Gergely Palla +1

Ranking athletes by their performance in competitions and tournaments is common in every popular sport and has significant benefits that contribute to both the organization and str…

physics.soc-ph2025

Community detection in hypergraphs through hyperedge percolation

Bianka Kovács, Barnabás Benedek, Gergely Palla

Complex networks often exhibit community structure, with communities corresponding to denser subgraphs in which nodes are closely linked. When modelling systems where interactions…

physics.soc-ph2024

CLOVE: Travelling Salesman's approach to hyperbolic embeddings of complex networks with communities

Sámuel G. Balogh, Bendegúz Sulyok, Tamás Vicsek +1

The embedding of complex networks into metric spaces has become a research topic of high interest with a wide variety of proposed methods. Low dimensional hyperbolic spaces offer a…