An Evolving Population Approach to Data-Stream Classification with Extreme Verification Latency
This addresses a critical challenge in data-stream mining for applications requiring real-time adaptation without labeled feedback, though it appears incremental as it builds on existing ensemble and one-class classifier methods.
The paper tackled the problem of maintaining classification accuracy in non-stationary data-streams with extreme verification latency, where no new labels are available after initial training, by proposing an evolving population-based approach using ensembles of one-class classifiers to adapt to changes.
Recognising and reacting to change in non-stationary data-streams is a challenging task. The majority of research in this area assumes that the true class label of incoming points are available, either at each time step or intermittently with some latency. In the worse case this latency approaches infinity and we can assume that no labels are available beyond the initial training set. When change is expected and no further training labels are provided the challenge of maintaining a high classification accuracy is very great. The challenge is to propagate the original training information through several timesteps, possibly indefinitely, while adapting to underlying change in the data-stream. In this paper we conduct an initial study into the effectiveness of using an evolving, population-based approach as the mechanism for adapting to change. An ensemble of one-class-classifiers is maintained for each class. Each classifier is considered as an agent in the sub-population and is subject to selection pressure to find interesting areas of the feature space. This selection pressure forces the ensemble to adapt to the underlying change in the data-stream.