Concept Drift Detection from Multi-Class Imbalanced Data Streams

04/20/2021
by   Łukasz Korycki, et al.
0

Continual learning from data streams is among the most important topics in contemporary machine learning. One of the biggest challenges in this domain lies in creating algorithms that can continuously adapt to arriving data. However, previously learned knowledge may become outdated, as streams evolve over time. This phenomenon is known as concept drift and must be detected to facilitate efficient adaptation of the learning model. While there exists a plethora of drift detectors, all of them assume that we are dealing with roughly balanced classes. In the case of imbalanced data streams, those detectors will be biased towards the majority classes, ignoring changes happening in the minority ones. Furthermore, class imbalance may evolve over time and classes may change their roles (majority becoming minority and vice versa). This is especially challenging in the multi-class setting, where relationships among classes become complex. In this paper, we propose a detailed taxonomy of challenges posed by concept drift in multi-class imbalanced data streams, as well as a novel trainable concept drift detector based on Restricted Boltzmann Machine. It is capable of monitoring multiple classes at once and using reconstruction error to detect changes in each of them independently. Our detector utilizes a skew-insensitive loss function that allows it to handle multiple imbalanced distributions. Due to its trainable nature, it is capable of following changes in a stream and evolving class roles, as well as it can deal with local concept drift occurring in minority classes. Extensive experimental study on multi-class drifting data streams, enriched with a detailed analysis of the impact of local drifts and changing imbalance ratios, confirms the high efficacy of our approach.

READ FULL TEXT

page 1

page 3

page 4

research
09/20/2020

Adversarial Concept Drift Detection under Poisoning Attacks for Robust Data Stream Mining

Continuous learning from streaming data is among the most challenging to...
research
10/15/2022

The Influence of Multiple Classes on Learning Online Classifiers from Imbalanced and Concept Drifting Data Streams

This work is aimed at the experimental studying the influence of local d...
research
12/29/2020

Drift-Aware Multi-Memory Model for Imbalanced Data Streams

Online class imbalance learning deals with data streams that are affecte...
research
09/27/2018

Queue-based Resampling for Online Class Imbalance Learning

Online class imbalance learning constitutes a new problem and an emergin...
research
10/10/2022

Tracking changes using Kullback-Leibler divergence for the continual learning

Recently, continual learning has received a lot of attention. One of the...
research
03/15/2022

Improved Multi-label Classification under Temporal Concept Drift: Rethinking Group-Robust Algorithms in a Label-Wise Setting

In document classification for, e.g., legal and biomedical text, we ofte...
research
06/21/2023

An efficient and straightforward online quantization method for a data stream through remove-birth updating

The growth of network-connected devices is creating an explosion of data...

Please sign up or login with your details

Forgot password? Click here to reset