awesome-tensorial-neural-networks
github.com/tnbar/awesome-tensorial-neural-networks ↗A thoroughly investigated survey for tensorial neural networks.
Use this list with your AI agent
Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:
"Show me tensorial graph neural networks resources from awesome-tensorial-neural-networks"
Installation instructions →What's inside
Network compression via TNNs
- Baghershahi et al. "Efficient Relation-aware Neighborhood Aggregation in Graph Neural Networks via Tensor Decomposition". [linkTensorial Graph Neural Networks
Introducing a general knowledge graph encoder incorporating tensor decomposition in the aggregation function.
- Chen et al. "Matrix Product Operator Restricted Boltzmann Machines". [linkTensorial Restricted Boltzmann Machine
Proposing the matrix product operator RBM that utilizes a tensor network generalization of Mv/TvRBM.
- Denton et al. "Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation". [linkTensorial Convolutional Neural Networks
Speeding up the test-time evaluation of large convolutional networks via CP-decomposition.
- Garipov et al. "Ultimate tensorization: compressing convolutional and fc layers alike". [linkTensorial Convolutional Neural Networks
Compressing convolutional layers via Tensor Train format.
- Hayashi et al. "Einconv: Exploring Unexplored Tensor Network Decompositions for Convolutional Neural Networks". [linkTensorial Convolutional Neural Networks
Characterizing a decomposition class specific to CNNs by adopting a flexible graphical notation.
- Hua et al. "High-Order Pooling for Graph Neural Networks with Tensor Decomposition". [linkTensorial Graph Neural Networks
Proposing the highly expressive Tensorized Graph Neural Network (tGNN) to model high-order non-linear node interactions.
Information Fusion via TNNs
- Ben-Younes et al. "Mutan: Multimodal tucker fusion for visual question answering". [linkMultimodal Pooling-Based Methods
Proposing a multimodal tensor-based Tucker decomposition to efficiently parametrize bilinear interactions between visual and textual representations.
- Do et al. "Compact trilinear interaction for visual question answering". [linkMultimodal Pooling-Based Methods
Introducing a multimodal tensor-based PARALIND decomposition which efficiently parameterizes trilinear teraction between inputs.
- Fukui et al. "Multimodal compact bilinear pooling for visual question answering and visual grounding". [linkMultimodal Pooling-Based Methods
Proposing utilizing Multimodal Compact Bilinear pooling (MCB) to efficiently and expressively combine multimodal features.
- Hou et al. "Deep multimodal multilinear fusion with high-order polynomial pooling". [linkTensor Fusion Layer-Based Methods
Proposing a polynomial tensor pooling (PTP) block for integrating multimodal features by considering high-order moments.
- Kim et al. "Hadamard product for low-rank bilinear pooling". [linkMultimodal Pooling-Based Methods
Proposing low-rank bilinear pooling using Hadamard product for an efficient attention mechanism of multimodal learning.
- Liu et al. "Efficient low-rank multimodal fusion with modality-specific factors". [linkTensor Fusion Layer-Based Methods
Proposing the low-rank method, which performs multimodal fusion using low-rank tensors to improve efficiency.
Training Strategy
- Cheng et al. "A novel rank selection scheme in tensor ring decomposition based on reinforcement learning for deep neural networks". [linkRank Selection
Proposing a novel rank selection scheme, which is inspired by reinforcement learning, to automatically select ranks in recently studied tensor ring decomposition in each convolutional layer.
- Cole Hawkins and Zheng Zhang. "Bayesian tensorized neural networks with automatic rank selection". [linkRank Selection
Proposing approaches for posterior density calculation and maximum a posteriori (MAP) estimation for the end-to-end training of our tensorized neural network.
- Deng et al. "TIE: Energy-efficient tensor train-based inference engine for deep neural network". [linkHardware Training
Developing a computation-efficient inference scheme for TT-format DNN.
- Huang et al. "LTNN: An energy-efficient machine learning accelerator on 3D CMOS-RRAM for layer-wise tensorized neural network". [linkHardware Training
Mapping TNNs to a 3D CMOS-RRAM based accelerator with significant bandwidth boosting from vertical I/O connections.
- Kao et al. "Hardware Acceleration in Large-Scale Tensor Decomposition for Neural Network Compression". [linkHardware Training
Proposing an energy-efficient hardware accelerator that implements randomized CPD in large-scale tensors for neural network compression.
- Kim et al. "Compression of deep convolutional neural networks for fast and low power mobile applications". [linkRank Selection
Deriving an approximate rank by employing the Bayesian matrix factorization (BMF) to an unfolding weight tensor.
Quantum Circuit Simulation on TNNs
- Cheng et al. "Tree tensor networks for generative modeling". [linkQuantum Embedded Data Processing
Designing the tree tensor network to utilize the 2-dimensional prior of the natural images and develop sweeping learning and sampling algorithms.
- Cohen et al. "On the Expressive Power of Deep Learning: A Tensor Analysis". [linkConvolutional Arithmetic Circuits
Showing that a shallow network corresponds to CP (rank-1) decomposition, whereas a deep network corresponds to Hierarchical Tucker decomposition.
- Edwin Stoudenmire and David J. Schwab. "Supervised learning with tensor networks". [linkQuantum Embedded Data Processing
Introducing a framework for applying quantum-inspired tensor networks to image classification.
- Glasser et al. "Expressive power of tensor-network factorizations for probabilistic modeling". [linkQuantum Embedded Data Processing
Introducing locally purified states (LPS), a new factorization inspired by techniques for the simulation of quantum systems, with provably better expressive power than all other representations considered.
- Han et al. "Unsupervised generative modeling using matrix product states". [linkQuantum Embedded Data Processing
Proposing a generative model using matrix product states, which is a tensor network originally proposed for describing (particularly one-dimensional) entangled quantum states.
- Levine et al. "Deep Learning and Quantum Entanglement: Fundamental Connections with Implications to Network Design". [linkConvolutional Arithmetic Circuits
Showing an equivalence between the function realized by a deep convolutional arithmetic circuit (ConvAC) and a quantum many-body wave function.
Toolboxes
- ITensorQuantum Tensor Simulation
ITensor is a system for programming tensor network calculations with an interface modeled on tensor diagram notation, which allows users to focus on the connectivity of a tensor network without manually bookkeeping tensor indices.
- lambeqQuantum Tensor Simulation
Lambeq is a toolkit for quantum natural language processing.
- OSTDBasic Tensor Operation
Online Stochastic Tensor Decomposition for Background Subtraction in Multispectral Video Sequences.
- Scikit-TTBasic Tensor Operation
Scikit-TT provides a powerful TT class as well as different modules comprising solvers for algebraic problems, the automatic construction of tensor trains, and data-driven methods.
- T3FBasic Tensor Operation
T3F supports GPU execution, batch processing, automatic differentiation, and versatile functionality for the Riemannian optimization framework.
- TedNetDeep Model Implementation
TedNet implements 5 kinds of tensor decomposition (i.e., CANDECOMP/PARAFAC (CP), Block-Term Tucker (BTT), Tucker-2, Tensor Train (TT) and Tensor Ring (TR) on traditional deep neural layers.
Showing a sample of 89 resources. View the full list on GitHub →