Relevant data expansion for learning concept drift from sparsely labeled data
Citations Over TimeTop 10% of 2005 papers
Abstract
Keeping track of changing interests is a natural phenomenon as well as an interesting tracking problem because interests can emerge and diminish at different time frames. Being able to do so with a few feedback examples poses an even more important and challenging problem because existing concept drift learning algorithms that handle the task typically suffer from it. This work presents a new computational framework for extending incomplete labeled data stream (FEILDS), which extends the capability of existing algorithms for learning concept drift from a few labeled data. The system transforms the original input stream into a new stream that can be conveniently tracked by the existing learning algorithms. The experiment results reveal that FEILDS can significantly improve the performances of a Multiple Three-Descriptor Representation (MTDR) algorithm, Rocchio algorithm, and window-based concept drift learning algorithms when learning from a sparsely labeled data stream with respect to their performances without using FEILDS.
Related Papers
- → Detecting group concept drift from multiple data streams(2022)65 cited
- → An Efficient Approach to Detect Concept Drifts in Data Streams(2017)10 cited
- → Towards Online Concept Drift Detection with Feature Selection for Data Stream Classification(2016)9 cited
- An Ensemble Classification Framework toEvolving Data Streams(2014)
- → A Review of Classification and Novel Class Detection Technique of Data Streams(2012)