Network Science Informs AI (NSIA)

NetSci 2026 Satellite

Slides/Posters

Talks

Invited Talks

Nataša Pržulj
Simplicity Within Biological Complexity
Nataša Pržulj — Mohamed Bin Zayed University of AI
Slides: TBC
Rebekka Burkholz
Smarter and Sparser AI with Complex Network Science
Rebekka Burkholz — Helmholtz Center CISPA
Giovanni Petri
The Cost of Sharing: From Topological Multitasking Limits to Semantic Horizons
Giovanni Petri — Northeastern University London
Michael Williams
Representation Learning and Physics
Michael Williams — MIT
Tomaso Poggio
Compositional Sparsity
Tomaso Poggio — MIT

Contributed Talks

Siddhi Kanta Mishra
From Graphons to Graphlets: A Graph-Limit Lens on Sparse Neural Connectivity and Training
Siddhi Kanta Mishra — University of Central Florida
Adrien Pontlevy
Emergence of giant component in percolated artificial neural networks
Adrien Pontlevy — Paris Brain Institute
Bendeguz Sulyok
Robustness in sparse artificial neural networks trained with adaptive topology
Bendeguz Sulyok — Semmelweis University
Robert Jankowski
Task complexity shapes internal representations and robustness in neural networks
Robert Jankowski — Delft University of Technology
🏆 Best Contributed Talk Award

Posters

A Brain network science modelling of sparse neural networks enables Transformers and LLMs to perform as fully connected
Yingtao Zhang, Diego Cerretti, Jialin Zhao, Wenjing Wu, Ziheng Liao, Umberto Michieli, Carlo Vittorio Cannistraci
Adaptive Cannistraci Hebb Network Automata Modelling of Complex Networks for Path based Link Prediction
Jialin Zhao, Alessandro Muscoloni, Umberto Michieli, Yingtao Zhang, Carlo Vittorio Cannistraci
Emergence of giant component in percolated artificial neural networks
Adrien Pontlevy, Fabrizio de Vico Fallani
Entropy and Heterogeneity in the AI Research-to-Product Knowledge Transfer Network
Kranthi Kumar Manchikanti
Fréchet Regression on the Bures-Wasserstein Manifold
Duc Toan Nguyen, Cesar A Uribe
From Graphons to Graphlets: A Graph-Limit Lens on Sparse Neural Connectivity and Training
Siddhi Kanta Mishra, Ivan Garibay
Heavy-tailed update distributions arise from information-driven self-organization in nonequilibrium learning
Xin-Ya Zhang, Chao Tang
Latent Geometry-Driven Network Automata for Complex Network Dismantling
Thomas Adler, Marco Grassia, Ziheng Liao, Giuseppe Mangioni, Carlo Vittorio Cannistraci
Morse-Seeded Coresets for Structure-Preserving Landmarking on kNN Graphs
Tirth Joshi
🏆 Best Poster Award
Robustness in sparse artificial neural networks trained with adaptive topology
Bendeguz Sulyok
Simulation based inference for MRI diffusion microstructure models
Ding Zhou, Yousef Yeganeh, Azade Farshad, Saad Jbabdi, Hossein Rafipoor, Nassir Navab
Spark: Modular Spiking Neural Networks
Mario Franco, Carlos Gershenson
Task complexity shapes internal representations and robustness in neural networks
Robert Jankowski, Filippo Radicchi, M. Angeles Serrano, Marian Boguña, Santo Fortunato