QiVC-Net: Quantum-Inspired Variational Convolutional Network, with Application to Biosignal Classification

2025-11-07

AI Summary

To address challenges in phonocardiogram (PCG) classification—including high noise levels, substantial inter-subject variability, and severe class imbalance—this paper proposes QiVC-Net, a quantum-inspired variational convolutional network. Its core innovation is a differentiable low-dimensional subspace rotation mechanism that dynamically transforms convolutional weights without introducing additional parameters, enabling structured uncertainty modeling while preserving geometric consistency in the parameter space. This mechanism integrates probabilistic inference with variational optimization, yielding a lightweight and robust QiVC convolutional layer embedded within an end-to-end architecture. Evaluated on two benchmark PhysioNet PCG datasets, QiVC-Net achieves state-of-the-art accuracies of 97.84% and 97.89%, respectively. The method significantly enhances robustness and generalization for biosignal classification, demonstrating superior performance over existing approaches in noisy, heterogeneous, and imbalanced clinical settings.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

This work introduces the quantum-inspired variational convolution (QiVC) framework, a novel learning paradigm that integrates principles of probabilistic inference, variational optimization, and quantum-inspired transformations within convolutional architectures. The central innovation of QiVC lies in its quantum-inspired rotated ensemble (QiRE) mechanism. QiRE performs differentiable low-dimensional subspace rotations of convolutional weights, analogously to quantum state evolution. This approach enables structured uncertainty modeling while preserving the intrinsic geometry of the parameter space, resulting in more expressive, stable, and uncertainty-aware representations. To demonstrate its practical potential, the concept is instantiated in a QiVC-based convolutional network (QiVC-Net) and evaluated in the context of biosignal classification, focusing on phonocardiogram (PCG) recordings, a challenging domain characterized by high noise, inter-subject variability, and often imbalanced data. The proposed QiVC-Net integrates an architecture in which the QiVC layer does not introduce additional parameters, instead performing an ensemble rotation of the convolutional weights through a structured mechanism ensuring robustness without added highly computational burden. Experiments on two benchmark datasets, PhysioNet CinC 2016 and PhysioNet CirCor DigiScope 2022, show that QiVC-Net achieves state-of-the-art performance, reaching accuracies of 97.84% and 97.89%, respectively. These findings highlight the versatility of the QiVC framework and its promise for advancing uncertainty-aware modeling in real-world biomedical signal analysis. The implementation of the QiVConv layer is openly available in GitHub.

Problem

• Develops quantum-inspired variational convolution for uncertainty-aware biosignal classification
• Addresses high noise and variability in phonocardiogram recordings analysis
• Enables robust modeling without adding computational burden or parameters

Innovation

• Quantum-inspired variational convolution framework for probabilistic inference
• Differentiable subspace rotations of convolutional weights
• Uncertainty-aware modeling without additional parameters