Quantum Injection Pathways for Implicit Graph Neural Networks

• URL: http://arxiv.org/abs/2605.09226v1
• Date: Sat, 09 May 2026 23:51:46 GMT
• Title: Quantum Injection Pathways for Implicit Graph Neural Networks
• Abstract summary: Deep Equilibrium Models replace a stack of explicit layers with a single operator whose fixed point defines the output.<n>textitIndependent injection computes the quantum signal once per graph and forward fixed-point solve, and holds it fixed throughout the solve.<n>textitState-dependent injection instead recomputes the signal at every solver step and applies it to the current iteration.<n>textitBackbone-dependent injection likewise recomputes at every but applies the signal to the classical backbone's output evaluated at the current iteration.
• Score: 0.8826339811274068
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Deep Equilibrium Models (DEQs) replace a stack of explicit layers with a single operator whose fixed point defines the output, giving the expressive power of an arbitrarily deep network at the memory cost of a single layer. Quantum Deep Equilibrium Models (QDEQs) bring this idea to quantum machine learning, offering an alternative to Parameterized Quantum Circuits (PQCs), whose depth is limited by hardware coherence and trainability. Here, we introduce, formulate, and compare three ways of coupling a quantum signal to graph DEQs, differing in where the signal enters the fixed-point operator. \textit{Independent} injection computes the quantum signal once per graph and forward fixed-point solve, and holds it fixed throughout the solve. \textit{State-dependent} injection instead recomputes the signal at every solver step and applies it to the current iterate. \textit{Backbone-dependent} injection likewise recomputes at every iteration but applies the signal to the classical backbone's output evaluated at the current iterate. We establish contraction guarantees for each variant under explicit assumptions on the Lipschitz constants of the classical backbone and the quantum signal. On the TU Dortmund graph-classification benchmarks NCI1, PROTEINS, and MUTAG, independent injection achieves the best test accuracy while using fewer forward-solver iterations than both the classical equilibrium baseline and the two dependent variants.

Related papers

• Certifying Quantum Optimization and Circuit Cutting by Using Quantum-Classical Moment Duality [0.0]
  We establish a direct quantum-classical duality based on the degree-$2$ Sum-of-Squares semidefinite programming cone.<n>We show that the same moment matrix reveals the tensor-product structure of the underlying unitary circuit.<n>The framework is validated on Max-Cut instances for variational quantum algorithms and on random states for circuit cutting.
  arXiv  Detail & Related papers  (2026-06-19T12:48:36Z)
• Ancilla-Efficient QSAMPLE Preparation for Reversible Markov Chains [0.0]
  We present a new end-to-end framework requiring only one ancilla qubit in the working register.<n>The key technical ingredient is a selective phase compiler circuit using one ancilla qubit.<n>As a direct application, we apply the quantum algorithm to prepare a Gibbs QSAMPLE and obtain a rigorous complexity analysis.
  arXiv  Detail & Related papers  (2026-05-22T09:55:28Z)
• Iterative Optimization with Partial Convergence Guarantees on Neutral Atom Quantum Computers [0.0]
  Lp-Quts is a hybrid quantum-classical framework that integrates an NAQC sampler into a classical cutting-plane algorithm.<n>We show how Lp-Quts can be effectively embedded within classical optimization frameworks to deliver near-optimal solutions with reduced quantum resources.
  arXiv  Detail & Related papers  (2026-03-30T19:12:21Z)
• SpinGQE: A Generative Quantum Eigensolver for Spin Hamiltonians [42.007194397302825]
  Ground state search is central to quantum computing.<n>We present SpinGQE, an extension of the Generative Quantum Eigensolver framework to spin Hamiltonians.<n>We employ a transformer-based decoder to learn over quantum circuits that produce low-energy states.
  arXiv  Detail & Related papers  (2026-03-25T13:38:15Z)
• Continual Quantum Architecture Search with Tensor-Train Encoding: Theory and Applications to Signal Processing [68.35481158940401]
  CL-QAS is a continual quantum architecture search framework.<n>It mitigates challenges of costly encoding amplitude and forgetting in variational quantum circuits.<n>It achieves controllable robustness expressivity, sample-efficient generalization, and smooth convergence without barren plateaus.
  arXiv  Detail & Related papers  (2026-01-10T02:36:03Z)
• Quadratic Continuous Quantum Optimization [0.9023122463034333]
  Quantum annealers can solve QUBO problems efficiently but struggle with continuous optimization tasks like regression.<n>We introduce Quadratic Continuous Quantum Optimization (QCQO), an anytime algorithm that approximates solutions to unconstrained programs via a sequence of QUBO instances.
  arXiv  Detail & Related papers  (2025-12-31T10:08:41Z)
• Randomized Quantum Singular Value Transformation [18.660349597156266]
  We introduce the first randomized algorithms for Quantum Singular Value Transformation (QSVT)<n>Standard implementations of QSVT rely on block encodings of the Hamiltonian, requiring a logarithmic number of ancilla qubits, intricate multi-qubit control, and circuit depth scaling linearly with the number of Hamiltonian terms.<n>Our algorithms use only a single ancilla qubit and entirely avoid block encodings.
  arXiv  Detail & Related papers  (2025-10-08T10:14:15Z)
• QAMA: Scalable Quantum Annealing Multi-Head Attention Operator for Deep Learning [48.12231190677108]
  Quantum Annealing Multi-Head Attention (QAMA) is proposed, a novel drop-in operator that reformulates attention as an energy-based Hamiltonian optimization problem.<n>In this framework, token interactions are encoded into binary quadratic terms, and quantum annealing is employed to search for low-energy configurations.<n> Empirically, evaluation on both natural language and vision benchmarks shows that, across tasks, accuracy deviates by at most 2.7 points from standard multi-head attention.
  arXiv  Detail & Related papers  (2025-04-15T11:29:09Z)
• Extending Quantum Perceptrons: Rydberg Devices, Multi-Class Classification, and Error Tolerance [67.77677387243135]
  Quantum Neuromorphic Computing (QNC) merges quantum computation with neural computation to create scalable, noise-resilient algorithms for quantum machine learning (QML) At the core of QNC is the quantum perceptron (QP), which leverages the analog dynamics of interacting qubits to enable universal quantum computation.
  arXiv  Detail & Related papers  (2024-11-13T23:56:20Z)
• Projective Quantum Eigensolver with Generalized Operators [0.0]
  We develop a methodology for determining the generalized operators in terms of a closed form residual equations in the PQE framework. With the application on several molecular systems, we have demonstrated our ansatz achieves similar accuracy to the (disentangled) UCC with singles, doubles and triples.
  arXiv  Detail & Related papers  (2024-10-21T15:40:22Z)
• Distribution-Flexible Subset Quantization for Post-Quantizing Super-Resolution Networks [68.83451203841624]
  This paper introduces Distribution-Flexible Subset Quantization (DFSQ), a post-training quantization method for super-resolution networks. DFSQ conducts channel-wise normalization of the activations and applies distribution-flexible subset quantization (SQ) It achieves comparable performance to full-precision counterparts on 6- and 8-bit quantization, and incurs only a 0.1 dB PSNR drop on 4-bit quantization.
  arXiv  Detail & Related papers  (2023-05-10T04:19:11Z)
• Quantum Gate Generation in Two-Level Open Quantum Systems by Coherent and Incoherent Photons Found with Gradient Search [77.34726150561087]
  We consider an environment formed by incoherent photons as a resource for controlling open quantum systems via an incoherent control. We exploit a coherent control in the Hamiltonian and an incoherent control in the dissipator which induces the time-dependent decoherence rates.
  arXiv  Detail & Related papers  (2023-02-28T07:36:02Z)
• Simplifying a classical-quantum algorithm interpolation with quantum singular value transformations [0.0]
  We show that the scaling of $alpha$-QPE can be naturally and succinctly derived within framework of Quantum Singular Value Transformation. The better the approximation to the sign function, the fewer samples one needs to determine the sign accurately.
  arXiv  Detail & Related papers  (2022-07-29T17:57:03Z)

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.