Recent Advances on Distributed Unsupervised Learning

Rosato, Antonello; Altilio, Rosa; Panella, Massimo

doi:10.1007/978-3-319-33747-0_8

Cited by 6 publications

(1 citation statement)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are, however, many cases scenarios in which it is intriguing to engage in a more complex discussion with respect to how a model can be assessed when data is not found at a single point in space and time. Actually, decentralized and distributed learning techniques have being recently gaining traction in fields where data cannot be shared or moved [5], [6].…”

Section: Introductionmentioning

confidence: 99%

Hyperdimensional Computing for Efficient Distributed Classification with Randomized Neural Networks

Rosato,

Panella,

Kleyko

2021

Preprint

Self Cite

View full text Add to dashboard Cite

In the supervised learning domain, considering the recent prevalence of algorithms with high computational cost, the attention is steering towards simpler, lighter, and less computationally extensive training and inference approaches. In particular, randomized algorithms are currently having a resurgence, given their generalized elementary approach. By using randomized neural networks, we study distributed classification, which can be employed in situations were data cannot be stored at a central location nor shared. We propose a more efficient solution for distributed classification by making use of a lossy compression approach applied when sharing the local classifiers with other agents. This approach originates from the framework of hyperdimensional computing, and is adapted herein. The results of experiments on a collection of datasets demonstrate that the proposed approach has usually higher accuracy than local classifiers and getting close to the benchmark -the centralized classifier. This work can be considered as the first step towards analyzing the variegated horizon of distributed randomized neural networks.

show abstract

Section: Introductionmentioning

confidence: 99%