Huan Guo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Huan Guo has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Shirong Li
College of Mathematics and Statistics, Kashi University, Kashi 844000, China
2 shared publications - Maliyamuguli Maimaiti
College of Mathematics and Statistics, Kashi University, Kashi 844008, China
1 shared publication - Shaoyong Lai
School of Mathematics, Southwestern University of Finance and Economics, Chengdu 611130, China
1 shared publication - Yuekai Liu
College of Mathematics and Statistics, Kashi University, Kashi 844000, China
1 shared publication
Latest Publications
- Open Access
- 5 November 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (21) , 4049
Low-Rank CP Tensor Decomposition for Lightweight Image Super-Resolution
Deep convolutional neural networks have substantially advanced single-image super-resolution, or SR, but their high parameter counts and computational redundancy hinder deployment on resource-constrained edge devices. Most existing compression methods apply pruning or low-rank truncation as a post hoc step after training. This “train-then-compress” pipeline is reported in the compression literature to disrupt the spectral coherence of the learned feature manifold and to require costly fine-tuning to restore fidelity. We study an alternative, training-time approach that re-parameterizes the convolutional kernel with CANDECOMP/PARAFAC (CP) decomposition into three low-rank sublayers, optimizing directly on a rank-constrained manifold rather than compressing after convergence. We interpret the forward pass as a heuristic realization, rather than a formal equivalence, of a proximal gradient-descent–ADMM update for a tensor nuclear-norm-regularized problem, which motivates the design and its hyperparameters without invoking expensive singular value decompositions. An analysis of parameter complexity and gradient flow justifies the choice of CP over Tucker and tensor-train decompositions. Experiments on DIV2K, Kodak24, BSD100, and Set12 show that the CP module yields a M-parameter lightweight model at parity with a same-budget reduced residual baseline (at most dB difference on every test set), sacrificing roughly half a decibel relative to a larger residual baseline. Applied to a large-capacity SR backbone, the same module removes of the parameters, from M to M, at a PSNR cost of only – dB. These results indicate that training-time CP decomposition is a simple and parameter-efficient route to compact SR models in the extreme-compression regime.- 5 November 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (21) , 4049
Open AccessLow-Rank CP Tensor Decomposition for Lightweight Image Super-Resolution
Deep convolutional neural networks have substantially advanced single-image super-resolution, or SR, but their high parameter counts and computational redundancy hinder deployment on resource-constrained edge devices. Most existing compression methods apply pruning or low-rank truncation as a post hoc step after training. This “train-then-compress” pipeline is reported in the compression literature to disrupt the spectral coherence of the learned feature manifold and to require costly fine-tuning to restore fidelity. We study an alternative, training-time approach that re-parameterizes the convolutional kernel with CANDECOMP/PARAFAC (CP) decomposition into three low-rank sublayers, optimizing directly on a rank-constrained manifold rather than compressing after convergence. We interpret the forward pass as a heuristic realization, rather than a formal equivalence, of a proximal gradient-descent–ADMM update for a tensor nuclear-norm-regularized problem, which motivates the design and its hyperparameters without invoking expensive singular value decompositions. An analysis of parameter complexity and gradient flow justifies the choice of CP over Tucker and tensor-train decompositions. Experiments on DIV2K, Kodak24, BSD100, and Set12 show that the CP module yields a M-parameter lightweight model at parity with a same-budget reduced residual baseline (at most dB difference on every test set), sacrificing roughly half a decibel relative to a larger residual baseline. Applied to a large-capacity SR backbone, the same module removes of the parameters, from M to M, at a PSNR cost of only – dB. These results indicate that training-time CP decomposition is a simple and parameter-efficient route to compact SR models in the extreme-compression regime. - Open Access
- 11 November 2025
- Published by MDPI AG in Mathematics
- Vol. 13 (22) , 3607
PINN Based on Domain Adaptation for Solving Fornberg–Whitham-Type Equations
The Fornberg–Whitham equation, which contains high-order nonlinear derivatives, is widely recognized as a prominent model for describing shallow water dynamics. We explore physics-informed neural networks (PINsN) in conjunction with transfer learning technology to investigate numerical solutions for the FW equation. The proposed domain adaptation in transfer learning for PINN transforms the complex problem defined over the entire spatiotemporal domain into simpler problems defined over smaller subdomains. Training a neural network on these subdomains provides extra supervised learning data, effectively addressing optimization challenges associated with PINNs. Consequently, it enables the resolution of anisotropic and long-term predictive issues in these types of equations. Moreover, it enhances prediction accuracy and accelerates loss convergence by circumventing local optima in the specified scenarios. The method efficiently handles both forward and inverse FW equation problems, excelling in cost-effective accurate predictions for inverse problems. The efficiency and accuracy of our proposed approaches are demonstrated through examples and results.
- 11 November 2025
- Published by MDPI AG in Mathematics
- Vol. 13 (22) , 3607
Open AccessPINN Based on Domain Adaptation for Solving Fornberg–Whitham-Type Equations
The Fornberg–Whitham equation, which contains high-order nonlinear derivatives, is widely recognized as a prominent model for describing shallow water dynamics. We explore physics-informed neural networks (PINsN) in conjunction with transfer learning technology to investigate numerical solutions for the FW equation. The proposed domain adaptation in transfer learning for PINN transforms the complex problem defined over the entire spatiotemporal domain into simpler problems defined over smaller subdomains. Training a neural network on these subdomains provides extra supervised learning data, effectively addressing optimization challenges associated with PINNs. Consequently, it enables the resolution of anisotropic and long-term predictive issues in these types of equations. Moreover, it enhances prediction accuracy and accelerates loss convergence by circumventing local optima in the specified scenarios. The method efficiently handles both forward and inverse FW equation problems, excelling in cost-effective accurate predictions for inverse problems. The efficiency and accuracy of our proposed approaches are demonstrated through examples and results.