mlsanityData to 7 Oct 2026

Deep Tree Tensor Networks

arXiv 2502.09928 ↗First posted 14 Feb 2025cs.CV cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Originating in quantum physics, tensor networks (TNs) have been widely adopted as exponential machines and parametric decomposers for recognition tasks. Typical TN models, such as Matrix Product States (MPS), have not yet achieved successful application in natural image recognition. When employed, they primarily serve to compress parameters within pre-existing networks, thereby losing their distinctive capability to capture exponential-order feature interactions. This paper introduces a novel architecture named textitDeep Tree Tensor Network (DTTN), which captures 2L-order multiplicative interactions across features through multilinear operations, while essentially unfolding into a tree-like TN topology with the parameter-sharing property. DTTN is stacked with multiple antisymmetric interaction modules (AIMs), and this design facilitates efficient implementation. Furthermore, our theoretical analysis demonstrates the equivalence between quantum-inspired TN models and polynomial/multilinear networks under specific conditions. We posit that the DTTN could catalyze more interpretable research within this field. The proposed model is evaluated across multiple benchmarks and domains, demonstrating superior performance compared to both peer methods and state-of-the-art architectures. Our code is publicly available at https://github.com/NieCha/deeptreetensornetwork.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 45 of its 67 references that are in the map. First posted on arXiv 14 Feb 2025.

Builds on

45 of 67 references.

References · 45

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  6. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  7. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  8. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  9. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  10. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,051
  11. 2019Panoptic Feature Pyramid Networkscited by 644
  12. 2022Scientific Machine Learning through Physics-Informed Neural Networks: Where we are and What's nextcited by 603
33 more
  1. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 520
  2. 2019Attention Augmented Convolutional Networkscited by 363
  3. 2021DER: Dynamically Expandable Representation for Class Incremental Learningcited by 355
  4. 2021ResMLP: Feedforward networks for image classification with data-efficient trainingcited by 338
  5. 2020DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systemscited by 326
  6. 2018xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systemscited by 277
  7. 2019Understanding and Improving Layer Normalizationcited by 213
  8. 2018A2-Nets: Double Attention Networkscited by 136
  9. 2021CycleMLP: A MLP-like Architecture for Dense Predictioncited by 126
  10. 2016Tensor Ring Decompositioncited by 125
  11. 2021Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognitioncited by 103
  12. 2019FiBiNET: Combining Feature Importance and Bilinear feature Interaction for Click-Through Rate Predictioncited by 83
  13. 2021S2-MLP: Spatial-Shift MLP Architecture for Visioncited by 83
  14. 2022Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognitioncited by 81
  15. 2018Towards Quantum Machine Learning with Tensor Networkscited by 74
  16. 2021Hire-MLP: Vision MLP via Hierarchical Rearrangementcited by 66
  17. 2019Tree Tensor Networks for Generative Modelingcited by 63
  18. 2020Deep Polynomial Neural Networkscited by 63
  19. 2023Adaptive Frequency Filters As Efficient Global Token Mixerscited by 45
  20. 2017Machine Learning by Unitary Tensor Network of Hierarchical Tree Structurecited by 39
  21. 2020Supervised Learning with Projected Entangled Pair Statescited by 30
  22. 2022Adaptive Self-supervision Algorithms for Physics-informed Neural Networkscited by 24
  23. 2021Augmenting Deep Classifiers with Polynomial Neural Networkscited by 21
  24. 2020Tensor Networks for Medical Image Classificationcited by 20
  25. 2023Tensor networks for interpretable and efficient quantum-inspired machine learningcited by 16
  26. 2020A Multi-Scale Tensor Network Architecture for Classification and Regressioncited by 13
  27. 2023Regularization of polynomial networks for image recognitioncited by 13
  28. 2024Multilinear Operator Networkscited by 12
  29. 2020Residual Matrix Product State for Machine Learningcited by 9
  30. 2023Efficient tensor network simulation of IBM's largest quantum processorscited by 9
  31. 2021Multi-Tensor Network Representation for High-Order Tensor Completioncited by 2
  32. 2021Patch-based Medical Image Segmentation using Matrix Product State Tensor Networkscited by 2
  33. 2022STN: Scalable Tensorizing Networks via Structure-Aware Training and Adaptive Compressioncited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2025Trainable Quantum Neural Network for Multiclass Image Classification with the Power of Pre-trained Tree Tensor Networkscited by 0
  2. 2026Efficient Generative Modeling with Unitary Matrix Product States Using Riemannian Optimizationcited by 0
  3. 2026Tensor-Augmented Convolutional Neural Networks: Enhancing Expressivity with Generic Tensor Kernelscited by 0
  4. 2026Activation-Free Backbones for Image Recognition: Polynomial Alternatives within MetaFormer-Style Vision Modelscited by 0