Complex graph stream mining
Shirui Pan · UTS ePRESS (University of Technology Sydney) · 2015
Recent years have witnessed a dramatic increase of information due to the ever development of modern technologies.The large scale of information makes data analysis, particularly data mining and knowledge discovery tasks, unprecedentedly challenging.First, data is becoming more and more interconnected.In a variety of domains such as social networks, chemical compounds, and XML documents, data is no longer represented by a flat table with instance-feature format, but exhibits complex structures indicating dependency relationships.Second, data is evolving more and more dynamically.Emerging applications such as social networks continuously generate information over time.Third, the learning tasks in many real-life applications become more and more complicated in that there are various constraints on the number of labelled data, class distributions, misclassification costs, or the number of learning tasks etc. LIST OF TABLES8.5 Running statistics w.r.t different K values for MTG-ℓ 21 (50 training graphs for each task, S max = 150) . . . . . . . . . . . . . . . .192 8.6 Results w.r.t.different γ values for MTG-ℓ 1 (50 training graphs for each task, S max = 15) . . . . . . . . . .