Analysis of quantum neural network performance via edge cases

TL;DR

This paper investigates how the internal symmetry of quantum neural networks affects their performance on graph classification tasks, revealing that symmetry plays a crucial role in their effectiveness.

Contribution

It introduces an analysis of quantum neural networks with different symmetry properties and their performance on structured graph data, challenging previous assumptions.

Findings

Symmetry influences quantum neural network performance

Certain graph structures reveal limitations of learned models

Quantum networks do not simply learn edge-based surrogate models

Abstract

We evaluate the particular performance of different quantum machine learning networks on a graph classification task. Quantum circuits with varying internal symmetry that completely, partially and not at all confer to the symmetry of the graph show different performance on the data set. The convergence results are inspected using a number of special graphs with particular structure. These are unlikely to occur in the training data and cover specific cases that refute the assumption that the quantum neural network learns simpler surrogate models based on the number of edges in the graph.