TrimCaching introduces parameter-sharing edge caching for AI models, formulates it as a submodular maximization problem with submodular constraints, provides approximation algorithms for special and general cases, and shows improved cache hit ratios in simulations.
Pipelining split learning in multi-hop edge networks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.NI 2verdicts
UNVERDICTED 2representative citing papers
The paper derives the first convergence upper bound for split federated learning under activation upload, gradient download, and aggregation failures, then jointly optimizes client sampling and model splitting to minimize the bound, with simulations on EMNIST and CIFAR-10.
citing papers explorer
-
TrimCaching: Parameter-sharing Edge Caching for AI Model Downloading
TrimCaching introduces parameter-sharing edge caching for AI models, formulates it as a submodular maximization problem with submodular constraints, provides approximation algorithms for special and general cases, and shows improved cache hit ratios in simulations.
-
Optimizing Split Federated Learning with Unstable Client Participation
The paper derives the first convergence upper bound for split federated learning under activation upload, gradient download, and aggregation failures, then jointly optimizes client sampling and model splitting to minimize the bound, with simulations on EMNIST and CIFAR-10.