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.
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
ViT-based semantic communications yields +0.5 dB PSNR over CNN baselines, introduces cosine-similarity and Fourier analysis metrics, and demonstrates an SDR prototype.
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.
-
On the Role of ViT and CNN in Semantic Communications: Analysis and Prototype Validation
ViT-based semantic communications yields +0.5 dB PSNR over CNN baselines, introduces cosine-similarity and Fourier analysis metrics, and demonstrates an SDR prototype.