In a distributed computing environment, peers collaboratively learn to classify concepts of interest from each other. When external changes happen and their concepts drift, the peers should adapt to avoid increase in misclassification errors. The problem of adaptation becomes more difficult when the changes are asynchronous, i.e., when peers experience drifts at different times. We address this problem by developing an ensemble approach, PINE, that combines reactive adaptation via drift detection, and proactive handling of upcoming changes via early warning and adaptation across the peers. With empirical study on simulated and real-world data sets, we show that PINE handles asynchronous concept drifts better and faster than current state-of-the-art approaches, which have been designed to work in less challenging environments. In addition, PINE is parameter insensitive and incurs less communication cost while achieving better accuracy.
Accuracy, Adaptation models, Classification, Data models, Detectors, Distributed databases, Predictive models, Training, concept drift, distributed systems
Computer Sciences | Databases and Information Systems
Data Management and Analytics
IEEE Transactions on Knowledge and Data Engineering (TKDE)
ANG, Hock Hee; Gopalkrishnan, Vivek; Zliobaite, Indre; Pechenizkiy, Mykola; and HOI, Steven C. H..
Predictive Handling of Asynchronous Concept Drifts in Distributed Environments. (2013). IEEE Transactions on Knowledge and Data Engineering (TKDE). 25, (10), 2343-2355. Research Collection School Of Information Systems.
Available at: http://ink.library.smu.edu.sg/sis_research/2281
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.