Tutorial outline (3h30) including 30 min break 


PART IMoamar Sayed-Mouchaweh


a. Context and motivations 

b. Concept drift applications 

c. Learning from data streams in static and dynamic environments 

Handling concept drift 

a. General scheme to handle concept drift 

b. Methods to handle concept drift 

c. Drift handling evaluation 

Break (15 min) 

PART IIHamid Bouchachia

Semi-supervised for data streams

Active learning for data streams

Distributed streaming for data streams

Break (15 min) 

PART III - Rita P. Ribeiro, João Gama

Novelty Detection

            a. One-class Classification

            b. Multi-class Novelty Detection

            c. Evaluation Issues

Evolving Social Networks  

            a. Events in Social Networks

            b. Tracking Events in Evolving Networks

Streaming Networks 

            a. Sampling Evolving Networks

            b. Incremental Community Detection


Conclusions and Future Trends