Distributed Online Big Data Classification Using Context Information

TL;DR

This paper introduces a distributed online classification framework for big data that leverages context information and models the problem as a distributed contextual bandit, providing theoretical performance guarantees.

Contribution

It presents a novel distributed online learning algorithm with proven sublinear regret for classification across multiple data sources, incorporating context-aware decision making.

Findings

Proposed a new distributed contextual bandit model for data classification.

Developed an online learning algorithm with proven sublinear regret.

First to analytically characterize performance of such distributed classification algorithms.

Abstract

Distributed, online data mining systems have emerged as a result of applications requiring analysis of large amounts of correlated and high-dimensional data produced by multiple distributed data sources. We propose a distributed online data classification framework where data is gathered by distributed data sources and processed by a heterogeneous set of distributed learners which learn online, at run-time, how to classify the different data streams either by using their locally available classification functions or by helping each other by classifying each other's data. Importantly, since the data is gathered at different locations, sending the data to another learner to process incurs additional costs such as delays, and hence this will be only beneficial if the benefits obtained from a better classification will exceed the costs. We model the problem of joint classification by the distributed and heterogeneous learners from multiple data sources as a distributed contextual bandit problem where each data is characterized by a specific context. We develop a distributed online learning algorithm for which we can prove sublinear regret. Compared to prior work in distributed online data mining, our work is the first to provide analytic regret results characterizing the performance of the proposed algorithm.