Abstract Due to the beyond-classical capability of quantum computing, quantum machine learning is applied independently or embedded in classical models for decision making, especially in the field of finance. Fairness and other ethical issues are often one of the main concerns in decision making. In this work, we define a formal framework for the fairness verification and analysis of quantum machine learning decision models, where we adopt one of the most popular notions of fairness in the literature based on the intuition—any two similar individuals must be treated similarly and are thus unbiased. We show that quantum noise can improve fairness and develop an algorithm to check whether a (noisy) quantum machine learning model is fair. In particular, this algorithm can find bias kernels of quantum data (encoding individuals) during checking. These bias kernels generate infinitely many bias pairs for investigating the unfairness of the model. Our algorithm is designed based on a highly efficient data structure—Tensor Networks—and implemented on Google’s TensorFlow Quantum. The utility and effectiveness of our algorithm are confirmed by the experimental results, including income prediction and credit scoring on real-world data, for a class of random (noisy) quantum decision models with 27 qubits ( $$2^{27}$$ 227 -dimensional state space) tripling ( $$2^{18}$$ 218 times more than) that of the state-of-the-art algorithms for verifying quantum machine learning models.
Abstract Due to the beyond-classical capability of quantum computing, quantum machine learning is applied independently or embedded in classical models for decision making, especially in the field of finance. Fairness and other ethical issues are often one of the main concerns in decision making. In this work, we define a formal framework for the fairness verification and analysis of quantum machine learning decision models, where we adopt one of the most popular notions of fairness in the literature based on the intuition—any two similar individuals must be treated similarly and are thus unbiased. We show that quantum noise can improve fairness and develop an algorithm to check whether a (noisy) quantum machine learning model is fair. In particular, this algorithm can find bias kernels of quantum data (encoding individuals) during checking. These bias kernels generate infinitely many bias pairs for investigating the unfairness of the model. Our algorithm is designed based on a highly efficient data structure—Tensor Networks—and implemented on Google’s TensorFlow Quantum. The utility and effectiveness of our algorithm are confirmed by the experimental results, including income prediction and credit scoring on real-world data, for a class of random (noisy) quantum decision models with 27 qubits ( 227 227 -dimensional state space) tripling ( 218 218 times more than) that of the state-of-the-art algorithms for verifying quantum machine learning models.
Abstract Several important models of machine learning algorithms have been successfully generalized to the quantum world, with potential speedup to training classical classifiers and applications to data analytics in quantum physics that can be implemented on the near future quantum computers. However, quantum noise is a major obstacle to the practical implementation of quantum machine learning. In this work, we define a formal framework for the robustness verification and analysis of quantum machine learning algorithms against noises. A robust bound is derived and an algorithm is developed to check whether or not a quantum machine learning algorithm is robust with respect to quantum training data. In particular, this algorithm can find adversarial examples during checking. Our approach is implemented on Google’s TensorFlow Quantum and can verify the robustness of quantum machine learning algorithms with respect to a small disturbance of noises, derived from the surrounding environment. The effectiveness of our robust bound and algorithm is confirmed by the experimental results, including quantum bits classification as the “Hello World” example, quantum phase recognition and cluster excitation detection from real world intractable physical problems, and the classification of MNIST from the classical world.
Quantum algorithms for solving a wide range of practical problems have been proposed in the last ten years, such as data search and analysis, product recommendation, and credit scoring. The concern about privacy and other ethical issues in quantum computing naturally rises up. In this paper, we define a formal framework for detecting violations of differential privacy for quantum algorithms. A detection algorithm is developed to verify whether a (noisy) quantum algorithm is differentially private and automatically generates bugging information when the violation of differential privacy is reported. The information consists of a pair of quantum states that violate the privacy, to illustrate the cause of the violation. Our algorithm is equipped with Tensor Networks, a highly efficient data structure, and executed both on TensorFlow Quantum and TorchQuantum which are the quantum extensions of famous machine learning platforms - TensorFlow and PyTorch, respectively. The effectiveness and efficiency of our algorithm are confirmed by the experimental results of almost all types of quantum algorithms already implemented on realistic quantum computers, including quantum supremacy algorithms (beyond the capability of classical algorithms), quantum machine learning models, quantum approximate optimization algorithms, and variational quantum eigensolvers with up to 21 quantum bits.
Machine Learning (ML) algorithms in real-world applications have created an enormous and significant impact in terms of accuracy, efficiency and reliability. However, maintaining an appropriate bias in these algorithms seems to be a rigorous challenge to ensure fair and precise results obtained from decision making models. Various ML algorithms like Fairness Representation Learning, Adversarial Debiasing and Equalized Odds Post-Processing exist to mitigate bias but due to their computational limitations they lack the ability to do so which can have an adverse impact in sensitive sectors like finance and healthcare. Hence quantum algorithms arise with their promising features that can improve model performance with enhanced accuracy and fairness. In this study, we explore quantum approaches like Grover’s search algorithm and analyse the performance using different metrics. A comparative study of classical machine learning algorithms against quantum algorithms is done on adult income dataset. The results display a significant drop in Statistical Parity Difference (SPD) from 0.5173 (Baseline) to 0.4956 (Quantum) which indicates that the model is now less biased and fair predictions are done by the model. In future, hybrid quantum-machine learning techniques will play a key role in mitigation framework and general ML real-world applications.
Artificial Intelligence has significantly improved the efficiency of modern recruitment systems. Despite these advances, classical machine learning algorithms often perpetuate bias towards underrepresented groups, particularly in the context of imbalanced datasets. This study investigates whether Quantum Machine Learning (QML), through properties such as superposition and entanglement, can enhance fairness over classical methods. A rigorous system of comparative benchmarking, the Quantum-Fairness Recruitment Engine (Q-FRE), was designed to evaluate six architectures, with three classical (Logistic Regression, SVM, KNN) and three quantum (QSVM, VQC, QNN)-based machine learning algorithms, using real HR data (n=1,470). The results indicate a notable divergence between classical and quantum variational architectures. Classical models were highly accurate (84.7%), but had disastrous fairness errors, where 0% of minority high-performers were identified. This failure was repeated by Quantum SVM. On the other hand, the Variational Quantum Classifier (VQC) and Quantum Neural Network (QNN) were able to identify 29% of minority high-performers with a Disparate Impact Ratio of 0.82, which is legal for fairness. This research demonstrates empirical evidence of a quantifiable Fairness-Accuracy Trade-off: to gain a 29% increase in minority inclusion required a 16% sacrifice of overall accuracy. The results indicate that parameterized quantum circuits provide a possible, though computationally costly, route toward for achieving regulatory compliance in automated hiring.
Quantum Machine Learning represents a paradigm shift at the intersection of Quantum Computing and Machine Learning, leveraging quantum phenomena such as superposition, entanglement, and quantum parallelism to address the limitations of classical approaches in processing high-dimensional and large-scale datasets. This survey provides a comprehensive analysis of Quantum Machine Learning, detailing foundational concepts, algorithmic advancements, and their applications across domains such as healthcare, finance, and quantum chemistry. Key techniques, including Quantum Support Vector Machine, Quantum Neural Network, Quantum Decision Trees, and hybrid quantum-classical models, are explored with a focus on their theoretical foundations, computational benefits, and comparative performance against classical counterparts. While the potential for exponential speedups and enhanced efficiency is evident, the field faces significant challenges, including hardware constraints, noise, and limited qubit coherence in the current era of Noisy Intermediate-Scale Quantum devices. Emerging solutions, such as error mitigation techniques, hybrid frameworks, and advancements in quantum hardware, are discussed as critical enablers for scalable and fault-tolerant Quantum Machine Learning systems. By synthesizing state-of-the-art developments and identifying research gaps, this survey aims to provide a foundational resource for advancing Quantum Machine Learning toward practical, real-world applications in tackling computationally intensive problems.
Several important models of machine learning algorithms have been successfully generalized to the quantum world, with potential applications to data analytics in quantum physics that can be implemented on the near future quantum computers. However, noise and decoherence are two major obstacles to the practical implementation of quantum machine learning. In this work, we introduce a general framework for the robustness analysis of quantum machine learning algorithms against noise and decoherence. We argue that fidelity is the only pick of measuring the robustness. A robust bound is derived and an algorithm is developed to check whether or not a quantum machine learning algorithm is robust with respect to the training data. In particular, this algorithm can help to defense attacks and improve the accuracy as it can identify useful new training data during checking. The effectiveness of our robust bound and algorithm is confirmed by the case study of quantum phase recognition. Furthermore, this experiment demonstrates a trade-off between the accuracy of quantum machine learning algorithms and their robustness.