16 papers
A Tensor Network Framework for Interpretable Graph Analysis of Brain Networks
Domenico Pomarico, Giuseppe Magnifico, Alessandro Grecucci +10
Identifying robust neurobiological signatures of brain disorders requires machine learning approaches that combine predictive performance with interpretable representations of feat…
From Statistical to Structural Synergy: A Predictability Framework to Quantify the Effects due to High-Order Mechanisms
Yuri Antonacci, Chiara BarÃ, Laura Sparacino +3
High-order interactions are increasingly recognized as a hallmark of collective dynamics in complex systems. The relationship between high-order behaviours (HOBs), observed as syne…
Dissecting Spectral Granger Causality through Partial Information Decomposition
Luca Faes, Gorana Mijatovic, Riccardo Pernice +3
Granger causality (GC), a popular statistical method for the inference of directional influences between time series measured from a complex network, is sensitive to high-order (no…
The Representational Limit of Scalar Interactions: An Interventional Decomposition
Potito Aghilar, Sabino Roccotelli, Stanislao Fidanza +3
Signed pairwise interaction scores fundamentally conflate uniqueness (U), redundancy (R), and synergy (S). We prove this on a minimal 3-way XOR structural causal model: faithful in…
Investigating High-Order Behaviors in Multivariate Cardiovascular Interactions via Nonlinear Prediction and Information-Theoretic Tools
Chiara BarÃ, Yuri Antonacci, Laura Sparacino +4
Assessing the synergistic high-order behaviors (HOBs) that emerge from underlying structural mechanisms is crucial to characterize complex systems. This work leverages the combined…
Transfer entropy and O-information to detect grokking in tensor network multi-class classification problems
Domenico Pomarico, Roberto Cilli, Alfonso Monaco +10
Quantum-enhanced machine learning, encompassing both quantum algorithms and quantum-inspired classical methods such as tensor networks, offers promising tools for extracting struct…