Mining Noisy Data Streams via a Discriminative Model

The two main challenges typically associated with mining data streams are concept drift and data contamination. To address these challenges, we seek learning techniques and models that are robust to noise and can adapt to changes in timely fashion. In this paper, we approach the stream-mining problem using a statistical estimation framework, and propose a discriminative model for fast mining of noisy data streams. We build an ensemble of classifiers to achieve adaptation by weighting classifiers in a way that maximizes the likelihood of the data. We further employ robust statistical techniques to alleviate the problem of noise sensitivity. Experimental results on both synthetic and real-life data sets demonstrate the effectiveness of this new discriminative model. keywords. Data mining, discriminative modelling, robust statistics, logistic regression

• Type: Conference
• Year: 2004
• Where: DIS
• Authors: Fang Chu, Yizhou Wang, Carlo Zaniolo
• Keywords: Data Streams, DIS 2004, Discriminative Model, Mining Data Streams