This repository provides a PyTorch implementation of the Quantum SVDD method presented in our 2024 paper ”A Parameter-Efficient Quantum Anomaly Detection Method on a Superconducting Quantum Processor”.
You can find a PDF of the A Parameter-Efficient Quantum Anomaly Detection Method on a Superconducting Quantum Processor paper at [http://].
If you use our work, please also cite the paper:
https://arxiv.org/abs/2412.16867
If you would like to get in touch, please contact maida.wang.24@ucl.ac.uk.
Quantum machine learning has gained attention for its potential to address computational challenges. However, whether those algorithms can effectively solve practical problems and outperform their classical counterparts, especially on current quantum hardware, remains a critical question. In this work, we propose a novel quantum machine learning method, called Quantum Support Vector Data Description (QSVDD), for practical anomaly detection, which aims to achieve both parameter efficiency and superior accuracy compared to classical models. Emulation results indicate that QSVDD demonstrates favourable recognition capabilities compared to classical baselines, achieving an average accuracy of over 90% on benchmarks with significantly fewer trainable parameters. Theoretical analysis confirms that QSVDD has a comparable expressivity to classical counterparts while requiring only a fraction of the parameters. Furthermore, we demonstrate the first implementation of a quantum machine learning method for anomaly detection on a superconducting quantum processor. Specifically, we achieve an accuracy of over 80% with only 16 parameters on the device, providing initial evidence of QSVDD's practical viability in the noisy intermediate-scale quantum era and highlighting its significant reduction in parameter requirements.
This code is written in Python 3.8 and requires the packages listed in requirements.txt.
Clone the repository to your local machine and directory of choice:
git clone https://github.com/MaidaWang/QSVDD.git
To run the code, we recommend setting up a virtual environment, e.g. using virtualenv or conda:
# pip install virtualenv
cd <path-to-Quantum-SVDD-directory>
virtualenv myenv
source myenv/bin/activate
pip install -r requirements.txt
cd <path-to-Quantum-SVDD-directory>
conda create --name myenv
source activate myenv
while read requirement; do conda install -n myenv --yes $requirement; done < requirements.txt
We currently have implemented the MNIST (http://yann.lecun.com/exdb/mnist/) and CIFAR-10 (https://www.cs.toronto.edu/~kriz/cifar.html) datasets and FashionMNIST datasets (https://github.com/zalandoresearch/fashion-mnist).
Have a look into main.py for all possible arguments and options.
cd <path-to-Quantum-SVDD-directory>
# activate virtual environment
source myenv/bin/activate # or 'source activate myenv' for conda
# create folder for experimental output
mkdir log/mnist_test
# change to source directory
cd src
# run simulation
python main.py mnist mnist_LeNet ../log/mnist_test ../data --objective one-class --lr 0.0001 --n_epochs 150 --lr_milestone 50 --batch_size 200 --weight_decay 0.5e-6 --pretrain True --ae_lr 0.0001 --ae_n_epochs 150 --ae_lr_milestone 50 --ae_batch_size 200 --ae_weight_decay 0.5e-3 --normal_class 1;
This example trains a Quantum SVDD model where digit 3 (--normal_class 3) is considered to be the normal class. Autoencoder
pretraining is used for parameter initialization.
cd <path-to-Quantum-SVDD-directory>
# activate virtual environment
source myenv/bin/activate # or 'source activate myenv' for conda
# create folder for experimental output
mkdir log/FashionMNIST_test
# change to source directory
cd src
# run simulation
python main.py FashionMNIST FashionMNIST_LeNet ../log/FashionMNIST_test ../data --objective one-class --lr 0.0001 --n_epochs 150 --lr_milestone 50 --batch_size 200 --weight_decay 0.5e-6 --pretrain True --ae_lr 0.0001 --ae_n_epochs 350 --ae_lr_milestone 250 --ae_batch_size 200 --ae_weight_decay 0.5e-6 --normal_class 3;
This example trains a Quantum SVDD model where cloth (--normal_class 3) is considered to be the normal class.
Autoencoder pretraining is used for parameter initialization.
cd <path-to-Quantum-SVDD-directory>
# activate virtual environment
source myenv/bin/activate # or 'source activate myenv' for conda
# create folder for experimental output
mkdir log/cifar10_test
# change to source directory
cd src
# run simulation
python main.py cifar10 cifar10_LeNet ../log/cifar10_test ../data --objective one-class --lr 0.0001 --n_epochs 150 --lr_milestone 50 --batch_size 200 --weight_decay 0.5e-6 --pretrain True --ae_lr 0.0001 --ae_n_epochs 350 --ae_lr_milestone 250 --ae_batch_size 200 --ae_weight_decay 0.5e-6 --normal_class 3;
This example trains a Quantum SVDD model where cats (--normal_class 3) are considered to be the normal class.
Autoencoder pretraining is used for parameter initialization.
We can run QSVDD on several different quantum devices, including superconducting processors and photonic processors. We also plan to implement this method on more chips in the future. If any academic organization has hardware and would like to run the algorithm on their hardware, they can contact the authors.
UCL