Quantum Simplicial Neural Networks

TL;DR

This paper introduces Quantum Simplicial Networks, a novel quantum deep learning model operating on simplicial complexes, which outperforms classical models in accuracy and efficiency on synthetic tasks by leveraging quantum mechanics for higher-order data representation.

Contribution

It presents the first quantum topological deep learning model that integrates quantum neural networks with simplicial complexes for higher-order data modeling.

Findings

QSNs outperform classical models in accuracy.

QSNs demonstrate improved efficiency.

Quantum topological models effectively capture higher-order structures.

Abstract

Graph Neural Networks (GNNs) excel at learning from graph-structured data but are limited to modeling pairwise interactions, insufficient for capturing higher-order relationships present in many real-world systems. Topological Deep Learning (TDL) has allowed for systematic modeling of hierarchical higher-order interactions by relying on combinatorial topological spaces such as simplicial complexes. In parallel, Quantum Neural Networks (QNNs) have been introduced to leverage quantum mechanics for enhanced computational and learning power. In this work, we present the first Quantum Topological Deep Learning Model: Quantum Simplicial Networks (QSNs), being QNNs operating on simplicial complexes. QSNs are a stack of Quantum Simplicial Layers, which are inspired by the Ising model to encode higher-order structures into quantum states. Experiments on synthetic classification tasks show that QSNs can outperform classical simplicial TDL models in accuracy and efficiency, demonstrating the potential of combining quantum computing with TDL for processing data on combinatorial topological spaces.