Research map / Learning theory and algorithms / Matrix and tensor methods
Fully-Connected Tensor Network Decomposition and Its Application to Higher-Order Tensor Completion
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use fully connected tensor factors instead of TT/TR factor connections | Tensor completion · Synthetic fourth- and fifth-order tensors under tested permutations | RSE | Helped |
| Use FCTN decomposition for completion | FCTN-TC · HSV, 95% MR | PSNR: 37.352 -> 43.256 | Helped |
| Use FCTN decomposition for completion | FCTN-TC · containe, 90% MR | PSNR: 32.512 -> 37.326 | Helped |
| Use FCTN decomposition for completion | FCTN-TC · Traffic flow, 40% slice missing | RSE: 0.061 -> 0.055 | Helped |
| Use FCTN decomposition for completion | FCTN-TC · news, 95% MR | PSNR: 25.092 -> 26.392 | Helped |
| Use FCTN decomposition for completion | FCTN-TC · elephants, 90% MR | PSNR: 28.648 -> 30.835 | Helped |
| Permute tensor modes | FCTN-TC versus TT-TC and TR-TC · Synthetic fourth- and fifth-order tensors | RSE | Mixed |
Closest papers by meaning
- Tensor Wheel Decomposition and Its Tensor Completion Application (NeurIPS 2022 · similarity 0.92)
- Fast Tensor Completion via Approximate Richardson Iteration (ICML 2025 · similarity 0.90)
- SVDinsTN: A Tensor Network Paradigm for Efficient Structure Search from Regularized Modeling Perspective (CVPR 2024 · similarity 0.89)
- Efficient Leverage Score Sampling for Tensor Train Decomposition (NeurIPS 2024 · similarity 0.88)
- Towards Multi-Mode Outlier Robust Tensor Ring Decomposition (AAAI 2024 · similarity 0.87)
- Convolutions and More as Einsum: A Tensor Network Perspective with Advances for Second-Order Methods (NeurIPS 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.