The goal of this thesis subject, is to devise novel approaches for very lightweight GCN design that gathers the advantage of both structured and unstructured pruning, and discards their inconvenient; i.e., the proposed methods should impose constraints on the structure of the learned sub-networks (namely their topological consistency) while also ensuring their flexibility at some extent. The proposed solutions may consider network connections using different criteria (highest magnitudes, connectivity and predefined topologies, etc.) while guaranteeing their accessibility (i.e., their reachability from neural network inputs) and their co-accessibility (i.e., their actual contribution in the evaluation of neural network outputs) . Hence, only topologically consistent sub-networks should be considered when selecting network connections. Applications include image classification and human action recognition in large video collections. We consider both raw videos and already extracted skeleton data described with graphs, where nodes correspond to human joints, and edges to their spatial and temporal relationships.
This PhD research project has been submitted for a funding request to “Ecole Doctorale d‘Informatique, Télécommunication et d‘Electronique (EDITE)”. The PhD candidate selected by the project leader will therefore participate in the project selection process (including a file and an interview) to obtain funding.