Amplitude-based Input Attribution in Quantum Learning via Integrated Gradients

• URL: http://arxiv.org/abs/2510.02497v1
• Date: Thu, 02 Oct 2025 19:00:41 GMT
• Title: Amplitude-based Input Attribution in Quantum Learning via Integrated Gradients
• Abstract summary: We introduce HATTRIQ, a framework to compute amplitude-based input attribution scores in circuit-based QML models.<n>We validate HATTRIQ on classification tasks across several datasets.
• Score: 4.946006905837039
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Quantum machine learning (QML) algorithms have demonstrated early promise across hardware platforms, but remain difficult to interpret due to the inherent opacity of quantum state evolution. Widely used classical interpretability methods, such as integrated gradients and surrogate-based sensitivity analysis, are not directly compatible with quantum circuits due to measurement collapse and the exponential complexity of simulating state evolution. In this work, we introduce HATTRIQ, a general-purpose framework to compute amplitude-based input attribution scores in circuit-based QML models. HATTRIQ supports the widely-used input amplitude embedding feature encoding scheme and uses a Hadamard test-based construction to compute input gradients directly on quantum hardware to generate provably faithful attributions. We validate HATTRIQ on classification tasks across several datasets (Bars and Stripes, MNIST, and FashionMNIST).

Related papers

• Hybrid HPC-Quantum Simulations: DFT-Quantum Embedding for Molecular Systems [0.9368753183086049]
  This work presents a hybrid DFT-Quantum Embedding framework integrating classical HPC-based DFT with a quantum electronic-structure solver.<n>We focus on noiseless quantum simulation to systematically evaluate accuracy, convergence, active-space dependence, computational cost, and HPC scalability without hardware noise.
  arXiv  Detail & Related papers  (2026-08-13T06:57:25Z)
• AQER: a scalable and efficient data loader for digital quantum computers [62.40228216126285]
  We develop AQER, a scalable AQL method that constructs the loading circuit by systematically reducing entanglement in target states.<n>We conduct systematic experiments to evaluate the effectiveness of AQER, using synthetic datasets, classical image and language datasets, and a quantum many-body state datasets with up to 50 qubits.
  arXiv  Detail & Related papers  (2026-02-02T14:39:42Z)
• Adversarially Robust Quantum Transfer Learning [1.3113458064027566]
  Quantum machine learning (QML) has emerged as a promising area of research for enhancing the performance of classical machine learning systems.<n>This chapter introduces a hybrid quantum-classical architecture that combines the advantages of quantum computing with transfer learning techniques to address high-resolution image classification.
  arXiv  Detail & Related papers  (2025-10-18T02:16:34Z)
• Quantum-Efficient Convolution through Sparse Matrix Encoding and Low-Depth Inner Product Circuits [0.0]
  We present a resource-efficient quantum algorithm that reformulates the convolution product as a structured matrix multiplication.<n>We construct a quantum framework wherein sparse input patches are prepared using optimized key-value QRAM state encoding.<n>Our architecture supports batched convolution across multiple filters using a generalized SWAP circuit.
  arXiv  Detail & Related papers  (2025-07-25T20:08:12Z)
• A Qubit-Efficient Hybrid Quantum Encoding Mechanism for Quantum Machine Learning [11.861417859173859]
  Quantum Principal Geodesic Analysis (qPGA) is a non-invertible method for dimensionality reduction and qubit-efficient encoding.<n>We show that qPGA preserves local structure more effectively than both quantum and hybrid autoencoders.<n>In downstream QML classification tasks, qPGA can achieve over 99% accuracy and F1-score on MNIST and Fashion-MNIST, outperforming quantum-dependent baselines.
  arXiv  Detail & Related papers  (2025-06-24T03:09:16Z)
• VQC-MLPNet: An Unconventional Hybrid Quantum-Classical Architecture for Scalable and Robust Quantum Machine Learning [60.996803677584424]
  Variational Quantum Circuits (VQCs) offer a novel pathway for quantum machine learning.<n>Their practical application is hindered by inherent limitations such as constrained linear expressivity, optimization challenges, and acute sensitivity to quantum hardware noise.<n>This work introduces VQC-MLPNet, a scalable and robust hybrid quantum-classical architecture designed to overcome these obstacles.
  arXiv  Detail & Related papers  (2025-06-12T01:38:15Z)
• Minimal Quantum Reservoirs with Hamiltonian Encoding [72.27323884094953]
  We investigate a minimal architecture for quantum reservoir computing based on Hamiltonian encoding.<n>This approach circumvents many of the experimental overheads typically associated with quantum machine learning.
  arXiv  Detail & Related papers  (2025-05-28T16:50:05Z)
• An Efficient Quantum Classifier Based on Hamiltonian Representations [50.467930253994155]
  Quantum machine learning (QML) is a discipline that seeks to transfer the advantages of quantum computing to data-driven tasks.<n>We propose an efficient approach that circumvents the costs associated with data encoding by mapping inputs to a finite set of Pauli strings.<n>We evaluate our approach on text and image classification tasks, against well-established classical and quantum models.
  arXiv  Detail & Related papers  (2025-04-13T11:49:53Z)
• Expressivity Limits of Quantum Reservoir Computing [0.0]
  We establish a formal connection to parametrized quantum circuit quantum machine learning (PQC-QML)<n>We analytically prove, and numerically corroborate, that in QRC the number of non-linear functions that can be generated from classical data is bounded linearly by the number of input encoding gates.<n>Our results challenge the common assumption that exponential Hilbert space scaling confers a corresponding computational advantage in QRC.
  arXiv  Detail & Related papers  (2025-01-26T13:43:03Z)
• Entanglement scaling in matrix product state representation of smooth functions and their shallow quantum circuit approximations [0.28917933888634956]
  matrix product state (MPS) methods emerged as the most promising approach for constructing shallow quantum circuits.<n>We derive rigorous expansions for the decay of entanglement across bonds in the MPS representation depending on the smoothness of the input function.<n>We construct an improved MPS-based algorithm yielding shallow and accurate encoding quantum circuits.
  arXiv  Detail & Related papers  (2024-12-06T17:31:35Z)
• Efficient Learning for Linear Properties of Bounded-Gate Quantum Circuits [62.46800898243033]
  Recent progress in quantum learning theory prompts a question: can linear properties of a large-qubit circuit be efficiently learned from measurement data generated by varying classical inputs?<n>We prove that the sample complexity scaling linearly in $d$ is required to achieve a small prediction error, while the corresponding computational complexity may scale exponentially in d.<n>We propose a kernel-based method leveraging classical shadows and truncated trigonometric expansions, enabling a controllable trade-off between prediction accuracy and computational overhead.
  arXiv  Detail & Related papers  (2024-08-22T08:21:28Z)
• Drastic Circuit Depth Reductions with Preserved Adversarial Robustness by Approximate Encoding for Quantum Machine Learning [0.5181797490530444]
  We implement methods for the efficient preparation of quantum states representing encoded image data using variational, genetic and matrix product state based algorithms. Results show that these methods can approximately prepare states to a level suitable for QML using circuits two orders of magnitude shallower than a standard state preparation implementation.
  arXiv  Detail & Related papers  (2023-09-18T01:49:36Z)
• TeD-Q: a tensor network enhanced distributed hybrid quantum machine learning framework [48.491303218786044]
  TeD-Q is an open-source software framework for quantum machine learning.<n>It seamlessly integrates classical machine learning libraries with quantum simulators.<n>It provides a graphical mode in which the quantum circuit and the training progress can be visualized in real-time.
  arXiv  Detail & Related papers  (2023-01-13T09:35:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.