1 citations · 2 across the 11 of their papers we have counts for
11 papers
Latent geometry organizes higher-order interactions
Berné L. Nortier, Jasper van der Kolk, Robert Jankowski +4
Higher-order structures offer a natural representation of complex systems that involve interactions between groups of different sizes. A widespread feature of their higher-order st…
Hyperbolic Graph Embedders for Link Prediction and Topology Reconstruction
Robert Jankowski, Maksim Kitsak, Dorota Celińska-Kopczyńska
Hyperbolic embeddings provide compact geometric representations of complex networks in hyperbolic spaces, but systematic comparisons of methods developed in machine learning, netwo…
Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization
Robert Jankowski, Pedro Almagro-Blanco, Marián Boguñá +2
Graph neural networks (GNNs) can operate on large graphs but become infrastructure-sensitive at the scale of millions of nodes and typically require scalable training techniques fo…
Motif-based filtrations for persistent homology: A framework for graph isomorphism and property prediction
Meritxell Vila-Miñana, Robert Jankowski, Aina Ferrà Marcús +3
Determining whether two graphs are isomorphic is a fundamental problem with practical applications in areas such as molecular chemistry or social network analysis, yet it remains a…
Trade-offs between structural richness and perceptual robustness in music network representations
Lluc Bono Rosselló, Robert Jankowski, Hugues Bersini +2
Music is a structured and perceptually rich sequence of sounds in time, whose perception is shaped by the interplay of expectation and uncertainty about what comes next. Yet the un…
Shortest-path percolation on scale-free networks
Minsuk Kim, Lorenzo Cirigliano, Claudio Castellano +4
The shortest-path percolation (SPP) model aims at describing the consumption and eventual exhaustion of a network's resources. Starting from a network containing a macroscopic conn…
Chordless cycle filtrations for dimensionality detection in complex networks via topological data analysis
Aina Ferrà Marcús, Robert Jankowski, Meritxell Vila Miñana +2
Many complex networks, ranging from social to biological systems, exhibit structural patterns consistent with an underlying hyperbolic geometry. Revealing the dimensionality of thi…
Task complexity shapes internal representations and robustness in neural networks
Robert Jankowski, Filippo Radicchi, M. Ángeles Serrano +2
Neural networks excel across a wide range of tasks, yet remain black boxes. In particular, how their internal representations are shaped by the complexity of the input data and the…
Mapping bipartite networks into multidimensional hyperbolic spaces
Robert Jankowski, Roya Aliakbarisani, M. Ángeles Serrano +1
Bipartite networks appear in many real-world contexts, linking entities across two distinct sets. They are often analyzed via one-mode projections, but such projections can introdu…
Hyperbolic Benchmarking Unveils Network Topology-Feature Relationship in GNN Performance
Roya Aliakbarisani, Robert Jankowski, M. Ángeles Serrano +1
Graph Neural Networks (GNNs) have excelled in predicting graph properties in various applications ranging from identifying trends in social networks to drug discovery and malware d…
Feature-aware ultra-low dimensional reduction of real networks
Robert Jankowski, Pegah Hozhabrierdi, Marián Boguñá +1
In existing models and embedding methods of networked systems, node features describing their qualities are usually overlooked in favor of focusing solely on node connectivity. Thi…