Efficient instance-based learning on data streams

Abstract

The processing of data streams in general and the mining of such streams in particular have recently attracted considerable attention in various research fields. A key problem in stream mining is to extend existing machine learning and data mining methods so as to meet the increased requirements imposed by the data stream scenario, including the ability to analyze incoming data in an online, incremental manner, to observe tight time and memory constraints, and to appropriately respond to changes of the data characteristics and underlying distributions, amongst others. This paper considers the problem of classification on data streams and develops an instance-based learning algorithm for that purpose. The experimental studies presented in the paper suggest that this algorithm has a number of desirable properties that are not, at least not as a whole, shared by currently existing alternatives. Notably, * Draft of a paper to appear in "Intelligent Data Analysis". our method is very flexible and thus able to adapt to an evolving environment quickly, a point of utmost importance in the data stream context. At the same time, the algorithm is relatively robust and thus applicable to streams with different characteristics.

Reliable All-Pairs Evolving Fuzzy Classifiers

“…f) Decision stump [52]: one-level decision trees that are updatable by appropriate counts in the information criterion; in addition, this classifier is available in the MOA tool. g) IB1 [45], [53]: an instanced-based classifier [54] where the reference update base is growing-for each classification query, the whole history is available instead of single snapshots of the data stream. We use this classifier from a WEKA tool to demonstrate a rigorous comparison of our novel approach compared with classifiers seeing all data at once.…”

Combining similarity in time and space for training set formation under concept drift

“…The idea is closely related to the work by Beringer and Hullermeier [3] and has the same limitations regarding following the current concept. The former work was presented four years later than the latter.…”

“…The issue of systematic training set selection in space under concept drift has been brought up in [3,[13][14][15][16][17]. Ganti et al [13] give a generic interpretation of systematic training data selection without a real plug-and-play algorithm.…”

“…Beringer and Hullermeier [3] organize training data into prototype clusters, referred to as case bases. In contrast to the peer works, they exclude the instances which are too similar to the ones already present in the training set.…”

“…Manipulating training set includes instance selection (e.g. training windows [2], selective sampling [3]), instance weighting [4] and dynamic feature selection [5]. Training set manipulation strategies are wrapper approaches in a sense that they can be used for online learning plugging in different types of base classifiers.…”