Bilevel Online Deep Learning in Non-stationary Environment

by   Ya-nan Han, et al.

Recent years have witnessed enormous progress of online learning. However, a major challenge on the road to artificial agents is concept drift, that is, the data probability distribution would change where the data instance arrives sequentially in a stream fashion, which would lead to catastrophic forgetting and degrade the performance of the model. In this paper, we proposed a new Bilevel Online Deep Learning (BODL) framework, which combine bilevel optimization strategy and online ensemble classifier. In BODL algorithm, we use an ensemble classifier, which use the output of different hidden layers in deep neural network to build multiple base classifiers, the important weights of the base classifiers are updated according to exponential gradient descent method in an online manner. Besides, we apply the similar constraint to overcome the convergence problem of online ensemble framework. Then an effective concept drift detection mechanism utilizing the error rate of classifier is designed to monitor the change of the data probability distribution. When the concept drift is detected, our BODL algorithm can adaptively update the model parameters via bilevel optimization and then circumvent the large drift and encourage positive transfer. Finally, the extensive experiments and ablation studies are conducted on various datasets and the competitive numerical results illustrate that our BODL algorithm is a promising approach.


page 1

page 2

page 3

page 4


Employing chunk size adaptation to overcome concept drift

Modern analytical systems must be ready to process streaming data and co...

Diverse Instances-Weighting Ensemble based on Region Drift Disagreement for Concept Drift Adaptation

Concept drift refers to changes in the distribution of underlying data a...

Drift anticipation with forgetting to improve evolving fuzzy system

Working with a non-stationary stream of data requires for the analysis s...

Adaptive Online Incremental Learning for Evolving Data Streams

Recent years have witnessed growing interests in online incremental lear...

Prototype-based classifiers in the presence of concept drift: A modelling framework

We present a modelling framework for the investigation of prototype-base...

Reinforcement Evolutionary Learning Method for self-learning

In statistical modelling the biggest threat is concept drift which makes...

Power Plant Performance Modeling with Concept Drift

Power plant is a complex and nonstationary system for which the traditio...

Please sign up or login with your details

Forgot password? Click here to reset