Noisy intermediate-scale quantum (NISQ) devices build the first generation of quantum computers. Quantum neural networks (QNNs) gained high interest as one of the few suitable quantum algorithms to run on these NISQ devices. Most of the QNNs exploit supervised training algorithms with quantum states in form of pairs to learn their underlying relation. However, only little attention has been given to unsupervised training algorithms despite interesting applications where the quantum data does not occur in pairs. Here we propose an approach to unsupervised learning and reproducing characteristics of any given set of quantum states. We build a generative adversarial model using two dissipative quantum neural networks (DQNNs), leading to the dissipative quantum generative adversarial network (DQGAN). The generator DQNN aims to produce quantum states similar to the training data while the discriminator DQNN aims to distinguish the generator's output from the training data. We find that training both parts in a competitive manner results in a well trained generative DQNN. We see our contribution as a proof of concept for using DQGANs to learn and extend unlabeled training sets.
Noisy intermediate-scale quantum (NISQ) devices build the first generation of quantum computers. Quantum neural networks (QNNs) gained high interest as one of the few suitable quantum algorithms to run on these NISQ devices. Most of the QNNs exploit supervised training algorithms with quantum states in form of pairs to learn their underlying relation. However, only little attention has been given to unsupervised training algorithms despite interesting applications where the quantum data does not occur in pairs. Here we propose an approach to unsupervised learning and reproducing characteristics of any given set of quantum states. We build a generative adversarial model using two dissipative quantum neural networks (DQNNs), leading to the dissipative quantum generative adversarial network (DQGAN). The generator DQNN aims to produce quantum states similar to the training data while the discriminator DQNN aims to distinguish the generator's output from the training data. We find that training both parts in a competitive manner results in a well trained generative DQNN. We see our contribution as a proof of concept for using DQGANs to learn and extend unlabeled training sets.
Quantum computing is one of the most exciting research areas of the last decades. At the same time, methods of machine learning have started to dominate science, industry and our everyday life. In this thesis we combine these two essential research topics of the 21st century and introduce dissipative quantum neural networks (DQNNs), which are designed for fully quantum learning tasks, are capable of universal quantum computation and have low memory requirements while training. We start the discussion of this interdisciplinary topic by introducing artificial neural networks, which are a very common tool in classical machine learning. Next, we give an overview on quantum information. Here we focus on quantum algorithms and circuits, which are used to implement quantum neural networks. Moreover, we explain the opportunities and challenges arising with today's quantum computers. The discussion of the architecture and training algorithm of the DQNNs forms the core of this work. These networks are optimised with training data pairs in form of input and desired output states and therefore can be used for characterising unknown or untrusted quantum devices. We not only demonstrate the generalisation behaviour of these quantum neural networks using classical simulations, but also implement them successfully on actual quantum computers. To understand the ultimate limits for such quantum machine learning methods, we discuss the quantum no free lunch theorem, which describes a bound on the probability that a quantum device, which can be modelled as a unitary process and is optimised with quantum examples, gives an incorrect output for a random input. This gives us a tool to review the learning behaviour of quantum neural networks in general and the DQNNs in particular. Moreover we expand the area of applications of DQNNs in two directions. In the first case, we include additional information beyond just the training data pairs: since quantum devices are always structured, the resulting data is always structured as well. We modify the DQNN's training algorithm such that knowledge about the graph-structure of the training data pairs is included in the training process and show that this can lead to better generalisation behaviour. Both the original DQNN and the DQNN including graph structure are trained with data pairs in order to characterise an underlying relation. However, in the second extension of the algorithm we aim to learn characteristics of a set of quantum states in order to extend it to quantum states which have similar properties. Therefore we build a generative adversarial model where two DQNNs, called the generator and discriminator, are trained in a competitive way. Overall, we observe that DQNNs can not only be trained efficiently but also, similar to their classical counterparts, modified to suit different applications.
Quantum machine learning holds the promise of harnessing quantum advantage to achieve speedup beyond classical algorithms. Concurrently, research indicates that dissipation can serve as an effective resource in quantum computation. In this paper, we introduce a novel dissipation-driven quantum generative adversarial network (DQGAN) architecture specifically tailored for generating classical data. Our DQGAN comprises two interacting networks: a generative network and a discriminative network, both constructed from qubits. The classical data is encoded into the input qubits of the input layer via strong tailored dissipation processes. This encoding scheme enables us to extract both the generated data and the classification results by measuring the observables of the steady state of the output qubits. The network coupling weight, i.e., the strength of the interaction Hamiltonian between layers, is iteratively updated during the training process. This training procedure closely resembles the training of conventional generative adversarial networks (GANs). By alternately updating the two networks, we foster adversarial learning until the equilibrium point is reached. Our preliminary numerical test on a simplified instance of the task substantiate the feasibility of our DQGAN model.
Quantum computing hardware is prone to decoherence and control errors, which can reduce entanglement and lead to mixed states. Practical quantum algorithms must extract insights from this noisy data. We test the hypothesis that a compact, circuit-based Quantum Generative Adversarial Network (QGAN) trained against a moving, noise-scheduled target can learn the action of a depolarizing channel and generate a family of noisy entangled two-qubit states that match state-level similarity and reproduce entanglement trends. We implement a compact QGAN in PennyLane with TensorFlow and train it against a moving target formed by Bell-pair states passed through a depolarizing channel whose strength is scheduled during training. The generator and discriminator are variational circuits; learning is assessed by state-level similarity (fidelity and trace distance) and by entanglement measures (concurrence and negativity). Our model learns the action of the noise channel and reproduces a family of noisy, entangled two-qubit states. Our results indicate that QGANs can capture hardware-relevant noise while preserving essential structure in the data. Such models can serve as error-aware state preparers, compact surrogates for device noise, and practical tools for quantum data augmentation and benchmarking on near-term quantum computing hardware. To our knowledge, this is the first systematic QGAN evaluation combining dynamic depolarizing noise schedule, finite-shot/readout-noisy training, and entanglement-aware metrics.
This paper investigates the application of Quantum Generative Adversarial Networks (QGANs) to data augmentation for machine learning. Traditional Generative Adversarial Networks (GANs) rely on classical neural networks, while this research explores leveraging quantum circuits as generators within a QGAN architecture. The core idea is to train a quantum generator to produce synthetic data samples, supplementing existing datasets with novel instances. The discriminator remains a classical neural network, tasked with distinguishing between real and generated data. We present a theoretical framework for this approach, outlining the mathematical formulation and key components. Specifically, we introduce the notation (x, s_1, s_2, ..., s_K) to represent data samples, generator states, and relevant parameters. The objective function for the QGAN is defined as minimizing the Jensen-Shannon divergence between the real and generated data distributions. The effectiveness of this approach is discussed, highlighting potential advantages and challenges. This work contributes to the emerging field of quantum machine learning and offers a novel strategy for improving the performance of machine learning models, particularly in scenarios with limited training data.
The advent of noisy intermediate-scale quantum (NISQ) devices offers crucial opportunities for the development of quantum algorithms. Here we evaluate the noise tolerance of two quantum neural network (QNN) architectures on IBM's NISQ devices, namely, dissipative QNN (DQNN) whose building-block perceptron is a completely positive map, and the quantum approximate optimization algorithm (QAOA). We compare these two approaches to learning an unknown unitary. While both networks succeed in this learning task, we find that a DQNN learns an unknown unitary more reliably than QAOA and is less susceptible to gate noise.
One of the most promising applications in the era of Noisy Intermediate-Scale Quantum (NISQ) computing is quantum generative adversarial networks (QGANs), which offer significant quantum advantages over classical machine learning in various domains. However, QGANs suffer from mode collapse and lack explicit control over the features of generated outputs. To overcome these limitations, we propose InfoQGAN, a novel quantum-classical hybrid generative adversarial network that integrates the principles of InfoGAN with a QGAN architecture. Our approach employs a variational quantum circuit for data generation, a classical discriminator, and a Mutual Information Neural Estimator (MINE) to explicitly optimize the mutual information between latent codes and generated samples. Numerical simulations on synthetic 2D distributions and Iris dataset augmentation demonstrate that InfoQGAN effectively mitigates mode collapse while achieving robust feature disentanglement in the quantum generator. By leveraging these advantages, InfoQGAN not only enhances training stability but also improves data augmentation performance through controlled feature generation. These results highlight the potential of InfoQGAN as a foundational approach for advancing quantum generative modeling in the NISQ era.