Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Bulletin of the American Physical Society

Generative quantum models over tensor network architectures

Khadijeh Najafi, Ahmadreza Azizi, Carlos Fuertes, Miles Stoudenmire, Masoud Mohseni

Published Mar 6, 2020• 0 citations
OpenAlex

Related papers

Tensor Networks in Quantum Neural Network Architectures

K. Meenakshi, Rakhi Chauhan, Deepshikha Bhargava

Signals and communication technology•Jan 1, 2026•0 citations

From Probabilistic Graphical Models to Generalized Tensor Networks for Supervised Learning

Ivan Glasser, Nicola Pancotti, J. I. Cirac

Tensor networks have found a wide use in a variety of applications in physics and computer science, recently leading to both theoretical insights as well as practical algorithms in machine learning. In this work we explore the connection between tensor networks and probabilistic graphical models, and show that it motivates the definition of generalized tensor networks where information from a tensor can be copied and reused in other parts of the network. We discuss the relationship between generalized tensor network architectures used in quantum physics, such as string-bond states, and architectures commonly used in machine learning. We provide an algorithm to train these networks in a supervised-learning context and show that they overcome the limitations of regular tensor networks in higher dimensions, while keeping the computation efficient. A method to combine neural networks and tensor networks as part of a common deep learning architecture is also introduced. We benchmark our algorithm for several generalized tensor network architectures on the task of classifying images and sounds, and show that they outperform previously introduced tensor-network algorithms. The models we consider also have a natural implementation on a quantum computer and may guide the development of near-term quantum machine learning architectures.

arXiv:1806.05964•IEEE Access•Jan 1, 2020•135 citations

Tensor networks for quantum computing

A. V. Berezutskii, Minzhao Liu, Atithi Acharya +25 more

arXiv:2503.08626•Nature Reviews Physics•Jul 30, 2025•66 citations

TextTN: Probabilistic Encoding of Language on Tensor Network

Peng Zhang, Jing Zhang, Xindian Ma +3 more

As a novel model that bridges machine learning and quantum theory, tensor network (TN) has recently gained increasing attention and successful applications for processing natural images. However, for natural languages, it is unclear how to design a probabilistic encoding architecture to efficiently and accurately learn and classify texts based on TN. This paper proposes a general two-step scheme of text classification based on Tensor Network, which is named as TextTN. TextTN first encodes the word vectors in a probabilistic space by a generative TN (word-GTN), and then classifies a text sentence using a discriminative TN (sentence-DTN). Moreover, in sentence-DTN, its hyper-parameter (i.e., bond-dimension) can be analyzed and selected by the theoretical property of TextTN's expressive power. In experiments, our TextTN also obtains the state-of-the-art result on SST-5 sentiment classification task.

•May 4, 2021•4 citations

Comb Tensor Networks vs. Matrix Product States: Enhanced Efficiency in High-Dimensional Spaces

Danylo Kolesnyk, Yelyzaveta Vodovozova

Modern approaches to generative modeling of continuous data using tensor networks incorporate compression layers to capture the most meaningful features of high-dimensional inputs. These methods, however, rely on traditional Matrix Product States (MPS) architectures. Here, we demonstrate that beyond a certain threshold in data and bond dimensions, a comb-shaped tensor network architecture can yield more efficient contractions than a standard MPS. This finding suggests that for continuous and high-dimensional data distributions, transitioning from MPS to a comb tensor network representation can substantially reduce computational overhead while maintaining accuracy.

arXiv:2412.06857•Dec 8, 2024•1 citation

Scalable Quantum Molecular Generation via GPU-Accelerated Tensor-Network Simulation

Yu-Cheng Xiao, Jen-Yu Chang, Tzu-Ling Kuo +7 more

We propose Scalable Quantum Molecular Generation (SQMG), a variational quantum-circuit for sampling molecular graphs using chemical priors on atoms and bonds. SQMG assigns a fixed 3-qubit register to each heavy atom and reuses a single 2-qubit bond register to generate bonds sequentially, yielding an ''atom no-reuse, bond reuse'' architecture with linear qubit scaling. Measurement results are mapped to molecular graphs via lightweight classical decoding with structural constraints. In CUDA-Q, we benchmark the state-vector simulation (CPU/GPU) and the tensor-network simulation (GPU). At $N=8$ heavy atoms, the state-vector simulator (GPU) and the tensor-network simulator (GPU) achieve speeds of up to $4.5\times 10^{4}$ and $2.2\times 10^{3}$ over the state-vector (CPU) baseline, respectively. Crucially, tensor-network simulation extends exact simulation to $N=40$ heavy atoms, where state-vector methods become memory-limited. For training, Bayesian optimization outperforms COBYLA on a Validity$\times$Uniqueness objective, and the same architecture supports \textit{de novo} generation, scaffold decoration, and linker design. Overall, SQMG provides a scalable, reproducible testbed for evaluating accelerated tensor-network simulation and future quantum molecular generation algorithms.

quant-pharXiv:2604.13877•International Conference on Quantum Communications, Networking, and Computing (QCNC)•Apr 16, 2026•2 citations
Tensor networks have found a wide use in a variety of applications in physics and computer science, recently leading to both theoretical insights as well as practical algorithms in machine learning. In this work we explore the connection between tensor networks and probabilistic graphical models, and show that it motivates the definition of generalized tensor networks where information from a tensor can be copied and reused in other parts of the network. We discuss the relationship between generalized tensor network architectures used in quantum physics, such as string-bond states, and architectures commonly used in machine learning. We provide an algorithm to train these networks in a supervised-learning context and show that they overcome the limitations of regular tensor networks in higher dimensions, while keeping the computation efficient. A method to combine neural networks and tensor networks as part of a common deep learning architecture is also introduced. We benchmark our algorithm for several generalized tensor network architectures on the task of classifying images and sounds, and show that they outperform previously introduced tensor-network algorithms. The models we consider also have a natural implementation on a quantum computer and may guide the development of near-term quantum machine learning architectures.
As a novel model that bridges machine learning and quantum theory, tensor network (TN) has recently gained increasing attention and successful applications for processing natural images. However, for natural languages, it is unclear how to design a probabilistic encoding architecture to efficiently and accurately learn and classify texts based on TN. This paper proposes a general two-step scheme of text classification based on Tensor Network, which is named as TextTN. TextTN first encodes the word vectors in a probabilistic space by a generative TN (word-GTN), and then classifies a text sentence using a discriminative TN (sentence-DTN). Moreover, in sentence-DTN, its hyper-parameter (i.e., bond-dimension) can be analyzed and selected by the theoretical property of TextTN's expressive power. In experiments, our TextTN also obtains the state-of-the-art result on SST-5 sentiment classification task.
Modern approaches to generative modeling of continuous data using tensor networks incorporate compression layers to capture the most meaningful features of high-dimensional inputs. These methods, however, rely on traditional Matrix Product States (MPS) architectures. Here, we demonstrate that beyond a certain threshold in data and bond dimensions, a comb-shaped tensor network architecture can yield more efficient contractions than a standard MPS. This finding suggests that for continuous and high-dimensional data distributions, transitioning from MPS to a comb tensor network representation can substantially reduce computational overhead while maintaining accuracy.
We propose Scalable Quantum Molecular Generation (SQMG), a variational quantum-circuit for sampling molecular graphs using chemical priors on atoms and bonds. SQMG assigns a fixed 3-qubit register to each heavy atom and reuses a single 2-qubit bond register to generate bonds sequentially, yielding an ''atom no-reuse, bond reuse'' architecture with linear qubit scaling. Measurement results are mapped to molecular graphs via lightweight classical decoding with structural constraints. In CUDA-Q, we benchmark the state-vector simulation (CPU/GPU) and the tensor-network simulation (GPU). At N=8N=8N=8 heavy atoms, the state-vector simulator (GPU) and the tensor-network simulator (GPU) achieve speeds of up to 4.5×1044.5\times 10^{4}4.5×104 and 2.2×1032.2\times 10^{3}2.2×103 over the state-vector (CPU) baseline, respectively. Crucially, tensor-network simulation extends exact simulation to N=40N=40N=40 heavy atoms, where state-vector methods become memory-limited. For training, Bayesian optimization outperforms COBYLA on a Validity×\times×Uniqueness objective, and the same architecture supports \textit{de novo} generation, scaffold decoration, and linker design. Overall, SQMG provides a scalable, reproducible testbed for evaluating accelerated tensor-network simulation and future quantum molecular generation algorithms.