Trainable Quantum Neural Network for Multiclass Image Classification with the Power of Pre-trained Tree Tensor Networks

Abstract

Tree tensor networks (TTNs) offer powerful models for image classification. While these TTN image classifiers already show excellent performance on classical hardware, embedding them into quantum neural networks (QNNs) may further improve the performance by leveraging quantum resources. However, embedding TTN classifiers into QNNs for multiclass classification remains challenging. Key obstacles are the highorder gate operations required for large bond dimensions and the mid-circuit postselection with exponentially low success rates necessary for the exact embedding. In this work, to address these challenges, we propose forest tensor network (FTN)-classifiers, which aggregate multiple small-bond-dimension TTNs. This allows us to handle multiclass classification without requiring large gates in the embedded circuits. We then remove the overhead of mid-circuit postselection by extending the adiabatic encoding framework to our setting and smoothly encode the FTN-classifiers into a quantum forest tensor network (qFTN)- classifiers. Numerical experiments on MNIST and CIFAR-10 demonstrate that we can successfully train FTN-classifiers and encode them into qFTN-classifiers, while maintaining or even improving the performance of the pre-trained FTN-classifiers. These results suggest that synergy between TTN classification models and QNNs can provide a robust and scalable framework for multiclass quantum-enhanced image classification.

11 pages, 12 figures, 2 tables. This work has been submitted to the IEEE for possible publication

References in corpus (43)

• A variational eigenvalue solver on a quantum processor
• Efficient classical simulation of slightly entangled quantum computations
• Barren plateaus in quantum neural network training landscapes
• A Practical Introduction to Tensor Networks: Matrix Product States and Projected Entangled Pair States
• Matrix Product States, Projected Entangled Pair States, and variational renormalization group methods for quantum spin systems
• Quantum Convolutional Neural Networks
• Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
• A class of quantum many-body states that can be efficiently simulated
• Hamiltonian Simulation by Qubitization
• Matrix Product States and Projected Entangled Pair States: Concepts, Symmetries, and Theorems
• Validating quantum computers using randomized model circuits
• Efficient Learning for Deep Quantum Neural Networks
• Classical simulation of quantum many-body systems with a tree tensor network
• Tensor networks for complex quantum systems
• Generalization in quantum machine learning from few training data
• Stochastic gradient descent on Riemannian manifolds
• The Density Matrix Renormalization Group in Chemistry and Molecular Physics: Recent Developments and New Challenges
• Towards Quantum Machine Learning with Tensor Networks
• Minimal Universal Two-qubit Quantum Circuits
• Opportunities and challenges for quantum-assisted machine learning in near-term quantum computers
• Unsupervised Generative Modeling Using Matrix Product States
• Efficient decomposition of quantum gates
• Beyond Barren Plateaus: Quantum Variational Algorithms Are Swamped With Traps
• Quantum Circuits for Isometries
• Encoding of Matrix Product States into Quantum Circuits of One- and Two-Qubit Gates
• Tree Tensor Networks for Generative Modeling
• Closing the "Quantum Supremacy" Gap: Achieving Real-Time Simulation of a Random Quantum Circuit Using a New Sunway Supercomputer
• Machine Learning by Unitary Tensor Network of Hierarchical Tree Structure
• Preparation of matrix product states with log-depth quantum circuits
• Learning Feynman Diagrams with Tensor Trains
• Synergy Between Quantum Circuits and Tensor Networks: Short-cutting the Race to Practical Quantum Advantage
• Efficient tensor network simulation of IBM's largest quantum processors
• The Presence and Absence of Barren Plateaus in Tensor-network Based Machine Learning
• Multi-class quantum classifiers with tensor network circuits for quantum phase recognition
• Tensor networks for quantum machine learning
• Quantum State Preparation of Normal Distributions using Matrix Product States
• Automatic structural optimization of tree tensor networks
• Classical versus Quantum: comparing Tensor Network-based Quantum Circuits on LHC data
• Tree tensor network classifiers for machine learning: from quantum-inspired to quantum-assisted
• Generative machine learning with tensor networks: benchmarks on near-term quantum computers
• Machine learning with tree tensor networks, CP rank constraints, and tensor dropout
• Tensor tree learns hidden relational structures in data to construct generative models
• Image Classification by Throwing Quantum Kitchen Sinks at Tensor Networks