Feedforward Neural Networks for Caching: Enough or Too Much?
Networking and Internet Architecture
2018-10-17 v1
Abstract
We propose a caching policy that uses a feedforward neural network (FNN) to predict content popularity. Our scheme outperforms popular eviction policies like LRU or ARC, but also a new policy relying on the more complex recurrent neural networks. At the same time, replacing the FNN predictor with a naive linear estimator does not degrade caching performance significantly, questioning then the role of neural networks for these applications.
Cite
@article{arxiv.1810.06930,
title = {Feedforward Neural Networks for Caching: Enough or Too Much?},
author = {Vladyslav Fedchenko and Giovanni Neglia and Bruno Ribeiro},
journal= {arXiv preprint arXiv:1810.06930},
year = {2018}
}