The paper introduces CompJF and CompRandJF, federated Tucker-based reconstruction algorithms that aggregate clients via joint factorization and randomized sketching, claiming improved SSIM and communication efficiency on synthetic multimodal tomography.
Deep learning model compression with rank reduction in tensor decomposition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
contradiction 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
contradiction 1polarities
contest 1representative citing papers
citing papers explorer
-
Federated Low-Rank Tensor Estimation for Multimodal Image Reconstruction
The paper introduces CompJF and CompRandJF, federated Tucker-based reconstruction algorithms that aggregate clients via joint factorization and randomized sketching, claiming improved SSIM and communication efficiency on synthetic multimodal tomography.