Coupled Tensor-Tensor Completion Method with Applications in Drug Repurposing
Abstract
Many biomedical challenges can be posed as tensor completion problems where the observed entries of a multidimensional array (a tensor) are used to impute the missing values. In such settings, incorporating side information about the modes of the tensor, such as gene-gene similarity, can significantly enhance the solutions of the completion problem. Most existing tensor completion methods can only incorporate side information in the form of matrices. In this study, we introduce a novel framework to incorporate side information in the form of tensors. Our new approach, called Coupled Tensor-Tensor Completion (CTTC), leverages the hidden connections among multimodal tensors to improve tensor completion performance. In addition to practical utility, CTTC has theoretical foundations in distance metric learning and group theory. We derive an alternating algorithm to solve the CTTC optimization problem and establish its convergence to a stationary point. Finally, we show that CTTC outperforms state-of-the-art tensor completion methods at predicting drug effects. Results: Compared with other tensor completion methods, including HaLRTC, CTRC, Cell, and NTDDR, CTTC demonstrates superior run-time and RSE tensor completion accuracy on two benchmark datasets, DTD and LINCS.
Related
- Robust low-rank tensor completion via factorized weighted tensor schatten-p norm minimization
- Tensor Completion using Subspace Information
- The tubal Arnoldi method for tensor function approximation
- Dynamical Tensor Train Approximation for Wigner--Fokker--Planck Equation with Applications to Open Quantum Systems
- Randomized average block coordinate descent method with heavy-ball momentum for tensor least squares problem under the t-product
BibTeX
@misc{bagherian2026coupled,
title = {{Coupled Tensor-Tensor Completion Method with Applications in Drug Repurposing}},
author = {Maryam Bagherian and Albert Hung and Ivo Dinov and Joshua Welch},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.03190},
eprint = {2609.03190},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.03190},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Coupled Tensor-Tensor Completion Method with Applications in Drug Repurposing
AU - Maryam Bagherian
AU - Albert Hung
AU - Ivo Dinov
AU - Joshua Welch
PY - 2026
DA - 2026/09/02
PB - arXiv
DO - 10.48550/arxiv.2609.03190
UR - https://arxiv.org/abs/2609.03190
AB - Many biomedical challenges can be posed as tensor completion problems where the observed entries of a multidimensional array (a tensor) are used to impute the missing values. In such settings, incorporating side information about the modes of the tensor, such as gene-gene similarity, can significantly enhance the solutions of the completion problem. Most existing tensor completion methods can only incorporate side information in the form of matrices. In this study, we introduce a novel framework to incorporate side information in the form of tensors. Our new approach, called Coupled Tensor-Tensor Completion (CTTC), leverages the hidden connections among multimodal tensors to improve tensor completion performance. In addition to practical utility, CTTC has theoretical foundations in distance metric learning and group theory. We derive an alternating algorithm to solve the CTTC optimization problem and establish its convergence to a stationary point. Finally, we show that CTTC outperforms state-of-the-art tensor completion methods at predicting drug effects. Results: Compared with other tensor completion methods, including HaLRTC, CTRC, Cell, and NTDDR, CTTC demonstrates superior run-time and RSE tensor completion accuracy on two benchmark datasets, DTD and LINCS.
ER -