AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

To Fold or Not to Fold: Graph Regularized Tensor Train for Visual Data Completion

Le Xu, Lei Cheng, Ngai Wong, Yik‐Chung Wu

TPAMI 2025 · Graph learning › Graph algorithms and clustering · approach: Graph embedding and spectral sparsification · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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 changedWhereMeasuredEffect
not folding the tensor, using graph regularization (GraphTT-VI) instead of folding (ablation)GraphTT-VI · Image completion, airplane, 90% missingPSNR (dB): 22.14 -> 23.34Improved
not folding the tensor, using graph regularization (GraphTT-VI) instead of folding (ablation)GraphTT-VI · Image completion, facade, 90% missingPSNR (dB): 20.38 -> 27.14Improved
not folding the tensor, using graph regularization (GraphTT-VI) instead of folding (ablation)GraphTT-VI · Image completion, barbara, 90% missingPSNR (dB): 22.90 -> 24.29Improved
add graph regularization without folding on TMAC-TT style completion (GraphTT-VI vs TMAC-TT with ket-folding)TT completion · airplane, 60% missing entriesPSNR (dB): 24.75 -> 29.81Improved
remove folding from TMAC-TT without adding graph regularizationTMAC-TT · airplane, 60% missing entriesPSNR (dB): 24.75 -> 22.69Hurt
add TV regularization to folded TT completion (TTC-TV vs TMAC-TT)TMAC-TT · airplane, 60% missing entriesPSNR (dB): 24.75 -> 23.87Hurt
use Bayesian VI (GraphTT-VI) instead of optimization with manual parameters (GraphTT-opt)GraphTT-opt · Image completion, facade, 90% missingPSNR (dB): 26.10 -> 27.14Improved
use Bayesian VI (GraphTT-VI) instead of GraphTT-optGraphTT-opt · Image completion, barbara, 90% missingPSNR (dB): 24.38 -> 24.29No clear effect
increase regularization weight beta0 to 5 from 0.5 (ablation)GraphTT-opt · synthetic TT data, SNR 10dB, 90% missingRSEHurt
increase initial TT rank from 5 to 15 (ablation)GraphTT-opt · synthetic TT data, SNR 10dB, 90% missingRSE: 5 -> 15Hurt
increase initial TT rank from 5 to 15 (ablation)GraphTT-VI · synthetic TT data, SNR 10dB, 90% missingRSE: 5 -> 15No clear effect
update TT core fibers instead of whole TT cores (ablation)GraphTT-opt · synthetic TT dataRSE and time per iterationImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy