mlsanityData to 7 Oct 2026

Wide Compression: Tensor Ring Nets

arXiv 1802.09052 ↗First posted 25 Feb 2018cs.LG cs.CV stat.MLcited by 50

Not on the map. Why?

Abstract (arXiv)

Deep neural networks have demonstrated state-of-the-art performance in a variety of real-world applications. In order to obtain performance gains, these networks have grown larger and deeper, containing millions or even billions of parameters and over a thousand layers. The trade-off is that these large architectures require an enormous amount of memory, storage, and computation, thus limiting their usability. Inspired by the recent tensor ring factorization, we introduce Tensor Ring Networks (TR-Nets), which significantly compress both the fully connected layers and the convolutional layers of deep neural networks. Our results show that our TR-Nets approach is able to compress LeNet-5 by 11× without losing accuracy, and can compress the state-of-the-art Wide ResNet by 243× with only 2.3% degradation in Cifar10 image classification. Overall, this compression scheme shows promise in scientific computing and deep learning, especially for emerging resource-constrained devices such as smartphones, wearables, and IoT devices.

Key facts. Cited by 50 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 12; 2022: 15; 2023: 9; 2024: 7; 2025: 7.

50 papers.

Sort:

  1. 2021TT-Rec: Tensor Train Compression for Deep Learning Recommendation Modelscited by 58
  2. 2021Towards Efficient Tensor Decomposition-Based DNN Model Compression with Optimization Frameworkcited by 52
  3. 2024Automated Federated Pipeline for Parameter-Efficient Fine-Tuning of Large Language Modelscited by 49
  4. 2022The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural Networkscited by 41
  5. 2023Tensor Networks Meet Neural Networks: A Survey and Future Perspectivescited by 29
  6. 2021Scaling Up Exact Neural Network Compression by ReLU Stabilitycited by 19
  7. 2022Parallel Successive Learning for Dynamic Distributed Model Training over Heterogeneous Wireless Networkscited by 18
  8. 2023Tensor networks for interpretable and efficient quantum-inspired machine learningcited by 16
  9. 2021Convolutional Neural Network Compression through Generalized Kronecker Product Decompositioncited by 14
  10. 2024ELRT: Efficient Low-Rank Training for Compact Convolutional Neural Networkscited by 11
  11. 2021Joint Matrix Decomposition for Deep Convolutional Neural Networks Compressioncited by 10
  12. 2022Towards Practical Control of Singular Values of Convolutional Layerscited by 9
38 more
  1. 2022A Unified Weight Initialization Paradigm for Tensorial Convolutional Neural Networkscited by 8
  2. 2022TT-NF: Tensor Train Neural Fieldscited by 7
  3. 2021Spectral Tensor Train Parameterization of Deep Learning Layerscited by 6
  4. 2022Nimble GNN Embedding with Tensor-Train Decompositioncited by 6
  5. 2025LaX: Boosting Low-Rank Training of Foundation Models via Latent Crossingcited by 6
  6. 2023Low Rank Optimization for Efficient Deep Learning: Making A Balance between Compact Architecture and Fast Trainingcited by 5
  7. 2022FAMLP: A Frequency-Aware MLP-Like Architecture For Domain Generalizationcited by 4
  8. 2022Interaction Decompositions for Tensor Network Regressioncited by 4
  9. 2022CSTAR: Towards Compact and STructured Deep Neural Networks with Adversarial Robustnesscited by 4
  10. 2024Edge AI: Evaluation of Model Compression Techniques for Convolutional Neural Networkscited by 4
  11. 2025A Survey of Link Prediction in N-ary Knowledge Graphscited by 4
  12. 2021Tensor Yard: One-Shot Algorithm of Hardware-Friendly Tensor-Train Decomposition for Convolutional Neural Networkscited by 3
  13. 2021Semi-tensor Product-based TensorDecomposition for Neural Network Compressioncited by 3
  14. 2022Classical Simulation of Variational Quantum Classifiers using Tensor Ringscited by 3
  15. 2022How to Train Unstable Looped Tensor Networkcited by 3
  16. 2025Transformed Low-rank Adaptation via Tensor Decomposition and Its Applications to Text-to-image Modelscited by 3
  17. 2025Tensorization is a powerful but underexplored tool for compression and interpretability of neural networkscited by 3
  18. 2024Scalable Bayesian Tensor Ring Factorization for Multiway Data Analysiscited by 2
  19. 2021Lower and Upper Bounds on the VC-Dimension of Tensor Network Modelscited by 1
  20. 2021Learning Circular Hidden Quantum Markov Models: A Tensor Network Approachcited by 1
  21. 2022STN: Scalable Tensorizing Networks via Structure-Aware Training and Adaptive Compressioncited by 1
  22. 2023Compressive Sensing with Tensorized Autoencodercited by 1
  23. 2023Tensorized Hypergraph Neural Networkscited by 1
  24. 2023Tensor Ring Optimized Quantum-Enhanced Tensor Neural Networkscited by 1
  25. 2024conv_einsum: A Framework for Representation and Fast Evaluation of Multilinear Operations in Convolutional Tensorial Neural Networkscited by 1
  26. 2021Reconstructing Pruned Filters using Cheap Spatial Transformationscited by 0
  27. 2021Nonlinear Tensor Ring Networkcited by 0
  28. 2022Tensor Shape Search for Optimum Data Compressioncited by 0
  29. 2022SeKron: A Decomposition Method Supporting Many Factorization Structurescited by 0
  30. 2022Training Lightweight Graph Convolutional Networks with Phase-field Modelscited by 0
  31. 2023Review of compressed embedding layers and their applications for recommender systemscited by 0
  32. 2023Noisy Tensor Ring approximation for computing gradients of Variational Quantum Eigensolver for Combinatorial Optimizationcited by 0
  33. 2023Hyperspectral Image Fusion via Logarithmic Low-rank Tensor Ring Decompositioncited by 0
  34. 2024Reduced storage direct tensor ring decomposition for convolutional neural networks compressioncited by 0
  35. 2024Convolutional Neural Network Compression Based on Low-Rank Decompositioncited by 0
  36. 2025DNAD: Differentiable Neural Architecture Distillationcited by 0
  37. 2025Remote Sensing Image Classification with Decoupled Knowledge Distillationcited by 0
  38. 2025Unpacking the Implicit Norm Dynamics of Sharpness-Aware Minimization in Tensorized Modelscited by 0