Pith. sign in

REVIEW 14 cited by

Tensor Networks Meet Neural Networks: A Survey and Future Perspectives

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2302.09019 v3 pith:7ZEPFCB3 submitted 2023-01-22 cs.LG

Maolin Wang , Yu Pan , Zenglin Xu , Guangxi Li , Xiangli Yang , Danilo Mandic , Andrzej Cichocki This is my paper
classification cs.LG
keywords networksneuraltnnsdataprocessingquantumsurveycombinations
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Tensor networks (TNs) and neural networks (NNs) are two fundamental data modeling approaches. TNs were introduced to solve the curse of dimensionality in large-scale tensors by converting an exponential number of dimensions to polynomial complexity. As a result, they have attracted significant attention in the fields of quantum physics and machine learning. Meanwhile, NNs have displayed exceptional performance in various applications, e.g., computer vision, natural language processing, and robotics research. Interestingly, although these two types of networks originate from different observations, they are inherently linked through the typical multilinearity structure underlying both TNs and NNs, thereby motivating a significant number of developments regarding combinations of TNs and NNs. In this paper, we refer to these combinations as tensorial neural networks~(TNNs) and present an introduction to TNNs from both data processing and model architecture perspectives. From the data perspective, we explore the capabilities of TNNs in multi-source fusion, multimodal pooling, data compression, multi-task training, and quantum data processing. From the model perspective, we examine TNNs' integration with various architectures, including Convolutional Neural Networks, Recurrent Neural Networks, Graph Neural Networks, Transformers, Large Language Models, and Quantum Neural Networks. Furthermore, this survey also explores methods for improving TNNs, examines flexible toolboxes for implementing TNNs, and documents TNN development while highlighting potential future directions. To the best of our knowledge, this is the first comprehensive survey that bridges the connections among NNs and TNs. We provide a curated list of TNNs at https://github.com/tnbar/awesome-tensorial-neural-networks.

Discussion (0). Sign in to comment.

Forward citations

Cited by 14 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. A fast sum-of-Gaussians algorithm for the high-dimensional fractional Fokker-Planck equation

    math.NA 2026-06 conditional novelty 7.0 of 10

    A sum-of-Gaussians approximation to the Fourier multiplier of the FFPE fundamental solution yields an O(M d N) separated representation that works in dimensions up to 10^5 with logarithmic growth in M for fixed accuracy.

  2. Classical Neural Networks on Quantum Devices via Tensor Network Disentanglers: A Case Study in Image Classification

    quant-ph 2025-09 unverdicted novelty 7.0 of 10

    A hybrid classical-quantum scheme compresses and disentangles bottleneck layers of pre-trained neural networks into MPO form for execution on quantum devices, validated via proof-of-concept on MNIST and CIFAR-10 image...

  3. Derivation of Runge--Kutta Order Conditions via Functional Tree Tensor Networks

    math.NA 2025-04 unverdicted novelty 7.0 of 10

    A functional tree tensor network framework derives Runge-Kutta order conditions by direct comparison of tensor-structured Taylor expansions for exact and numerical solutions.

  4. Automatically Differentiable Nonlinear Tensor Networks (ADNTNs) for Exponential Parameter Compression of Deep Neural Networks

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    ADNTNs compress DNN weights by 2000x-77000x per layer on AlexNet and VGG-16 using nonlinear tensor network cores trained with reverse-mode AD, often matching or exceeding baseline accuracy.

  5. T-GINEE: A Tensor-Based Multilayer Graph Representation Learning

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    T-GINEE combines CP tensor decomposition with a generalized estimating equation framework and task-specific loss to explicitly model inter-layer correlations in multilayer graphs while providing consistency and asympt...

  6. KromHC: Manifold-Constrained Hyper-Connections with Kronecker-Product Residual Matrices

    cs.CL 2026-01 conditional novelty 6.0 of 10

    KromHC uses Kronecker products of small doubly stochastic matrices to make Hyper-Connection residual matrices exactly balanced with O(n^2C) parameters, and matches or beats prior variants on small LLM pretraining runs.

  7. Neuralized Fermionic Tensor Networks for Quantum Many-Body Systems

    cond-mat.dis-nn 2025-06 unverdicted novelty 6.0 of 10

    NN-fTNS enhance fermionic tensor networks with neural parametrization to improve expressivity and achieve order-of-magnitude better energies than pure fTNS on Hubbard models while maintaining linear scaling.

  8. Hybrid between biologically and quantum-inspired many-body states

    cond-mat.str-el 2025-06 conditional novelty 6.0 of 10

    A perceptrain-based variational ansatz achieves relative ground-state energy accuracy of 10^{-5} (VMC) to 10^{-6} (GFMC) on a 10x10 transverse-field Ising model with 1/r^6 interactions using ranks of only 2-5.

  9. Automatically Differentiable Nonlinear Tensor Networks (ADNTNs) for Exponential Parameter Compression of Deep Neural Networks

    cs.LG 2026-05 conditional novelty 5.5 of 10

    Hierarchical nonlinear tensor networks generate dense, conv, and attention weights from few cores, yielding extreme per-layer compression with competitive CIFAR-10 accuracy on VGG-16.

  10. Tensor-Augmented Convolutional Neural Networks: Enhancing Expressivity with Generic Tensor Kernels

    cs.CV 2026-04 unverdicted novelty 5.0 of 10

    A two-layer tensor-augmented CNN reaches 93.7% test accuracy on Fashion-MNIST, matching or exceeding deeper models like VGG-16 and GoogLeNet by using tensors for richer expressivity.

  11. Entanglement is Half the Story: Post-Selection vs. Partial Traces

    quant-ph 2026-05 unverdicted novelty 4.0 of 10

    A hybrid tensor network framework interpolates between classical and quantum models via controllable post-selection, with a trainable hyperparameter that complements bond dimension to enhance quantum machine learning.

  12. When AI meets quantum information: A comprehensive review

    quant-ph 2026-07 unverdicted novelty 2.0 of 10

    A comprehensive review organizing progress at the AI-quantum information intersection from both directions.

  13. Quantum-inspired tensor networks in machine learning models

    cs.LG 2026-04 unverdicted novelty 2.0 of 10

    Tensor networks developed for quantum states are reviewed as tools for machine learning models, with assessment of their potential computational, explanatory, and privacy advantages alongside remaining challenges.

  14. A review of quantum machine learning and quantum-inspired applied methods to computational fluid dynamics

    quant-ph 2025-10 unverdicted novelty 2.0 of 10

    A survey of variational quantum algorithms, quantum neural networks, and tensor networks for addressing scalability challenges in computational fluid dynamics.

Pith tools