Home
Scholarly Works
TeamNet: A Collaborative Inference Framework on...
Conference

TeamNet: A Collaborative Inference Framework on the Edge

Abstract

With significant increases in wireless link capacity, edge devices are more connected than ever, which makes possible forming artificial neural network (ANN) federations on the connected edge devices. Partition is the key to the success of distributed ANN inference while unsolved because of the unclear knowledge representation in most of the ANN models. We propose a novel partition approach (TeamNet) based on the psychologically-plausible competitive and selective learning schemes while evaluating its performance carefully with thorough comparisons to other existing distributed machine learning approaches. Our experiments demonstrate that TeamNet with sockets and transmission control protocol (TCP) significantly outperforms sophisticated message passing interface (MPI) approaches and the state-of-the-art mixture of experts (MoE) approaches. The response time of ANN inference is shortened by as much as 53% without compromising predictive accuracy. TeamNet is promising for having distributed ANN inference on connected edge devices and forming edge intelligence for future applications.

Authors

Fang Y; Jin Z; Zheng R

Volume

00

Pagination

pp. 1487-1496

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Publication Date

July 7, 2019

DOI

10.1109/icdcs.2019.00148

Name of conference

2019 IEEE 39th International Conference on Distributed Computing Systems (ICDCS)
View published work (Non-McMaster Users)

Contact the Experts team