Ziheng Liao — accepted AI-conference papers

2026

Latent Geometry-Driven Network Automata for Complex Network Dismantling

Thomas Adler, Marco Grassia, Ziheng Liao, Giuseppe Mangioni, Carlo Vittorio Cannistraci

ICLR 2026poster

Complex networks model the structure and function of critical technological, biological, and communication systems. Network dismantling, the targeted removal of nodes to fragment a network, is essential for analyzing and improving system robustness. Existing dismantling methods suffer from key limit…

Cited by 0 Source ↗Scholar ↗

2025

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 +1

NeurIPS 2025poster

This study aims to enlarge our current knowledge on the application of brain-inspired network science principles for training artificial neural networks (ANNs) with sparse connectivity. Dynamic sparse training (DST) emulates the synaptic turnover of real brain networks, reducing the computational de…

Cited by 0 Source ↗code ↗Scholar ↗