Sorry, you need to enable JavaScript to visit this website.

DeepCABAC - Plug&Play Compression of Neural Network Weights and Weight Updates

Citation Author(s):
David Neumann, Felix Sattler, Heiner Kirchhoffer, Simon Wiedemann, Karsten Müller, Heiko Schwarz, Thomas Wiegand, Detlev Marpe, Wojciech Samek
Submitted by:
David Neumann
Last updated:
18 November 2020 - 9:06am
Document Type:
Presentation Slides
Document Year:
2020
Event:
Presenters Name:
David Neumann

Abstract 

Abstract: 

An increasing number of distributed machine learning applications require efficient communication of neural network parameterizations. DeepCABAC, an algorithm in the current working draft of the emerging MPEG-7 part 17 standard for compression of neural networks for multimedia content description and analysis, has demonstrated high compression gains for a variety of neural network models. In this paper we propose a method for employing DeepCABAC in a Federated Learning scenario for the exchange of intermediate differential parameterizations. Furthermore, we discuss the efficiency of DeepCABAC when compressing trained neural networks. Our experiments on large neural networks show that in both scenarios, DeepCABAC achieves competitive compression rates, without degrading the network accuracy.

up
0 users have voted:

Dataset Files

DeepCABAC - Plug&Play Compression of Neural Network Weights and Weight Updates Presentation Slides.pdf

(43)