works on

From the 1 of 8 linked papers with an AI index.

most citedTask complexity shapes internal representations and robustness in neural networks

1 citations · 2 across the 4 of their papers we have counts for

collaborators

8 papers

cs.LG2026

Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization

Robert Jankowski, Pedro Almagro-Blanco, Marián Boguñá +2

The paper proposes training graph neural networks on geometrically renormalized, coarse‑grained versions of a graph and then directly applying the learned weights to the original f…

cs.LG20261 cited

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…

physics.soc-ph20261 cited

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…

physics.soc-ph2026

Multiplexity amplifies geometry in networks

Jasper van der Kolk, Dmitri Krioukov, Marián Boguñá +1

Many real-world network are multilayer, with nontrivial correlations across layers. Here we show that these correlations amplify geometry in networks. We focus on mutual clustering…

physics.soc-ph2026

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…

physics.soc-ph2025

Extracting the geometric backbone of bipartite networks

Lucía S. Ramírez, Roya Aliakbarisani, M. Ángeles Serrano +1

Real bipartite networks combine degree-constrained random mixing with structured, locality-like rules. We introduce a statistical filter that benchmarks node-level bipartite cluste…