Distributed multi-task classification: a decentralized online learning approach

Chi Zhang

doi:10.1007/s10994-017-5676-y

Distributed multi-task classification: a decentralized online learning approach

2017-11-02

25

OA

AI

DOI：10.1007/s10994-017-5676-y

Original

Save

View PDF

Abstract

En 中文

Although dispersing one single task to distributed learning nodes has been intensively studied by the previous research, multi-task learning on distributed networks is still an area that has not been fully exploited, especially under decentralized settings. The challenge lies in the fact that different tasks may have different optimal learning weights while communication through the distributed network forces all tasks to converge to an unique classifier. In this paper, we present a novel algorithm to overcome this challenge and enable learning multiple tasks simultaneously on a decentralized distributed network. Specifically, the learning framework can be separated into two phases: (i) multi-task information is shared within each node on the first phase; (ii) communication between nodes then leads the whole network to converge to a common minimizer. Theoretical analysis indicates that our algorithm achieves a regret bound when compared with the best classifier in hindsight, which is further validated by experiments on both synthetic and real-world datasets.

Keywords:

Decentralized distributed learning

Multi-task learning

Online learning

Distributed multi-task classification: a decentralized online learning approach

Abstract

AI Summary

Journal

Organization