Quantum Neural Network Compression

TL;DR

This paper introduces CompVQC, a novel framework for compressing quantum neural networks that reduces circuit depth and enhances robustness on noisy quantum devices, addressing unique challenges of quantum-specific compression.

Contribution

It presents the first systematic framework for quantum neural network compression, incorporating a novel ADMM-based algorithm and emphasizing the importance of compilation in the process.

Findings

Reduces quantum circuit depth by over 2.5% with less than 1% accuracy loss.

Outperforms existing methods in quantum neural network compression.

Improves robustness of QNNs on noisy near-term quantum devices.

Abstract

Model compression, such as pruning and quantization, has been widely applied to optimize neural networks on resource-limited classical devices. Recently, there are growing interest in variational quantum circuits (VQC), that is, a type of neural network on quantum computers (a.k.a., quantum neural networks). It is well known that the near-term quantum devices have high noise and limited resources (i.e., quantum bits, qubits); yet, how to compress quantum neural networks has not been thoroughly studied. One might think it is straightforward to apply the classical compression techniques to quantum scenarios. However, this paper reveals that there exist differences between the compression of quantum and classical neural networks. Based on our observations, we claim that the compilation/traspilation has to be involved in the compression process. On top of this, we propose the very first systematical framework, namely CompVQC, to compress quantum neural networks (QNNs).In CompVQC, the key component is a novel compression algorithm, which is based on the alternating direction method of multipliers (ADMM) approach. Experiments demonstrate the advantage of the CompVQC, reducing the circuit depth (almost over 2.5 %) with a negligible accuracy drop (<1%), which outperforms other competitors. Another promising truth is our CompVQC can indeed promote the robustness of the QNN on the near-term noisy quantum devices.