Continual learning for adaptive social network identification

Simone Magistri, Daniele Baracchi, Dasara Shullani, Andrew D. Bagdanov, Alessandro Piva

Abstract: Highlights•We investigate continual learning methods for social network identification.•We exploit a state-of-the-art dual-branch neural network designed for this task.•We define two realistic experimental scenarios on multiple datasets.•Exemplar-based methods yield good performance with limited memory requirements.•Prototype-based methods are a viable solution when storing exemplars is not feasible.