Proposes FedACnnL for analytic layer-wise DNN training in federated settings and pFedACnnL for analytic personalized meta-learning, claiming 83-99% training time reduction and 4-8% accuracy gains over baselines with SOTA results in most tested cases.
Learning multiple layers of features from tiny images
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
The paper proposes a robust B-spline decoupling framework using constrained coupled matrix-tensor factorization and the R-CMTF-BSD algorithm for compressing Vision and Swin Transformer models.
citing papers explorer
-
Analytic Personalized Federated Meta-Learning
Proposes FedACnnL for analytic layer-wise DNN training in federated settings and pFedACnnL for analytic personalized meta-learning, claiming 83-99% training time reduction and 4-8% accuracy gains over baselines with SOTA results in most tested cases.
-
Robust Basis Spline Decoupling for the Compression of Transformer Models
The paper proposes a robust B-spline decoupling framework using constrained coupled matrix-tensor factorization and the R-CMTF-BSD algorithm for compressing Vision and Swin Transformer models.